首页 > 最新文献

Journal of Intelligent Information Systems最新文献

英文 中文
A motif-based probabilistic approach for community detection in complex networks 基于图案的概率方法,用于复杂网络中的群落检测
IF 3.4 3区 计算机科学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2024-03-16 DOI: 10.1007/s10844-024-00850-3
Hossein Hajibabaei, Vahid Seydi, Abbas Koochari

Community detection in complex networks is an important task for discovering hidden information in network analysis. Neighborhood density between nodes is one of the fundamental indicators of community presence in the network. A community with a high edge density will have correlations between nodes that extend beyond their immediate neighbors, denoted by motifs. Motifs are repetitive patterns of edges observed with high frequency in the network. We proposed the PCDMS method (Probabilistic Community Detection with Motif Structure) that detects communities by estimating the triangular motif in the network. This study employs structural density between nodes, a key concept in graph analysis. The proposed model has the advantage of using a probabilistic generative model that calculates the latent parameters of the probabilistic model and determines the community based on the likelihood of triangular motifs. The relationship between observing two pairs of nodes in multiple communities leads to an increasing likelihood estimation of the existence of a motif structure between them. The output of the proposed model is the intensity of each node in the communities. The efficiency and validity of the proposed method are evaluated through experimental work on both synthetic and real-world networks; the findings will show that the community identified by the proposed method is more accurate and dense than other algorithms with modularity, NMI, and F1score evaluation metrics.

复杂网络中的社群检测是网络分析中发现隐藏信息的一项重要任务。节点之间的邻接密度是网络中存在社群的基本指标之一。一个边缘密度高的群落,其节点之间的相关性会超出其近邻的范围,这就是所谓的 "主题"(Motifs)。主题是在网络中高频观察到的边缘重复模式。我们提出了 PCDMS 方法(带动机结构的概率社群检测),该方法通过估计网络中的三角形动机来检测社群。这项研究采用了节点间的结构密度,这是图分析中的一个关键概念。拟议模型的优势在于使用概率生成模型,计算概率模型的潜在参数,并根据三角形图案的可能性确定社群。通过观察多个社区中两对节点之间的关系,可以对它们之间是否存在图案结构进行可能性递增估计。拟议模型的输出是每个节点在群落中的强度。通过在合成网络和真实世界网络上进行实验,评估了所提方法的效率和有效性;实验结果将表明,与其他采用模块化、NMI 和 F1score 评估指标的算法相比,所提方法识别的群落更准确、更密集。
{"title":"A motif-based probabilistic approach for community detection in complex networks","authors":"Hossein Hajibabaei, Vahid Seydi, Abbas Koochari","doi":"10.1007/s10844-024-00850-3","DOIUrl":"https://doi.org/10.1007/s10844-024-00850-3","url":null,"abstract":"<p>Community detection in complex networks is an important task for discovering hidden information in network analysis. Neighborhood density between nodes is one of the fundamental indicators of community presence in the network. A community with a high edge density will have correlations between nodes that extend beyond their immediate neighbors, denoted by motifs. Motifs are repetitive patterns of edges observed with high frequency in the network. We proposed the PCDMS method (Probabilistic Community Detection with Motif Structure) that detects communities by estimating the triangular motif in the network. This study employs structural density between nodes, a key concept in graph analysis. The proposed model has the advantage of using a probabilistic generative model that calculates the latent parameters of the probabilistic model and determines the community based on the likelihood of triangular motifs. The relationship between observing two pairs of nodes in multiple communities leads to an increasing likelihood estimation of the existence of a motif structure between them. The output of the proposed model is the intensity of each node in the communities. The efficiency and validity of the proposed method are evaluated through experimental work on both synthetic and real-world networks; the findings will show that the community identified by the proposed method is more accurate and dense than other algorithms with modularity, NMI, and F1score evaluation metrics.</p>","PeriodicalId":56119,"journal":{"name":"Journal of Intelligent Information Systems","volume":"16 1","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140149819","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Early detection of fake news on emerging topics through weak supervision 通过薄弱监管及早发现新兴话题的假新闻
IF 3.4 3区 计算机科学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2024-03-15 DOI: 10.1007/s10844-024-00852-1
Serhat Hakki Akdag, Nihan Kesim Cicekli

In this paper, we present a methodology for the early detection of fake news on emerging topics through the innovative application of weak supervision. Traditional techniques for fake news detection often rely on fact-checkers or supervised learning with labeled data, which is not readily available for emerging topics. To address this, we introduce the Weakly Supervised Text Classification framework (WeSTeC), an end-to-end solution designed to programmatically label large-scale text datasets within specific domains and train supervised text classifiers using the assigned labels. The proposed framework automatically generates labeling functions through multiple weak labeling strategies and eliminates underperforming ones. Labels assigned through the generated labeling functions are then used to fine-tune a pre-trained RoBERTa classifier for fake news detection. By using a weakly labeled dataset, which contains fake news related to the emerging topic, the trained fake news detection model becomes specialized for the topic under consideration. We explore both semi-supervision and domain adaptation setups, utilizing small amounts of labeled data and labeled data from other domains, respectively. The fake news classification model generated by the proposed framework excels when compared with all baselines in both setups. In addition, when compared to its fully supervised counterpart, our fake news detection model trained through weak labels achieves accuracy within 1%, emphasizing the robustness of the proposed framework’s weak labeling capabilities.

