Pub Date : 2024-06-29DOI: 10.1016/j.ipm.2024.103826
Yang Zhang, Yang Wang
With the growing prominence of interdisciplinary research and heightened concerns surrounding extended prepublication timelines, we still lack of understanding regarding the interplay between interdisciplinary level and the duration of the peer review process. This study aims to untangle the relationship between interdisciplinarity and the time manuscripts spend navigating the peer review phase. Leveraging a large-scale bibliometric dataset comprising over three million journal articles, we uncover a robust positive association between paper interdisciplinary level and the duration of the peer review process. This relationship persists across diverse fields, journals with various impacts, and articles with different citation impacts. Moreover, we find that conventionality and reference age partly contribute to such delay. Notably, our investigation indicates that journal editors cannot fully account for the prolonged peer review delays for interdisciplinary research. Furthermore, our results underscore a noteworthy observation: referees generally pose more inquiries toward interdisciplinary endeavors. This is consistent with the fact that scientists submitting interdisciplinary manuscripts may inherently require additional time to adequately address the detailed comments and questions posed by referees. Our results have policy implications for funders, journal editors, and institutions seeking to promote and facilitate interdisciplinary research.
{"title":"Understanding delays in publishing interdisciplinary research","authors":"Yang Zhang, Yang Wang","doi":"10.1016/j.ipm.2024.103826","DOIUrl":"https://doi.org/10.1016/j.ipm.2024.103826","url":null,"abstract":"<div><p>With the growing prominence of interdisciplinary research and heightened concerns surrounding extended prepublication timelines, we still lack of understanding regarding the interplay between interdisciplinary level and the duration of the peer review process. This study aims to untangle the relationship between interdisciplinarity and the time manuscripts spend navigating the peer review phase. Leveraging a large-scale bibliometric dataset comprising over three million journal articles, we uncover a robust positive association between paper interdisciplinary level and the duration of the peer review process. This relationship persists across diverse fields, journals with various impacts, and articles with different citation impacts. Moreover, we find that conventionality and reference age partly contribute to such delay. Notably, our investigation indicates that journal editors cannot fully account for the prolonged peer review delays for interdisciplinary research. Furthermore, our results underscore a noteworthy observation: referees generally pose more inquiries toward interdisciplinary endeavors. This is consistent with the fact that scientists submitting interdisciplinary manuscripts may inherently require additional time to adequately address the detailed comments and questions posed by referees. Our results have policy implications for funders, journal editors, and institutions seeking to promote and facilitate interdisciplinary research.</p></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":null,"pages":null},"PeriodicalIF":7.4,"publicationDate":"2024-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141486458","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-29DOI: 10.1016/j.ipm.2024.103813
Yujie Zeng , Yiming Huang , Qiang Wu , Linyuan Lü
The identification of influential simplices is crucial for understanding higher-order network dynamics. Yet, despite relatively mature research on influential nodes (0-simplices) mining, characterizing simplices’ influence and identifying influential simplices remain challenging due to notable discrepancies in vital nodes and vital simplices mining. In this paper, we propose a higher-order graph learning model, named influential simplices mining neural networks (ISMnet), to identify vital simplices in simplicial complexes. ISMnet leverages novel higher-order representations: hierarchical bipartite graphs and higher-order hierarchical (HoH) Laplacians, where target simplices are grouped into a hub set and can interact with other simplices. It also employs learnable graph convolution operators in each HoH Laplacian domain to capture interactions among simplices and can identify influential simplices of arbitrary order by changing the hub set. Notably, ISMnet addresses the limitations inherent in traditional graph neural networks that struggle with higher-order tasks, while seamlessly retaining the capability to exploit network topology and node features concurrently. Numerical results on empirical and synthetic datasets demonstrate that ISMnet significantly outperforms existing methods by at least 12% and 4%, respectively, in ranking 2-simplices. In general, this novel framework promises to serve as a potent tool in higher-order network analysis.
