Yang Zhou, Jiaxiang Ren, R. Jin, Zijie Zhang, Jingyi Zheng, Zhe Jiang, Da Yan, D. Dou
Network alignment, which aims at learning a matching between the same entities across multiple information networks, often suffers challenges from feature inconsistency, high-dimensional features, to unstable alignment results. This article presents a novel network alignment framework, Unsupervised Adversarial learning based Network Alignment(UANA), that combines generative adversarial network (GAN) and reinforcement learning (RL) techniques to tackle the above critical challenges. First, we propose a bidirectional adversarial network distribution matching model to perform the bidirectional cross-network alignment translations between two networks, such that the distributions of real and translated networks completely overlap together. In addition, two cross-network alignment translation cycles are constructed for training the unsupervised alignment without the need of prior alignment knowledge. Second, in order to address the feature inconsistency issue, we integrate a dual adversarial autoencoder module with an adversarial binary classification model together to project two copies of the same vertices with high-dimensional inconsistent features into the same low-dimensional embedding space. This facilitates the translations of the distributions of two networks in the adversarial network distribution matching model. Finally, we develop an RL based optimization approach to solve the vertex matching problem in the discrete space of the GAN model, i.e., directly select the vertices in target networks most relevant to the vertices in source networks, without unstable similarity computation that is sensitive to discriminative features and similarity metrics. Extensive evaluation on real-world graph datasets demonstrates the outstanding capability of UANA to address the unsupervised network alignment problem, in terms of both effectiveness and scalability.
{"title":"Unsupervised Adversarial Network Alignment with Reinforcement Learning","authors":"Yang Zhou, Jiaxiang Ren, R. Jin, Zijie Zhang, Jingyi Zheng, Zhe Jiang, Da Yan, D. Dou","doi":"10.1145/3477050","DOIUrl":"https://doi.org/10.1145/3477050","url":null,"abstract":"Network alignment, which aims at learning a matching between the same entities across multiple information networks, often suffers challenges from feature inconsistency, high-dimensional features, to unstable alignment results. This article presents a novel network alignment framework, Unsupervised Adversarial learning based Network Alignment(UANA), that combines generative adversarial network (GAN) and reinforcement learning (RL) techniques to tackle the above critical challenges. First, we propose a bidirectional adversarial network distribution matching model to perform the bidirectional cross-network alignment translations between two networks, such that the distributions of real and translated networks completely overlap together. In addition, two cross-network alignment translation cycles are constructed for training the unsupervised alignment without the need of prior alignment knowledge. Second, in order to address the feature inconsistency issue, we integrate a dual adversarial autoencoder module with an adversarial binary classification model together to project two copies of the same vertices with high-dimensional inconsistent features into the same low-dimensional embedding space. This facilitates the translations of the distributions of two networks in the adversarial network distribution matching model. Finally, we develop an RL based optimization approach to solve the vertex matching problem in the discrete space of the GAN model, i.e., directly select the vertices in target networks most relevant to the vertices in source networks, without unstable similarity computation that is sensitive to discriminative features and similarity metrics. Extensive evaluation on real-world graph datasets demonstrates the outstanding capability of UANA to address the unsupervised network alignment problem, in terms of both effectiveness and scalability.","PeriodicalId":435653,"journal":{"name":"ACM Transactions on Knowledge Discovery from Data (TKDD)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125432513","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Huandong Wang, Yong Li, Junjie Lin, Hancheng Cao, Depeng Jin
The wide adoption of mobile devices has provided us with a massive volume of human mobility records. However, a large portion of these records is unlabeled, i.e., only have GPS coordinates without semantic information (e.g., Point of Interest (POI)). To make those unlabeled records associate with more information for further applications, it is of great importance to annotate the original data with POIs information based on the external context. Nevertheless, semantic annotation of mobility records is challenging due to three aspects: the complex relationship among multiple domains of context, the sparsity of mobility records, and difficulties in balancing personal preference and crowd preference. To address these challenges, we propose CAP, a context-aware personalized semantic annotation model, where we use a Bayesian mixture model to model the complex relationship among five domains of context—location, time, POI category, personal preference, and crowd preference. We evaluate our model on two real-world datasets, and demonstrate that our proposed method significantly outperforms the state-of-the-art algorithms by over 11.8%.