在本文中,我们提出了一种通过创新应用弱监督来早期检测新兴话题假新闻的方法。传统的假新闻检测技术通常依赖于事实核查人员或有标注数据的监督学习,而对于新兴话题来说,这些数据并不容易获得。为了解决这个问题,我们推出了弱监督文本分类框架(WeSTeC),这是一个端到端的解决方案,旨在以编程方式为特定领域内的大规模文本数据集贴标签,并使用分配的标签训练监督文本分类器。所提出的框架通过多种弱标签策略自动生成标签函数,并消除表现不佳的标签。然后,通过生成的标签函数分配的标签被用于微调预训练的 RoBERTa 分类器,以检测假新闻。通过使用弱标签数据集(其中包含与新兴话题相关的假新闻),经过训练的假新闻检测模型变得专门针对所考虑的话题。我们探索了半监督和领域适应设置,分别利用了少量标记数据和来自其他领域的标记数据。在这两种设置中,与所有基线相比,拟议框架生成的假新闻分类模型都非常出色。此外,与完全监督的假新闻检测模型相比,我们通过弱标签训练的假新闻检测模型的准确率在 1%以内,强调了所提出框架的弱标签功能的鲁棒性。
{"title":"Early detection of fake news on emerging topics through weak supervision","authors":"Serhat Hakki Akdag, Nihan Kesim Cicekli","doi":"10.1007/s10844-024-00852-1","DOIUrl":"https://doi.org/10.1007/s10844-024-00852-1","url":null,"abstract":"<p>In this paper, we present a methodology for the early detection of fake news on emerging topics through the innovative application of weak supervision. Traditional techniques for fake news detection often rely on fact-checkers or supervised learning with labeled data, which is not readily available for emerging topics. To address this, we introduce the Weakly Supervised Text Classification framework (WeSTeC), an end-to-end solution designed to programmatically label large-scale text datasets within specific domains and train supervised text classifiers using the assigned labels. The proposed framework automatically generates labeling functions through multiple weak labeling strategies and eliminates underperforming ones. Labels assigned through the generated labeling functions are then used to fine-tune a pre-trained RoBERTa classifier for fake news detection. By using a weakly labeled dataset, which contains fake news related to the emerging topic, the trained fake news detection model becomes specialized for the topic under consideration. We explore both semi-supervision and domain adaptation setups, utilizing small amounts of labeled data and labeled data from other domains, respectively. The fake news classification model generated by the proposed framework excels when compared with all baselines in both setups. In addition, when compared to its fully supervised counterpart, our fake news detection model trained through weak labels achieves accuracy within 1%, emphasizing the robustness of the proposed framework’s weak labeling capabilities.</p>","PeriodicalId":56119,"journal":{"name":"Journal of Intelligent Information Systems","volume":"186 1","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140149966","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A hybrid recognition framework of crucial seed spreaders in complex networks with neighborhood overlap 具有邻域重叠的复杂网络中关键种子传播者的混合识别框架
IF 3.4 3区 计算机科学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2024-03-15 DOI: 10.1007/s10844-024-00849-w
Tianchi Tong, Min Wang, Wenying Yuan, Qian Dong, Jinsheng Sun, Yuan Jiang

Recognizing crucial seed spreaders of complex networks is an open issue that studies the dynamic spreading process and analyzes the performance of networks. However, most of the findings design the hierarchical model based on nodes’ degree such as Kshell decomposition for obtaining global information, and identifying effects brought by the weight value of each layer is coarse. In addition, local structural information fails to be effectively captured when neighborhood nodes are sometimes unconnected in the hierarchical structure. To solve these issues, in this paper, we design a novel hierarchical structure based on the shortest path distance by using the interpretative structure model and determine influence weights of each layer. Furthermore, we also design the local neighborhood overlap coefficient and the local index based on the overlap (LIO) by considering two conditions of connected and unconnected neighborhood nodes in the hierarchical structure. For reaching a comprehensive recognition and finding crucial seed spreaders precisely, we introduce influence weights vector, local evaluation index matrix after normalization and the weight vector of local indexes into a new hybrid recognition framework. The proposed method adopts a series of indicators, including the monotonicity relation, Susceptible-Infected-Susceptible model, complementary cumulative distribution function, Kendall’s coefficient, spreading scale ratio and average shortest path length, to execute corresponding experiments and evaluate the diffusion ability in different datasets. Results demonstrate that, our method outperforms involved algorithms in the recognition effects and spreading capability.