{"title":"Influential simplices mining via simplicial convolutional networks","authors":"Yujie Zeng , Yiming Huang , Qiang Wu , Linyuan Lü","doi":"10.1016/j.ipm.2024.103813","DOIUrl":"https://doi.org/10.1016/j.ipm.2024.103813","url":null,"abstract":"<div><p>The identification of influential simplices is crucial for understanding higher-order network dynamics. Yet, despite relatively mature research on influential nodes (0-simplices) mining, characterizing simplices’ influence and identifying influential simplices remain challenging due to notable discrepancies in vital nodes and vital simplices mining. In this paper, we propose a higher-order graph learning model, named influential simplices mining neural networks (ISMnet), to identify vital simplices in simplicial complexes. ISMnet leverages novel higher-order representations: hierarchical bipartite graphs and higher-order hierarchical (HoH) Laplacians, where target simplices are grouped into a hub set and can interact with other simplices. It also employs learnable graph convolution operators in each HoH Laplacian domain to capture interactions among simplices and can identify influential simplices of arbitrary order by changing the hub set. Notably, ISMnet addresses the limitations inherent in traditional graph neural networks that struggle with higher-order tasks, while seamlessly retaining the capability to exploit network topology and node features concurrently. Numerical results on empirical and synthetic datasets demonstrate that ISMnet significantly outperforms existing methods by at least 12% and 4%, respectively, in ranking 2-simplices. In general, this novel framework promises to serve as a potent tool in higher-order network analysis.</p></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":null,"pages":null},"PeriodicalIF":7.4,"publicationDate":"2024-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141486480","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-28DOI: 10.1016/j.ipm.2024.103802
Feng Gao , Yan Yang , Peng Gao , Ming Gu , Shangqing Zhao , Yuefeng Chen , Hao Yuan , Man Lan , Aimin Zhou , Liang He
Knowledge base question answering aims to answer complex questions from large-scale knowledge bases. Although existing generative language models that translate questions into SPARQL queries have achieved promising results, there are still generation errors due to redundancies or errors in the knowledge fed to the generative models and difficulties in representing the implicit logic of knowledge as the specific syntax of SPARQL. To address above issues, we propose TrackerQA, a novel self-supervised reasoning framework based on basic graph patterns (BGP) to determine precise paths and enhance SPARQL generation. First, we develop a contrastive learning semantic matching model to reduce the large knowledge searching space. Then, we built a BGP parser that parses the recalled knowledge and constraints into BGP graphs, which can deconstruct complex knowledge into BGP triples and naturally obtain supervision from gold SPARQL. Next, we design a self-supervised BGP graph neural network that encodes knowledge through graph transformation layers with directed message-passing control and employs a question-aware attention mechanism to predict the exact BGP paths. Finally, a SPARQL generator integrates the paths into a pre-trained language model to improve the performance of SPARQL generation. Experiments on the KQA Pro dataset show that our model achieves state-of-the-art answering accuracy scores of 95.32%, being the closest to the human level at 97.5%, and reasons out KB paths with F1 scores of 0.98 for nodes and 0.99 for edges.
{"title":"Self-supervised BGP-graph reasoning enhanced complex KBQA via SPARQL generation","authors":"Feng Gao , Yan Yang , Peng Gao , Ming Gu , Shangqing Zhao , Yuefeng Chen , Hao Yuan , Man Lan , Aimin Zhou , Liang He","doi":"10.1016/j.ipm.2024.103802","DOIUrl":"https://doi.org/10.1016/j.ipm.2024.103802","url":null,"abstract":"<div><p>Knowledge base question answering aims to answer complex questions from large-scale knowledge bases. Although existing generative language models that translate questions into SPARQL queries have achieved promising results, there are still generation errors due to redundancies or errors in the knowledge fed to the generative models and difficulties in representing the implicit logic of knowledge as the specific syntax of SPARQL. To address above issues, we propose TrackerQA, a novel self-supervised reasoning framework based on basic graph patterns (BGP) to determine precise paths and enhance SPARQL generation. First, we develop a contrastive learning semantic matching model to reduce the large knowledge searching space. Then, we built a BGP parser that parses the recalled knowledge and constraints into BGP graphs, which can deconstruct complex knowledge into BGP triples and naturally obtain supervision from gold SPARQL. Next, we design a self-supervised BGP graph neural network that encodes knowledge through graph transformation layers with directed message-passing control and employs a question-aware attention mechanism to predict the exact BGP paths. Finally, a SPARQL generator integrates the paths into a pre-trained language model to improve the performance of SPARQL generation. Experiments on the KQA Pro dataset show that our model achieves state-of-the-art answering accuracy scores of 95.32%, being the closest to the human level at 97.5%, and reasons out KB paths with F1 scores of 0.98 for nodes and 0.99 for edges.</p></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":null,"pages":null},"PeriodicalIF":7.4,"publicationDate":"2024-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141486457","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-28DOI: 10.1016/j.ipm.2024.103817