{"title":"Context-Aware Semantic Annotation of Mobility Records","authors":"Huandong Wang, Yong Li, Junjie Lin, Hancheng Cao, Depeng Jin","doi":"10.1145/3477048","DOIUrl":"https://doi.org/10.1145/3477048","url":null,"abstract":"The wide adoption of mobile devices has provided us with a massive volume of human mobility records. However, a large portion of these records is unlabeled, i.e., only have GPS coordinates without semantic information (e.g., Point of Interest (POI)). To make those unlabeled records associate with more information for further applications, it is of great importance to annotate the original data with POIs information based on the external context. Nevertheless, semantic annotation of mobility records is challenging due to three aspects: the complex relationship among multiple domains of context, the sparsity of mobility records, and difficulties in balancing personal preference and crowd preference. To address these challenges, we propose CAP, a context-aware personalized semantic annotation model, where we use a Bayesian mixture model to model the complex relationship among five domains of context—location, time, POI category, personal preference, and crowd preference. We evaluate our model on two real-world datasets, and demonstrate that our proposed method significantly outperforms the state-of-the-art algorithms by over 11.8%.","PeriodicalId":435653,"journal":{"name":"ACM Transactions on Knowledge Discovery from Data (TKDD)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122680907","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Network embedding has emerged as an effective way to deal with downstream tasks, such as node classification [16, 31, 42]. Most existing methods leverage multi-similarities between nodes such as connectivity, which considers vertices that are closely connected to be similar and structural similarity, which is measured by assessing their relations to neighbors; while these methods only focus on static graphs. In this work, we bridge connectivity and structural similarity in a uniform representation via motifs, and consequently present an algorithm for Learning Embeddings by leveraging Motifs Of Networks (LEMON), which aims to learn embeddings for vertices and various motifs. Moreover, LEMON is inherently capable of dealing with inductive learning tasks for dynamic graphs. To validate the effectiveness and efficiency, we conduct various experiments on two real-world datasets and five public datasets from diverse domains. Through comparison with state-of-the-art baseline models, we find that LEMON achieves significant improvements in downstream tasks. We release our code on Github at https://github.com/larry2020626/LEMON.
网络嵌入已经成为处理下游任务的有效方法，如节点分类[16,31,42]。大多数现有方法利用节点之间的多重相似性，如连通性，它认为紧密连接的顶点是相似的和结构相似性，这是通过评估它们与邻居的关系来衡量的;而这些方法只关注静态图形。在这项工作中，我们通过motif在统一表示中架起连接和结构相似性的桥梁，并因此提出了一种利用motifs Of Networks (LEMON)学习嵌入的算法，该算法旨在学习顶点和各种motif的嵌入。此外，LEMON天生就有能力处理动态图的归纳学习任务。为了验证有效性和效率，我们在两个真实数据集和五个来自不同领域的公共数据集上进行了各种实验。通过与最先进的基线模型的比较，我们发现LEMON在下游任务中取得了显著的改进。我们在Github上发布代码:https://github.com/larry2020626/LEMON。
{"title":"Network Embedding via Motifs","authors":"Ping Shao, Yang Yang, Shengyao Xu, Chunping Wang","doi":"10.1145/3473911","DOIUrl":"https://doi.org/10.1145/3473911","url":null,"abstract":"Network embedding has emerged as an effective way to deal with downstream tasks, such as node classification [16, 31, 42]. Most existing methods leverage multi-similarities between nodes such as connectivity, which considers vertices that are closely connected to be similar and structural similarity, which is measured by assessing their relations to neighbors; while these methods only focus on static graphs. In this work, we bridge connectivity and structural similarity in a uniform representation via motifs, and consequently present an algorithm for Learning Embeddings by leveraging Motifs Of Networks (LEMON), which aims to learn embeddings for vertices and various motifs. Moreover, LEMON is inherently capable of dealing with inductive learning tasks for dynamic graphs. To validate the effectiveness and efficiency, we conduct various experiments on two real-world datasets and five public datasets from diverse domains. Through comparison with state-of-the-art baseline models, we find that LEMON achieves significant improvements in downstream tasks. We release our code on Github at https://github.com/larry2020626/LEMON.","PeriodicalId":435653,"journal":{"name":"ACM Transactions on Knowledge Discovery from Data (TKDD)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128965582","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xingjian Li, H. Xiong, Zeyu Chen, Jun Huan, Ji Liu, Chengzhong Xu, D. Dou