识别复杂网络中的关键种子传播者是一个研究动态传播过程和分析网络性能的开放性课题。然而,大多数研究结果都是基于节点度(如 Kshell 分解)设计分层模型来获取全局信息,而识别各层权重值带来的影响则比较粗糙。此外,在分层结构中,邻近节点有时是不相连的,因此无法有效捕捉局部结构信息。为了解决这些问题,本文利用解释性结构模型设计了一种基于最短路径距离的新型分层结构,并确定了各层的影响权重。此外,我们还考虑了分层结构中连接邻域节点和非连接邻域节点两种情况,设计了局部邻域重叠系数和基于重叠的局部指数(LIO)。为了达到全面识别和精确找到关键种子传播者的目的,我们在新的混合识别框架中引入了影响权重向量、归一化后的局部评价指标矩阵和局部指标权重向量。该方法采用单调性关系、易感-易染-易感模型、互补累积分布函数、肯德尔系数、传播规模比和平均最短路径长度等一系列指标,在不同数据集中进行相应的实验和扩散能力评估。结果表明,我们的方法在识别效果和传播能力上都优于相关算法。
{"title":"A hybrid recognition framework of crucial seed spreaders in complex networks with neighborhood overlap","authors":"Tianchi Tong, Min Wang, Wenying Yuan, Qian Dong, Jinsheng Sun, Yuan Jiang","doi":"10.1007/s10844-024-00849-w","DOIUrl":"https://doi.org/10.1007/s10844-024-00849-w","url":null,"abstract":"<p>Recognizing crucial seed spreaders of complex networks is an open issue that studies the dynamic spreading process and analyzes the performance of networks. However, most of the findings design the hierarchical model based on nodes’ degree such as Kshell decomposition for obtaining global information, and identifying effects brought by the weight value of each layer is coarse. In addition, local structural information fails to be effectively captured when neighborhood nodes are sometimes unconnected in the hierarchical structure. To solve these issues, in this paper, we design a novel hierarchical structure based on the shortest path distance by using the interpretative structure model and determine influence weights of each layer. Furthermore, we also design the local neighborhood overlap coefficient and the local index based on the overlap (LIO) by considering two conditions of connected and unconnected neighborhood nodes in the hierarchical structure. For reaching a comprehensive recognition and finding crucial seed spreaders precisely, we introduce influence weights vector, local evaluation index matrix after normalization and the weight vector of local indexes into a new hybrid recognition framework. The proposed method adopts a series of indicators, including the monotonicity relation, Susceptible-Infected-Susceptible model, complementary cumulative distribution function, Kendall’s coefficient, spreading scale ratio and average shortest path length, to execute corresponding experiments and evaluate the diffusion ability in different datasets. Results demonstrate that, our method outperforms involved algorithms in the recognition effects and spreading capability.</p>","PeriodicalId":56119,"journal":{"name":"Journal of Intelligent Information Systems","volume":"9 1","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140149906","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Ensemble of temporal Transformers for financial time series 金融时间序列的时间变换器集合
IF 3.4 3区 计算机科学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2024-03-02 DOI: 10.1007/s10844-024-00851-2
Kenniy Olorunnimbe, Herna Viktor

The accuracy of price forecasts is important for financial market trading strategies and portfolio management. Compared to traditional models such as ARIMA and other state-of-the-art deep learning techniques, temporal Transformers with similarity embedding perform better for multi-horizon forecasts in financial time series, as they account for the conditional heteroscedasticity inherent in financial data. Despite this, the methods employed in generating these forecasts must be optimized to achieve the highest possible level of precision. One approach that has been shown to improve the accuracy of machine learning models is ensemble techniques. To this end, we present an ensemble approach that efficiently utilizes the available data over an extended timeframe. Our ensemble combines multiple temporal Transformer models learned within sliding windows, thereby making optimal use of the data. As combination methods, along with an averaging approach, we also introduced a stacking meta-learner that leverages a quantile estimator to determine the optimal weights for combining the base models of smaller windows. By decomposing the constituent time series of an extended timeframe, we optimize the utilization of the series for financial deep learning. This simplifies the training process of a temporal Transformer model over an extended time series while achieving better performance, particularly when accounting for the non-constant variance of financial time series. Our experiments, conducted across volatile and non-volatile extrapolation periods, using 20 companies from the Dow Jones Industrial Average show more than 40% and 60% improvement in predictive performance compared to the baseline temporal Transformer.