Meixiu Long , Siyuan Chen , Jiahai Wang
Network alignment (NA), discovering anchor nodes that represent the same entities across different networks, plays a fundamental role in information fusion. Most existing embedding-based methods rarely study the alignment module, which learns a global mapping to unify embedding spaces. However, global mapping is a holistic solution for nodes, incapable of optimally projecting each node, thus deteriorating alignment accuracy. To solve this problem, this paper proposes a local mapping framework named MANA, which fine-tunes global mapping by meta-learning to obtain node-level local mappings. One advantage of MANA is that it tailors local mapping adapted to the embedded locality of each node while maintaining the general knowledge of global mapping. The main challenge of applying meta-learning to network alignment is paradigm incompatibility; that is, how to construct effective meta-tasks and support sets for zero-shot NA. Therefore, the paper constructs meta-tasks with similarity-based support sets. A support set is taken from pairs of anchor nodes, the source nodes of which are embedded close to the query node. Our framework can be applied to existing mapping-based NA models. Experimental results show that mapping-based models with MANA improve evaluation scores by 1%–59% relative to their original models, demonstrating the effectiveness of local mapping. Some simple mapping-based models improved by MANA even outperform sophisticated sharing-based NA approaches.
网络对齐(NA)是指在不同网络中发现代表相同实体的锚节点,它在信息融合中发挥着基础性作用。大多数现有的基于嵌入的方法很少研究配准模块,而配准模块学习全局映射来统一嵌入空间。然而,全局映射是节点的整体解决方案,无法对每个节点进行最佳投射,从而降低了配准精度。为解决这一问题,本文提出了一种名为 MANA 的局部映射框架,通过元学习对全局映射进行微调,从而获得节点级的局部映射。MANA 的一个优点是,它能在保持全局映射一般知识的同时,根据每个节点的嵌入式局部性定制局部映射。将元学习应用于网络对齐的主要挑战在于范式不兼容,即如何为零次NA构建有效的元任务和支持集。因此,本文利用基于相似性的支持集构建元任务。支持集取自成对的锚节点,这些锚节点的源节点嵌入在查询节点附近。我们的框架可应用于现有的基于映射的 NA 模型。实验结果表明,使用 MANA 的基于映射的模型与原始模型相比,评估得分提高了 1%-59%,这证明了局部映射的有效性。一些经 MANA 改进的基于映射的简单模型甚至优于复杂的基于共享的 NA 方法。
{"title":"Locally-adaptive mapping for network alignment via meta-learning","authors":"Meixiu Long , Siyuan Chen , Jiahai Wang","doi":"10.1016/j.ipm.2024.103817","DOIUrl":"https://doi.org/10.1016/j.ipm.2024.103817","url":null,"abstract":"<div><p>Network alignment (NA), discovering anchor nodes that represent the same entities across different networks, plays a fundamental role in information fusion. Most existing embedding-based methods rarely study the alignment module, which learns a global mapping to unify embedding spaces. However, global mapping is a holistic solution for nodes, incapable of optimally projecting each node, thus deteriorating alignment accuracy. To solve this problem, this paper proposes a local mapping framework named MANA, which fine-tunes global mapping by meta-learning to obtain node-level local mappings. One advantage of MANA is that it tailors local mapping adapted to the embedded locality of each node while maintaining the general knowledge of global mapping. The main challenge of applying meta-learning to network alignment is paradigm incompatibility; that is, how to construct effective meta-tasks and support sets for zero-shot NA. Therefore, the paper constructs meta-tasks with similarity-based support sets. A support set is taken from pairs of anchor nodes, the source nodes of which are embedded close to the query node. Our framework can be applied to existing mapping-based NA models. Experimental results show that mapping-based models with MANA improve evaluation scores by 1%–59% relative to their original models, demonstrating the effectiveness of local mapping. Some simple mapping-based models improved by MANA even outperform sophisticated sharing-based NA approaches.</p></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":null,"pages":null},"PeriodicalIF":7.4,"publicationDate":"2024-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141486462","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The identification of sexual activities in images can be helpful in detecting the level of content severity and can assist pornography detectors in filtering specific types of content. In this paper, we propose a Deep Learning-based framework, named DeepHSAR, for semi-supervised fine-grained multi-label Human Sexual Activity Recognition (HSAR). To the best of our knowledge, this is the first work to propose an approach to HSAR. We also introduce a new multi-label dataset, named SexualActs-150k, containing 150k images manually labeled with 19 types of sexual activities. DeepHSAR has two multi-label classification streams: one for global image representation and another for fine-grained representation. To perform fine-grained image classification without ground-truth bounding box annotations, we propose a novel semi-supervised approach for multi-label fine-grained recognition, which learns through an iterative clustering and iterative CNN training process. We obtained a significant performance gain by fusing both streams (i.e., overall F1-score of 79.29%), compared to when they work separately. The experiments demonstrate that the proposed framework explicitly outperforms baseline and state-of-the-art approaches. In addition, the proposed framework also obtains state-of-the-art or competitive results in semi-supervised multi-label learning experiments on the NUS-WIDE and MS-COCO datasets with overall F1-scores of 75.98% and 85.17%, respectively. Furthermore, the proposed DeepHSAR has been assessed on the NPDI Pornography-2k video dataset, achieving a new state-of-the-art with 99.85% accuracy.