Transfer learning through fine-tuning a pre-trained neural network with an extremely large dataset, such as ImageNet, can significantly improve and accelerate training while the accuracy is frequently bottlenecked by the limited dataset size of the new target task. To solve the problem, some regularization methods, constraining the outer layer weights of the target network using the starting point as references (SPAR), have been studied. In this article, we propose a novel regularized transfer learning framework operatorname{DELTA} , namely DEep Learning Transfer using Feature Map with Attention. Instead of constraining the weights of neural network, operatorname{DELTA} aims at preserving the outer layer outputs of the source network. Specifically, in addition to minimizing the empirical loss, operatorname{DELTA} aligns the outer layer outputs of two networks, through constraining a subset of feature maps that are precisely selected by attention that has been learned in a supervised learning manner. We evaluate operatorname{DELTA} with the state-of-the-art algorithms, including L^2 and emph {L}^2text{-}SP . The experiment results show that our method outperforms these baselines with higher accuracy for new tasks. Code has been made publicly available.1
迁移学习通过对具有超大数据集(如ImageNet)的预训练神经网络进行微调，可以显著提高和加快训练速度，但由于新目标任务的数据集大小有限，迁移学习的准确性经常受到瓶颈。为了解决这一问题，研究了以起始点为参考约束目标网络外层权值的正则化方法。在本文中，我们提出了一个新的正则化迁移学习框架operatorname{DELTA}，即使用Feature Map with Attention的深度学习迁移。operatorname{DELTA}的目的是保留源网络的外层输出，而不是约束神经网络的权重。具体来说，除了最小化经验损失之外，operatorname{DELTA}通过约束特征映射的子集来对齐两个网络的外层输出，这些特征映射是由以监督学习的方式学习的注意力精确选择的。我们使用最先进的算法评估operatorname{DELTA}，包括L^2和emph {L}^2text{-}SP。实验结果表明，对于新任务，我们的方法具有更高的准确率。代码已经公开发布
{"title":"Knowledge Distillation with Attention for Deep Transfer Learning of Convolutional Networks","authors":"Xingjian Li, H. Xiong, Zeyu Chen, Jun Huan, Ji Liu, Chengzhong Xu, D. Dou","doi":"10.1145/3473912","DOIUrl":"https://doi.org/10.1145/3473912","url":null,"abstract":"Transfer learning through fine-tuning a pre-trained neural network with an extremely large dataset, such as ImageNet, can significantly improve and accelerate training while the accuracy is frequently bottlenecked by the limited dataset size of the new target task. To solve the problem, some regularization methods, constraining the outer layer weights of the target network using the starting point as references (SPAR), have been studied. In this article, we propose a novel regularized transfer learning framework operatorname{DELTA} , namely DEep Learning Transfer using Feature Map with Attention. Instead of constraining the weights of neural network, operatorname{DELTA} aims at preserving the outer layer outputs of the source network. Specifically, in addition to minimizing the empirical loss, operatorname{DELTA} aligns the outer layer outputs of two networks, through constraining a subset of feature maps that are precisely selected by attention that has been learned in a supervised learning manner. We evaluate operatorname{DELTA} with the state-of-the-art algorithms, including L^2 and emph {L}^2text{-}SP . The experiment results show that our method outperforms these baselines with higher accuracy for new tasks. Code has been made publicly available.1","PeriodicalId":435653,"journal":{"name":"ACM Transactions on Knowledge Discovery from Data (TKDD)","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131426975","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Liang Zhao, Yuyang Gao, Jieping Ye, Feng Chen, Yanfang Ye, Chang-Tien Lu, Naren Ramakrishnan