价格预测的准确性对于金融市场交易策略和投资组合管理非常重要。与 ARIMA 等传统模型和其他最先进的深度学习技术相比,具有相似性嵌入的时空变换器在金融时间序列的多视距预测方面表现更好,因为它们考虑到了金融数据固有的条件异方差性。尽管如此,生成这些预测的方法必须进行优化,以达到尽可能高的精度。已证明能提高机器学习模型准确性的一种方法是集合技术。为此,我们提出了一种集合方法,可有效利用扩展时间范围内的可用数据。我们的集合方法结合了在滑动窗口内学习的多个时间 Transformer 模型,从而优化了数据的使用。作为组合方法,除了平均方法,我们还引入了堆叠元学习器,利用量子估计器来确定组合较小窗口基础模型的最佳权重。通过分解扩展时间框架的组成时间序列,我们优化了金融深度学习对序列的利用。这简化了扩展时间序列上时序变换器模型的训练过程,同时实现了更好的性能,尤其是在考虑到金融时间序列的非恒定方差时。我们使用道琼斯工业平均指数中的 20 家公司,在波动和非波动外推期进行了实验,结果表明,与基线时空变换器相比,预测性能分别提高了 40% 和 60% 以上。
{"title":"Ensemble of temporal Transformers for financial time series","authors":"Kenniy Olorunnimbe, Herna Viktor","doi":"10.1007/s10844-024-00851-2","DOIUrl":"https://doi.org/10.1007/s10844-024-00851-2","url":null,"abstract":"<p>The accuracy of price forecasts is important for financial market trading strategies and portfolio management. Compared to traditional models such as ARIMA and other state-of-the-art deep learning techniques, temporal Transformers with similarity embedding perform better for multi-horizon forecasts in financial time series, as they account for the conditional heteroscedasticity inherent in financial data. Despite this, the methods employed in generating these forecasts must be optimized to achieve the highest possible level of precision. One approach that has been shown to improve the accuracy of machine learning models is ensemble techniques. To this end, we present an ensemble approach that efficiently utilizes the available data over an extended timeframe. Our ensemble combines multiple temporal Transformer models learned within sliding windows, thereby making optimal use of the data. As combination methods, along with an averaging approach, we also introduced a stacking meta-learner that leverages a quantile estimator to determine the optimal weights for combining the base models of smaller windows. By decomposing the constituent time series of an extended timeframe, we optimize the utilization of the series for financial deep learning. This simplifies the training process of a temporal Transformer model over an extended time series while achieving better performance, particularly when accounting for the non-constant variance of financial time series. Our experiments, conducted across volatile and non-volatile extrapolation periods, using 20 companies from the Dow Jones Industrial Average show more than 40% and 60% improvement in predictive performance compared to the baseline temporal Transformer.</p>","PeriodicalId":56119,"journal":{"name":"Journal of Intelligent Information Systems","volume":"1 1","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140017636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Enhancing sentiment and emotion translation of review text through MLM knowledge integration in NMT 通过在 NMT 中整合 MLM 知识,加强评论文本的情感和情绪翻译
IF 3.4 3区 计算机科学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2024-02-29 DOI: 10.1007/s10844-024-00843-2
Divya Kumari, Asif Ekbal

Producing a high-quality review translation is a multifaceted process. It goes beyond successful semantic transfer and requires conveying the original message’s tone and style in a way that resonates with the target audience, whether they are human readers or Natural Language Processing (NLP) applications. Capturing these subtle nuances of the review text demands a deeper understanding and better encoding of the source message. In order to achieve this goal, we explore the use of self-supervised masked language modeling (MLM) and a variant called polarity masked language modeling (p-MLM) as auxiliary tasks in a multi-learning setup. MLM is widely recognized for its ability to capture rich linguistic representations of the input and has been shown to achieve state-of-the-art accuracy in various language understanding tasks. Motivated by its effectiveness, in this paper we adopt joint learning, combining the neural machine translation (NMT) task with source polarity-masked language modeling within a shared embedding space to induce a deeper understanding of the emotional nuances of the text. We analyze the results and observe that our multi-task model indeed exhibits a better understanding of linguistic concepts like sentiment and emotion. Intriguingly, this is achieved even without explicit training on sentiment-annotated or domain-specific sentiment corpora. Our multi-task NMT model consistently improves the translation quality of affect sentences from diverse domains in three language pairs.