{"title":"DeepHSAR: Semi-supervised fine-grained learning for multi-label human sexual activity recognition","authors":"Abhishek Gangwar , Víctor González-Castro , Enrique Alegre , Eduardo Fidalgo , Alicia Martínez-Mendoza","doi":"10.1016/j.ipm.2024.103800","DOIUrl":"https://doi.org/10.1016/j.ipm.2024.103800","url":null,"abstract":"<div><p>The identification of sexual activities in images can be helpful in detecting the level of content severity and can assist pornography detectors in filtering specific types of content. In this paper, we propose a Deep Learning-based framework, named DeepHSAR, for semi-supervised fine-grained multi-label Human Sexual Activity Recognition (HSAR). To the best of our knowledge, this is the first work to propose an approach to HSAR. We also introduce a new multi-label dataset, named SexualActs-150k, containing 150k images manually labeled with 19 types of sexual activities. DeepHSAR has two multi-label classification streams: one for global image representation and another for fine-grained representation. To perform fine-grained image classification without ground-truth bounding box annotations, we propose a novel semi-supervised approach for multi-label fine-grained recognition, which learns through an iterative clustering and iterative CNN training process. We obtained a significant performance gain by fusing both streams (i.e., overall F1-score of 79.29%), compared to when they work separately. The experiments demonstrate that the proposed framework explicitly outperforms baseline and state-of-the-art approaches. In addition, the proposed framework also obtains state-of-the-art or competitive results in semi-supervised multi-label learning experiments on the NUS-WIDE and MS-COCO datasets with overall F1-scores of 75.98% and 85.17%, respectively. Furthermore, the proposed DeepHSAR has been assessed on the NPDI Pornography-2k video dataset, achieving a new state-of-the-art with 99.85% accuracy.</p></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":null,"pages":null},"PeriodicalIF":7.4,"publicationDate":"2024-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141486461","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-25DOI: 10.1016/j.ipm.2024.103810
Na Li , Tianao Li , Zhaorui Ma , Xinhao Hu , Shicheng Zhang , Fenlin Liu , Xiaowen Quan , Xiangyang Luo , Guoming Ren , Hao Feng , Shubo Zhang
Network entities have important asset mapping, vulnerability, and service delivery applications. In cyberspace, where the network structure is complex and the number of entities is large, effectively obtaining the relevant attributes of entities is a difficult task. Graph neural network-based approaches focus on target IP node messaging from neighboring nodes; however, the graph learning task ignores the heterophilous relationship of network entity identification (NEI) tasks in the graph structure and fails to effectively message from non-neighboring nodes. To address the limitations of the existing task, we propose a NEI model based on heterophilous graph learning (HpGraphNEI); HpGraphNEI converts heterophilous graphs under the NEI task into homophilous graphs and uses the graph learning mechanism to carry out attribute completion task for incomplete entity attributes. First, the acquired dataset is feature-extracted by network measurement, and the clustering algorithm is employed to divide the target nodes into communities. Second, the network topology graph is constructed to embed the node attribute information and neighborhood structure information into the graph in the form of feature vectors. Then, the global attention in the community is calculated according to the attention results, the edges with strong correlation in the network are filtered, the adjacency matrix is reconstructed, and then the updated node information is aggregated to complete the incomplete attribute completion. Fourth, the updated nodes are categorized to output network entity categories and construct network entity portraits based on the attribute completion nodes. We conducted a 2-month data collection in three real regions and successfully identified 6 types of network entities. Compared with the optimal baseline, all the metrics have significantly improved, with NEI accuracy above 93.74% and up to 96.28%, improved 2.27% to 2.69%.