高质量的评论翻译是一个多方面的过程。它不仅仅是成功的语义转换,还要求以一种能与目标受众(无论是人类读者还是自然语言处理 (NLP) 应用程序)产生共鸣的方式传达原始信息的语气和风格。要捕捉评论文本中这些细微的差别,就需要对源信息有更深入的理解和更好的编码。为了实现这一目标,我们探索了在多重学习设置中使用自监督掩蔽语言建模(MLM)和称为极性掩蔽语言建模(p-MLM)的变体作为辅助任务。MLM 因其捕捉输入的丰富语言表征的能力而得到广泛认可,并已被证明在各种语言理解任务中达到了最先进的准确度。受其有效性的激励,我们在本文中采用了联合学习的方法,将神经机器翻译(NMT)任务与共享嵌入空间中的源极性掩蔽语言建模相结合,以加深对文本情感细微差别的理解。我们对结果进行了分析,发现我们的多任务模型确实能更好地理解情感和情绪等语言概念。耐人寻味的是,即使没有对情感注释或特定领域的情感语料库进行明确的训练,我们也能做到这一点。我们的多任务 NMT 模型在三种语言对中持续提高了来自不同领域的情感句子的翻译质量。
{"title":"Enhancing sentiment and emotion translation of review text through MLM knowledge integration in NMT","authors":"Divya Kumari, Asif Ekbal","doi":"10.1007/s10844-024-00843-2","DOIUrl":"https://doi.org/10.1007/s10844-024-00843-2","url":null,"abstract":"<p>Producing a high-quality review translation is a multifaceted process. It goes beyond successful semantic transfer and requires conveying the original message’s tone and style in a way that resonates with the target audience, whether they are human readers or Natural Language Processing (NLP) applications. Capturing these subtle nuances of the review text demands a deeper understanding and better encoding of the source message. In order to achieve this goal, we explore the use of self-supervised masked language modeling (MLM) and a variant called polarity masked language modeling (p-MLM) as auxiliary tasks in a multi-learning setup. MLM is widely recognized for its ability to capture rich linguistic representations of the input and has been shown to achieve state-of-the-art accuracy in various language understanding tasks. Motivated by its effectiveness, in this paper we adopt joint learning, combining the neural machine translation (NMT) task with source polarity-masked language modeling within a shared embedding space to induce a deeper understanding of the emotional nuances of the text. We analyze the results and observe that our multi-task model indeed exhibits a better understanding of linguistic concepts like sentiment and emotion. Intriguingly, this is achieved even without explicit training on sentiment-annotated or domain-specific sentiment corpora. Our multi-task NMT model consistently improves the translation quality of affect sentences from diverse domains in three language pairs.</p>","PeriodicalId":56119,"journal":{"name":"Journal of Intelligent Information Systems","volume":"135 1","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-02-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140010850","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
CMC-MMR: multi-modal recommendation model with cross-modal correction CMC-MMR:跨模态校正的多模态推荐模型
IF 3.4 3区 计算机科学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2024-02-20 DOI: 10.1007/s10844-024-00848-x

Abstract

Multi-modal recommendation using multi-modal features (e.g., image and text features) has received significant attention and has been shown to have more effective recommendation. However, there are currently the following problems with multi-modal recommendation: (1) Multi-modal recommendation often handle individual modes’ raw data directly, leading to noise affecting the model’s effectiveness and the failure to explore interconnections between modes; (2) Different users have different preferences. It’s impractical to treat all modalities equally, as this could interfere with the model’s ability to make recommendation. To address the above problems, this paper proposes a Multi-modal recommendation model with cross-modal correction (CMC-MMR). Firstly, in order to reduce the effect of noise in the raw data and to take full advantage of the relationships between modes, we designed a cross-modal correction module to denoise and correct the modes using a cross-modal correction mechanism; Secondly, the similarity between the same modalities of each item is used as a benchmark to build item-item graphs for each modality, and user-item graphs with degree-sensitive pruning strategies are also built to mine higher-order information; Finally, we designed a self-supervised task to adaptively mine user preferences for modality. We conducted comparative experiments with eleven baseline models on four real-world datasets. The experimental results show that CMC-MMR improves 6.202%, 4.975% , 6.054% and 11.368% on average on the four datasets, respectively, demonstrates the effectiveness of CMC-MMR.

摘要 使用多模态特征(如图像和文本特征)的多模态推荐已受到广泛关注,并被证明具有更高的推荐效率。然而,多模态推荐目前存在以下问题:(1)多模态推荐通常直接处理单个模态的原始数据,导致噪声影响模型的有效性,并且无法探索模态之间的内在联系;(2)不同用户有不同的偏好。对所有模式一视同仁是不切实际的,因为这会影响模型的推荐能力。针对上述问题,本文提出了一种具有跨模态修正功能的多模态推荐模型(CMC-MMR)。首先,为了降低原始数据中噪声的影响,并充分利用模态之间的关系,我们设计了一个跨模态校正模块,利用跨模态校正机制对模态进行去噪和校正;其次,以每个条目相同模态之间的相似度为基准,为每种模态建立条目-条目图,同时建立具有程度敏感剪枝策略的用户-条目图,以挖掘高阶信息;最后,我们设计了一个自监督任务,以自适应地挖掘用户对模态的偏好。我们在四个真实数据集上与 11 个基准模型进行了对比实验。实验结果表明,CMC-MMR 在四个数据集上的平均提升率分别为 6.202%、4.975%、6.054% 和 11.368%,证明了 CMC-MMR 的有效性。
{"title":"CMC-MMR: multi-modal recommendation model with cross-modal correction","authors":"","doi":"10.1007/s10844-024-00848-x","DOIUrl":"https://doi.org/10.1007/s10844-024-00848-x","url":null,"abstract":"<h3>Abstract</h3> <p>Multi-modal recommendation using multi-modal features (e.g., image and text features) has received significant attention and has been shown to have more effective recommendation. However, there are currently the following problems with multi-modal recommendation: (1) Multi-modal recommendation often handle individual modes’ raw data directly, leading to noise affecting the model’s effectiveness and the failure to explore interconnections between modes; (2) Different users have different preferences. It’s impractical to treat all modalities equally, as this could interfere with the model’s ability to make recommendation. To address the above problems, this paper proposes a <span>M</span>ulti-<span>m</span>odal <span>r</span>ecommendation model with <span>c</span>ross-<span>m</span>odal <span>c</span>orrection (CMC-MMR). Firstly, in order to reduce the effect of noise in the raw data and to take full advantage of the relationships between modes, we designed a cross-modal correction module to denoise and correct the modes using a cross-modal correction mechanism; Secondly, the similarity between the same modalities of each item is used as a benchmark to build item-item graphs for each modality, and user-item graphs with degree-sensitive pruning strategies are also built to mine higher-order information; Finally, we designed a self-supervised task to adaptively mine user preferences for modality. We conducted comparative experiments with eleven baseline models on four real-world datasets. The experimental results show that CMC-MMR improves 6.202%, 4.975% , 6.054% and 11.368% on average on the four datasets, respectively, demonstrates the effectiveness of CMC-MMR.</p>","PeriodicalId":56119,"journal":{"name":"Journal of Intelligent Information Systems","volume":"4 1","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139918440","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Querying knowledge graphs through positive and negative examples and feedback 通过正反实例和反馈查询知识图谱
IF 3.4 3区 计算机科学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2024-02-15 DOI: 10.1007/s10844-024-00846-z
Akritas Akritidis, Yannis Tzitzikas

The formulation of structured queries over Knowledge Graphs is not an easy task. To alleviate this problem, we propose a novel interactive method for SPARQL query formulation, for enabling users (plain and advanced) to formulate gradually queries by providing examples and various kinds of positive and negative feedback, in a manner that does not pre-suppose knowledge of the query language or the contents of the Knowledge Graph. In comparison to other example-based query approaches, distinctive features of our approach is the support of negative examples, and the positive/negative feedback on the generated constraints. We detail the algorithmic aspect and we present an interactive user interface that implements the approach. The application of the model on real datasets from DBpedia (Movies, Actors) and other datasets (scientific papers), showcases the feasibility and the effectiveness of the approach. A task-based evaluation that included users that are not familiar with SPARQL, provided positive evidence that the interaction is easy-to-grasp and enabled most users to formulate the desired queries.

对知识图谱进行结构化查询并非易事。为了缓解这一问题,我们提出了一种新颖的 SPARQL 查询交互式方法,通过提供示例和各种积极和消极反馈,使用户(普通用户和高级用户)能够以一种不预先假定查询语言或知识图谱内容知识的方式逐步提出查询。与其他基于示例的查询方法相比,我们的方法的显著特点是支持负面示例,并对生成的约束条件提供正面/负面反馈。我们详细介绍了算法方面的内容,并展示了实现该方法的交互式用户界面。该模型在 DBpedia 的真实数据集(电影、演员)和其他数据集(科学论文)上的应用展示了该方法的可行性和有效性。对不熟悉 SPARQL 的用户进行的基于任务的评估提供了积极的证据,证明这种交互方式易于掌握,大多数用户都能提出所需的查询。
{"title":"Querying knowledge graphs through positive and negative examples and feedback","authors":"Akritas Akritidis, Yannis Tzitzikas","doi":"10.1007/s10844-024-00846-z","DOIUrl":"https://doi.org/10.1007/s10844-024-00846-z","url":null,"abstract":"<p>The formulation of structured queries over Knowledge Graphs is not an easy task. To alleviate this problem, we propose a novel interactive method for SPARQL query formulation, for enabling users (plain and advanced) to formulate gradually queries by providing examples and various kinds of positive and negative feedback, in a manner that does not pre-suppose knowledge of the query language or the contents of the Knowledge Graph. In comparison to other example-based query approaches, distinctive features of our approach is the support of negative examples, and the positive/negative feedback on the generated constraints. We detail the algorithmic aspect and we present an interactive user interface that implements the approach. The application of the model on real datasets from DBpedia (Movies, Actors) and other datasets (scientific papers), showcases the feasibility and the effectiveness of the approach. A task-based evaluation that included users that are not familiar with SPARQL, provided positive evidence that the interaction is easy-to-grasp and enabled most users to formulate the desired queries.</p>","PeriodicalId":56119,"journal":{"name":"Journal of Intelligent Information Systems","volume":"74 1","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139752017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Semantic-enhanced reasoning question answering over temporal knowledge graphs 时态知识图谱上的语义增强推理问题解答
IF 3.4 3区 计算机科学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2024-02-02 DOI: 10.1007/s10844-024-00840-5
Chenyang Du, Xiaoge Li, Zhongyang Li

Question Answering Over Temporal Knowledge Graphs (TKGQA) is an important topic in question answering. TKGQA focuses on accurately understanding questions involving temporal constraints and retrieving accurate answers from knowledge graphs. In previous research, the hierarchical structure of question contexts and the constraints imposed by temporal information on different sentence components have been overlooked. In this paper, we propose a framework called “Semantic-Enhanced Reasoning Question Answering” (SERQA) to tackle this problem. First, we adopt a pretrained language model (LM) to obtain the question relation representation vector. Then, we leverage syntactic information from the constituent tree and dependency tree, in combination with Masked Self-Attention (MSA), to enhance temporal constraint features. Finally, we integrate the temporal constraint features into the question relation representation using an information fusion function for answer prediction. Experimental results demonstrate that SERQA achieves better performance on the CRONQUESTIONS and ImConstrainedQuestions datasets. In comparison with existing temporal KGQA methods, our model exhibits outstanding performance in comprehending temporal constraint questions. The ablation experiments verified the effectiveness of combining the constituent tree and the dependency tree with MSA in question answering.