网络实体具有重要的资产映射、脆弱性和服务提供应用。在网络空间中,网络结构复杂,实体数量庞大,有效获取实体的相关属性是一项艰巨的任务。基于图神经网络的方法侧重于目标 IP 节点从相邻节点发送信息;然而,图学习任务忽略了图结构中网络实体识别(NEI)任务的异亲关系,无法有效地从非相邻节点发送信息。针对现有任务的局限性,我们提出了一种基于异亲图学习的网络实体识别模型(HpGraphNEI);HpGraphNEI 将网络实体识别任务下的异亲图转换为同亲图,并利用图学习机制完成不完整实体属性的属性补全任务。首先,通过网络测量对获取的数据集进行特征提取,并采用聚类算法将目标节点划分为社区。其次,构建网络拓扑图,将节点属性信息和邻域结构信息以特征向量的形式嵌入图中。然后,根据关注度结果计算社区内的全局关注度,过滤网络中相关性较强的边,重构邻接矩阵,再汇总更新后的节点信息,完成不完整的属性补全。第四,对更新后的节点进行分类,输出网络实体类别,并根据属性补全节点构建网络实体肖像。我们在三个实际地区进行了为期 2 个月的数据采集,成功识别了 6 类网络实体。与最优基线相比,所有指标都有明显改善,其中 NEI 准确率高于 93.74%,最高达 96.28%,提高了 2.27% 至 2.69%。
{"title":"HpGraphNEI: A network entity identification model based on heterophilous graph learning","authors":"Na Li , Tianao Li , Zhaorui Ma , Xinhao Hu , Shicheng Zhang , Fenlin Liu , Xiaowen Quan , Xiangyang Luo , Guoming Ren , Hao Feng , Shubo Zhang","doi":"10.1016/j.ipm.2024.103810","DOIUrl":"https://doi.org/10.1016/j.ipm.2024.103810","url":null,"abstract":"<div><p>Network entities have important asset mapping, vulnerability, and service delivery applications. In cyberspace, where the network structure is complex and the number of entities is large, effectively obtaining the relevant attributes of entities is a difficult task. Graph neural network-based approaches focus on target IP node messaging from neighboring nodes; however, the graph learning task ignores the heterophilous relationship of network entity identification (NEI) tasks in the graph structure and fails to effectively message from non-neighboring nodes. To address the limitations of the existing task, we propose a NEI model based on heterophilous graph learning (HpGraphNEI); HpGraphNEI converts heterophilous graphs under the NEI task into homophilous graphs and uses the graph learning mechanism to carry out attribute completion task for incomplete entity attributes. First, the acquired dataset is feature-extracted by network measurement, and the clustering algorithm is employed to divide the target nodes into communities. Second, the network topology graph is constructed to embed the node attribute information and neighborhood structure information into the graph in the form of feature vectors. Then, the global attention in the community is calculated according to the attention results, the edges with strong correlation in the network are filtered, the adjacency matrix is reconstructed, and then the updated node information is aggregated to complete the incomplete attribute completion. Fourth, the updated nodes are categorized to output network entity categories and construct network entity portraits based on the attribute completion nodes. We conducted a 2-month data collection in three real regions and successfully identified 6 types of network entities. Compared with the optimal baseline, all the metrics have significantly improved, with NEI accuracy above 93.74% and up to 96.28%, improved 2.27% to 2.69%.</p></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":null,"pages":null},"PeriodicalIF":7.4,"publicationDate":"2024-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141486460","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-24DOI: 10.1016/j.ipm.2024.103814
Wenchuan Yang , Cheng Yang , Jichao Li , Yuejin Tan , Xin Lu , Chuan Shi
The personalized bundle generation problem, which aims to create a preferred bundle for user from numerous candidate items, receives increasing attention in recommendation. However, existing works ignore the order-invariant nature of the bundle and adopt sequential modeling methods as the solution, which might introduce inductive bias and cause a large latency in prediction. To address this problem, we propose to perform the bundle generation via non-autoregressive mechanism and design a novel encoder–decoder framework named BundleNAT, which can effectively output the targeted bundle in one-shot without relying on any inherent order. In detail, instead of learning sequential dependency, we propose to adopt pre-training techniques and graph neural network to fully embed user-based preference and item-based compatibility information, and use a self-attention based encoder to further extract global dependency pattern. We then design a permutation-equivariant decoding architecture that is able to directly output the desired bundle in a one-shot manner. Experiments on three real-world datasets from Youshu and Netease show the proposed BundleNAT significantly outperforms the current state-of-the-art methods in average by up to 35.92%, 10.97% and 23.67% absolute improvements in Precision, Precision+, and Recall, respectively.