时态知识图谱问题解答(TKGQA)是问题解答领域的一个重要课题。TKGQA 的重点是准确理解涉及时间限制的问题,并从知识图谱中检索出准确的答案。在以往的研究中,问题上下文的层次结构和时间信息对不同句子成分的约束一直被忽视。本文提出了一个名为 "语义增强推理问题解答"(SERQA)的框架来解决这一问题。首先,我们采用预训练语言模型(LM)来获取问题关系表示向量。然后,我们利用来自成分树和依赖树的句法信息,结合掩码自注意(MSA)来增强时间约束特征。最后,我们利用信息融合函数将时间限制特征整合到问题关系表示中,从而进行答案预测。实验结果表明,SERQA 在 CRONQUESTIONS 和 ImConstrainedQuestions 数据集上取得了更好的性能。与现有的时态 KGQA 方法相比,我们的模型在理解时态约束问题方面表现突出。消融实验验证了将成分树和依赖树与 MSA 结合起来进行问题解答的有效性。
{"title":"Semantic-enhanced reasoning question answering over temporal knowledge graphs","authors":"Chenyang Du, Xiaoge Li, Zhongyang Li","doi":"10.1007/s10844-024-00840-5","DOIUrl":"https://doi.org/10.1007/s10844-024-00840-5","url":null,"abstract":"<p>Question Answering Over Temporal Knowledge Graphs (TKGQA) is an important topic in question answering. TKGQA focuses on accurately understanding questions involving temporal constraints and retrieving accurate answers from knowledge graphs. In previous research, the hierarchical structure of question contexts and the constraints imposed by temporal information on different sentence components have been overlooked. In this paper, we propose a framework called “Semantic-Enhanced Reasoning Question Answering” (SERQA) to tackle this problem. First, we adopt a pretrained language model (LM) to obtain the question relation representation vector. Then, we leverage syntactic information from the constituent tree and dependency tree, in combination with Masked Self-Attention (MSA), to enhance temporal constraint features. Finally, we integrate the temporal constraint features into the question relation representation using an information fusion function for answer prediction. Experimental results demonstrate that SERQA achieves better performance on the CRONQUESTIONS and ImConstrainedQuestions datasets. In comparison with existing temporal KGQA methods, our model exhibits outstanding performance in comprehending temporal constraint questions. The ablation experiments verified the effectiveness of combining the constituent tree and the dependency tree with MSA in question answering.</p>","PeriodicalId":56119,"journal":{"name":"Journal of Intelligent Information Systems","volume":"40 1","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139669190","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
KIMedQA: towards building knowledge-enhanced medical QA models KIMedQA:建立知识增强型医疗质量保证模型
IF 3.4 3区 计算机科学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2024-01-25 DOI: 10.1007/s10844-024-00844-1
Aizan Zafar, Sovan Kumar Sahoo, Deeksha Varshney, Amitava Das, Asif Ekbal

Medical question-answering systems require the ability to extract accurate, concise, and comprehensive answers. They will better comprehend the complex text and produce helpful answers if they can reason on the explicit constraints described in the question’s textual context and the implicit, pertinent knowledge of the medical world. Integrating Knowledge Graphs (KG) with Language Models (LMs) is a common approach to incorporating structured information sources. However, effectively combining and reasoning over KG representations and language context remains an open question. To address this, we propose the Knowledge Infused Medical Question Answering system (KIMedQA), which employs two techniques viz. relevant knowledge graph selection and pruning of the large-scale graph to handle Vector Space Inconsistent (VSI) and Excessive Knowledge Information (EKI). The representation of the query and context are then combined with the pruned knowledge network using a pre-trained language model to generate an informed answer. Finally, we demonstrate through in-depth empirical evaluation that our suggested strategy provides cutting-edge outcomes on two benchmark datasets, namely MASH-QA and COVID-QA. We also compared our results to ChatGPT, a robust and very powerful generative model, and discovered that our model outperforms ChatGPT according to the F1 Score and human evaluation metrics such as adequacy.

医学问题解答系统需要能够提取准确、简洁和全面的答案。如果它们能根据问题文本上下文中描述的显式限制条件和医学界的隐式相关知识进行推理,就能更好地理解复杂文本并生成有用的答案。将知识图谱(KG)与语言模型(LMs)相结合是整合结构化信息源的常用方法。然而,如何有效地将知识图谱表示和语言上下文结合起来并进行推理,仍然是一个有待解决的问题。为了解决这个问题,我们提出了知识注入式医学问题解答系统(KIMedQA),该系统采用了两种技术,即相关知识图谱选择和大规模图谱修剪,以处理矢量空间不一致(VSI)和知识信息过多(EKI)问题。然后,利用预先训练好的语言模型,将查询和上下文的表示与剪枝后的知识网络相结合,生成有依据的答案。最后,我们通过深入的实证评估证明,我们建议的策略在两个基准数据集(即 MASH-QA 和 COVID-QA)上提供了最先进的结果。我们还将结果与强大的生成模型 ChatGPT 进行了比较,发现根据 F1 分数和人类评估指标(如充分性),我们的模型优于 ChatGPT。
{"title":"KIMedQA: towards building knowledge-enhanced medical QA models","authors":"Aizan Zafar, Sovan Kumar Sahoo, Deeksha Varshney, Amitava Das, Asif Ekbal","doi":"10.1007/s10844-024-00844-1","DOIUrl":"https://doi.org/10.1007/s10844-024-00844-1","url":null,"abstract":"<p>Medical question-answering systems require the ability to extract accurate, concise, and comprehensive answers. They will better comprehend the complex text and produce helpful answers if they can reason on the explicit constraints described in the question’s textual context and the implicit, pertinent knowledge of the medical world. Integrating Knowledge Graphs (KG) with Language Models (LMs) is a common approach to incorporating structured information sources. However, effectively combining and reasoning over KG representations and language context remains an open question. To address this, we propose the Knowledge Infused Medical Question Answering system <b>(KIMedQA)</b>, which employs two techniques <i>viz.</i> relevant knowledge graph selection and pruning of the large-scale graph to handle Vector Space Inconsistent <i>(VSI)</i> and Excessive Knowledge Information <i>(EKI)</i>. The representation of the query and context are then combined with the pruned knowledge network using a pre-trained language model to generate an informed answer. Finally, we demonstrate through in-depth empirical evaluation that our suggested strategy provides cutting-edge outcomes on two benchmark datasets, namely MASH-QA and COVID-QA. We also compared our results to ChatGPT, a robust and very powerful generative model, and discovered that our model outperforms ChatGPT according to the F1 Score and human evaluation metrics such as adequacy.</p>","PeriodicalId":56119,"journal":{"name":"Journal of Intelligent Information Systems","volume":"67 1","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139551670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Data- & compute-efficient deviance mining via active learning and fast ensembles 通过主动学习和快速集合进行数据和计算效率较高的偏差挖掘
IF 3.4 3区 计算机科学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2024-01-23 DOI: 10.1007/s10844-024-00841-4

Abstract

Detecting deviant traces in business process logs is crucial for modern organizations, given the harmful impact of deviant behaviours (e.g., attacks or faults). However, training a Deviance Prediction Model (DPM) by solely using supervised learning methods is impractical in scenarios where only few examples are labelled. To address this challenge, we propose an Active-Learning-based approach that leverages multiple DPMs and a temporal ensembling method that can train and merge them in a few training epochs. Our method needs expert supervision only for a few unlabelled traces exhibiting high prediction uncertainty. Tests on real data (of either complete or ongoing process instances) confirm the effectiveness of the proposed approach.

摘要 鉴于异常行为(如攻击或故障)的有害影响,检测业务流程日志中的异常痕迹对现代组织至关重要。然而,在只有少数示例被标记的情况下,仅使用监督学习方法来训练偏差预测模型(DPM)是不切实际的。为了应对这一挑战,我们提出了一种基于主动学习的方法,该方法利用多个 DPM 和一种时间集合方法,可以在几个训练历时内训练和合并这些 DPM。我们的方法只需要专家的监督,就能对少数表现出高度预测不确定性的未标记轨迹进行预测。对真实数据(完整或正在进行的流程实例)的测试证实了所提方法的有效性。
{"title":"Data- & compute-efficient deviance mining via active learning and fast ensembles","authors":"","doi":"10.1007/s10844-024-00841-4","DOIUrl":"https://doi.org/10.1007/s10844-024-00841-4","url":null,"abstract":"<h3>Abstract</h3> <p>Detecting deviant traces in business process logs is crucial for modern organizations, given the harmful impact of deviant behaviours (e.g., attacks or faults). However, training a Deviance Prediction Model (DPM) by solely using supervised learning methods is impractical in scenarios where only few examples are labelled. To address this challenge, we propose an Active-Learning-based approach that leverages multiple DPMs and a temporal ensembling method that can train and merge them in a few training epochs. Our method needs expert supervision only for a few unlabelled traces exhibiting high prediction uncertainty. Tests on real data (of either complete or ongoing process instances) confirm the effectiveness of the proposed approach.</p>","PeriodicalId":56119,"journal":{"name":"Journal of Intelligent Information Systems","volume":"10 1","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139551676","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
Journal of Intelligent Information Systems
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1