{"title":"Non-autoregressive personalized bundle generation","authors":"Wenchuan Yang , Cheng Yang , Jichao Li , Yuejin Tan , Xin Lu , Chuan Shi","doi":"10.1016/j.ipm.2024.103814","DOIUrl":"https://doi.org/10.1016/j.ipm.2024.103814","url":null,"abstract":"<div><p>The personalized bundle generation problem, which aims to create a preferred bundle for user from numerous candidate items, receives increasing attention in recommendation. However, existing works ignore the order-invariant nature of the bundle and adopt sequential modeling methods as the solution, which might introduce inductive bias and cause a large latency in prediction. To address this problem, we propose to perform the bundle generation via non-autoregressive mechanism and design a novel encoder–decoder framework named BundleNAT, which can effectively output the targeted bundle in one-shot without relying on any inherent order. In detail, instead of learning sequential dependency, we propose to adopt pre-training techniques and graph neural network to fully embed user-based preference and item-based compatibility information, and use a self-attention based encoder to further extract global dependency pattern. We then design a permutation-equivariant decoding architecture that is able to directly output the desired bundle in a one-shot manner. Experiments on three real-world datasets from Youshu and Netease show the proposed BundleNAT significantly outperforms the current state-of-the-art methods in average by up to 35.92%, 10.97% and 23.67% absolute improvements in Precision, Precision+, and Recall, respectively.</p></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":null,"pages":null},"PeriodicalIF":7.4,"publicationDate":"2024-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141486481","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-24DOI: 10.1016/j.ipm.2024.103811
Junchi Zhang , Tao Chen , Songtao Li , Ming Zhang , Yafeng Ren , Jun Wan
The task of event relation extraction (ERE) aims to organize multiple events and their relations as a directed graph. However, existing ERE methods exhibit two limitations: (1) Events in a document are typically expressed with merely a trigger word or phrase neglecting the rich semantic structure of event arguments and roles. (2) Various event relations such as coreference, temporal, causal, and subevent relations are correlated with each other, while little work has explored the benefits of extracting all relations in a joint manner. In this work, we investigate an event-relation graph propagation network and a novel document-level semantically-enriched event representation for joint ERE. First, we address the lack of event argument annotations by extracting cross-sentence implicit arguments based on the AMR graph. Then triggers and argument roles are aggregated with a structure-aware encoder. Second, based on the rich event information, event relation interactions are incorporated with a subgraph propagation and aggregation mechanism. During training, we further develop a novel triadic contrastive loss to capture high-order event pair relationships. We conduct experiments based on the public MAVEN-ERE benchmark and the results show that our model achieves 60.7%, 37.4%, 32.9% F1-scores on temporal, causal and subevent relations, and 86.1% MUC-score on coreferences, outperforming the current joint models by a large margin. Further in-depth analysis shows the effectiveness of our model in capturing event-event dependencies in document context. The proposed model can be used for event graph construction and storyline understanding.
事件关系提取(ERE)任务旨在将多个事件及其关系组织成一个有向图。然而,现有的ERE 方法有两个局限性:(1) 文档中的事件通常只用一个触发词或短语来表达,忽略了事件参数和角色的丰富语义结构。(2) 各种事件关系(如核心参照关系、时间关系、因果关系和子事件关系)之间相互关联,而很少有人探索以联合方式提取所有关系的益处。在这项工作中,我们研究了一种事件关系图传播网络和一种用于联合ERE的新型文档级语义丰富事件表示法。首先,我们根据 AMR 图提取跨句子隐含参数,解决了缺乏事件参数注释的问题。然后使用结构感知编码器聚合触发器和参数角色。其次,基于丰富的事件信息,利用子图传播和聚合机制将事件关系交互纳入其中。在训练过程中,我们进一步开发了一种新颖的三元组对比损失,以捕捉高阶事件对关系。我们基于公开的 MAVEN-ERE 基准进行了实验,结果表明我们的模型在时间关系、因果关系和子事件关系上分别获得了 60.7%、37.4% 和 32.9% 的 F1 分数,在核心参照关系上获得了 86.1% 的 MUC 分数,大大优于当前的联合模型。进一步的深入分析表明,我们的模型能有效捕捉文档上下文中的事件-事件依赖关系。所提出的模型可用于事件图构建和故事情节理解。
{"title":"A graph propagation model with rich event structures for joint event relation extraction","authors":"Junchi Zhang , Tao Chen , Songtao Li , Ming Zhang , Yafeng Ren , Jun Wan","doi":"10.1016/j.ipm.2024.103811","DOIUrl":"https://doi.org/10.1016/j.ipm.2024.103811","url":null,"abstract":"<div><p>The task of event relation extraction (ERE) aims to organize multiple events and their relations as a directed graph. However, existing ERE methods exhibit two limitations: (1) Events in a document are typically expressed with merely a trigger word or phrase neglecting the rich semantic structure of event arguments and roles. (2) Various event relations such as coreference, temporal, causal, and subevent relations are correlated with each other, while little work has explored the benefits of extracting all relations in a joint manner. In this work, we investigate an event-relation graph propagation network and a novel document-level semantically-enriched event representation for joint ERE. First, we address the lack of event argument annotations by extracting cross-sentence implicit arguments based on the AMR graph. Then triggers and argument roles are aggregated with a structure-aware encoder. Second, based on the rich event information, event relation interactions are incorporated with a subgraph propagation and aggregation mechanism. During training, we further develop a novel triadic contrastive loss to capture high-order event pair relationships. We conduct experiments based on the public MAVEN-ERE benchmark and the results show that our model achieves 60.7%, 37.4%, 32.9% F1-scores on temporal, causal and subevent relations, and 86.1% MUC-score on coreferences, outperforming the current joint models by a large margin. Further in-depth analysis shows the effectiveness of our model in capturing event-event dependencies in document context. The proposed model can be used for event graph construction and storyline understanding.</p></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":null,"pages":null},"PeriodicalIF":7.4,"publicationDate":"2024-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141486515","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-22DOI: 10.1016/j.ipm.2024.103820
Petr Hajek , Michal Munk
This study presents a financial distress prediction model focusing on the linguistic analysis of risk-related sections of corporate annual reports. Here, we introduce a novel methodology that leverages BERT-based contextualized embedding models for nuanced extraction of financial sentiment and topic coherence. This stands in contrast to existing research, which predominantly relies on dictionary-based or non-contextual word embeddings and addresses their limitations in context sensitivity. Furthermore, we apply an innovative financial distress prediction model that combines the robust XGBoost algorithm with unsupervised outlier detection techniques. This hybrid model is specifically designed to tackle the issue of class imbalance, a persistent challenge in financial distress prediction. The efficacy of the proposed model is empirically validated using a comprehensive dataset of 2545 companies listed on major global stock exchanges. Our findings indicate that the introduced model not only significantly outperforms most existing state-of-the-art financial distress prediction models in terms of predictive accuracy, but also significantly outperforms the Loughran & McDonald dictionary-based approach and the Word2Vec model, underlining its potential as a superior analytical tool for financial distress prediction.
{"title":"Corporate financial distress prediction using the risk-related information content of annual reports","authors":"Petr Hajek , Michal Munk","doi":"10.1016/j.ipm.2024.103820","DOIUrl":"https://doi.org/10.1016/j.ipm.2024.103820","url":null,"abstract":"<div><p>This study presents a financial distress prediction model focusing on the linguistic analysis of risk-related sections of corporate annual reports. Here, we introduce a novel methodology that leverages BERT-based contextualized embedding models for nuanced extraction of financial sentiment and topic coherence. This stands in contrast to existing research, which predominantly relies on dictionary-based or non-contextual word embeddings and addresses their limitations in context sensitivity. Furthermore, we apply an innovative financial distress prediction model that combines the robust XGBoost algorithm with unsupervised outlier detection techniques. This hybrid model is specifically designed to tackle the issue of class imbalance, a persistent challenge in financial distress prediction. The efficacy of the proposed model is empirically validated using a comprehensive dataset of 2545 companies listed on major global stock exchanges. Our findings indicate that the introduced model not only significantly outperforms most existing state-of-the-art financial distress prediction models in terms of predictive accuracy, but also significantly outperforms the Loughran & McDonald dictionary-based approach and the Word2Vec model, underlining its potential as a superior analytical tool for financial distress prediction.</p></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":null,"pages":null},"PeriodicalIF":7.4,"publicationDate":"2024-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141444646","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-22DOI: 10.1016/j.ipm.2024.103808
Yifan Zhang , Zhiyun Wang , Zhengting He , Jingxuan Li , Gengchen Mai , Jianfeng Lin , Cheng Wei , Wenhao Yu
Large language models (LLMs) exhibit impressive capabilities across diverse tasks in natural language processing. Nevertheless, challenges arise such as large model parameter size and limited model accessibility through APIs such as ChatGPT and GPT-4, which prohibits the model deployment on mobile devices and domain adaptation or fine-tuning. Moreover, while LLMs excel in general domains, their performance in specialized fields such as GIS may not always align with the expectations of domain experts. This is primarily attributed to the diverse disciplinary origins of the training data, which often lack comprehensive coverage and treatment of knowledge specific to individual disciplines (e.g., GIS). Therefore, there is a crucial need to train and adapt LLMs specifically designed for different professional fields. In this paper, our focus is on the GIS domain, where we introduce BB(BaBy)-GeoGPT, a large language model with GIS-specific knowledge. To achieve this goal, we curated a comprehensive set of resources, comprising model pretraining data (BB-GeoPT, 26,907 documents), supervised fine-tuning data (BB-GeoSFT, 35,876 instructions), and evaluation data (BB-GeoEval, 600 objective questions and 150 subjective questions). BB-GeoGPT is developed by first adapting an open-source general-domain LLM, the LLaMA-2-7B model, to our pretraining data. Subsequently, we use instruction tuning to further fine-tune the model on our BB-GeoSFT. Through extensive experiments on the evaluation dataset, BB-GeoGPT demonstrates improvements ranging from 10.55% to 47.57% for objective questions and from 7.87% to 27.73% for subjective questions, when compared to general LLMs of similar size in terms of accuracy. Moreover, our data collection strategy and the amassed data can serve as a foundation for advancing LLM research in the GIS domain, fostering further development.
{"title":"BB-GeoGPT: A framework for learning a large language model for geographic information science","authors":"Yifan Zhang , Zhiyun Wang , Zhengting He , Jingxuan Li , Gengchen Mai , Jianfeng Lin , Cheng Wei , Wenhao Yu","doi":"10.1016/j.ipm.2024.103808","DOIUrl":"https://doi.org/10.1016/j.ipm.2024.103808","url":null,"abstract":"<div><p>Large language models (LLMs) exhibit impressive capabilities across diverse tasks in natural language processing. Nevertheless, challenges arise such as large model parameter size and limited model accessibility through APIs such as ChatGPT and GPT-4, which prohibits the model deployment on mobile devices and domain adaptation or fine-tuning. Moreover, while LLMs excel in general domains, their performance in specialized fields such as GIS may not always align with the expectations of domain experts. This is primarily attributed to the diverse disciplinary origins of the training data, which often lack comprehensive coverage and treatment of knowledge specific to individual disciplines (e.g., GIS). Therefore, there is a crucial need to train and adapt LLMs specifically designed for different professional fields. In this paper, our focus is on the GIS domain, where we introduce BB(BaBy)-GeoGPT, a large language model with GIS-specific knowledge. To achieve this goal, we curated a comprehensive set of resources, comprising model pretraining data (BB-GeoPT, 26,907 documents), supervised fine-tuning data (BB-GeoSFT, 35,876 instructions), and evaluation data (BB-GeoEval, 600 objective questions and 150 subjective questions). BB-GeoGPT is developed by first adapting an open-source general-domain LLM, the LLaMA-2-7B model, to our pretraining data. Subsequently, we use instruction tuning to further fine-tune the model on our BB-GeoSFT. Through extensive experiments on the evaluation dataset, BB-GeoGPT demonstrates improvements ranging from 10.55% to 47.57% for objective questions and from 7.87% to 27.73% for subjective questions, when compared to general LLMs of similar size in terms of accuracy. Moreover, our data collection strategy and the amassed data can serve as a foundation for advancing LLM research in the GIS domain, fostering further development.</p></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":null,"pages":null},"PeriodicalIF":7.4,"publicationDate":"2024-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141444647","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}