The forecasting of significant societal events such as civil unrest and economic crisis is an interesting and challenging problem which requires both timeliness, precision, and comprehensiveness. Significant societal events are influenced and indicated jointly by multiple aspects of a society, including its economics, politics, and culture. Traditional forecasting methods based on a single data source find it hard to cover all these aspects comprehensively, thus limiting model performance. Multi-source event forecasting has proven promising but still suffers from several challenges, including (1) geographical hierarchies in multi-source data features, (2) hierarchical missing values, (3) characterization of structured feature sparsity, and (4) difficulty in model’s online update with incomplete multiple sources. This article proposes a novel feature learning model that concurrently addresses all the above challenges. Specifically, given multi-source data from different geographical levels, we design a new forecasting model by characterizing the lower-level features’ dependence on higher-level features. To handle the correlations amidst structured feature sets and deal with missing values among the coupled features, we propose a novel feature learning model based on an Nth-order strong hierarchy and fused-overlapping group Lasso. An efficient algorithm is developed to optimize model parameters and ensure global optima. More importantly, to enable the model update in real time, the online learning algorithm is formulated and active set techniques are leveraged to resolve the crucial challenge when new patterns of missing features appear in real time. Extensive experiments on 10 datasets in different domains demonstrate the effectiveness and efficiency of the proposed models.
{"title":"Spatio-Temporal Event Forecasting Using Incremental Multi-Source Feature Learning","authors":"Liang Zhao, Yuyang Gao, Jieping Ye, Feng Chen, Yanfang Ye, Chang-Tien Lu, Naren Ramakrishnan","doi":"10.1145/3464976","DOIUrl":"https://doi.org/10.1145/3464976","url":null,"abstract":"The forecasting of significant societal events such as civil unrest and economic crisis is an interesting and challenging problem which requires both timeliness, precision, and comprehensiveness. Significant societal events are influenced and indicated jointly by multiple aspects of a society, including its economics, politics, and culture. Traditional forecasting methods based on a single data source find it hard to cover all these aspects comprehensively, thus limiting model performance. Multi-source event forecasting has proven promising but still suffers from several challenges, including (1) geographical hierarchies in multi-source data features, (2) hierarchical missing values, (3) characterization of structured feature sparsity, and (4) difficulty in model’s online update with incomplete multiple sources. This article proposes a novel feature learning model that concurrently addresses all the above challenges. Specifically, given multi-source data from different geographical levels, we design a new forecasting model by characterizing the lower-level features’ dependence on higher-level features. To handle the correlations amidst structured feature sets and deal with missing values among the coupled features, we propose a novel feature learning model based on an Nth-order strong hierarchy and fused-overlapping group Lasso. An efficient algorithm is developed to optimize model parameters and ensure global optima. More importantly, to enable the model update in real time, the online learning algorithm is formulated and active set techniques are leveraged to resolve the crucial challenge when new patterns of missing features appear in real time. Extensive experiments on 10 datasets in different domains demonstrate the effectiveness and efficiency of the proposed models.","PeriodicalId":435653,"journal":{"name":"ACM Transactions on Knowledge Discovery from Data (TKDD)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128476583","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Riccardo Cantini, F. Marozzo, Giovanni Bruno, Paolo Trunfio
The growing use of microblogging platforms is generating a huge amount of posts that need effective methods to be classified and searched. In Twitter and other social media platforms, hashtags are exploited by users to facilitate the search, categorization, and spread of posts. Choosing the appropriate hashtags for a post is not always easy for users, and therefore posts are often published without hashtags or with hashtags not well defined. To deal with this issue, we propose a new model, called HASHET (HAshtag recommendation using Sentence-to-Hashtag Embedding Translation), aimed at suggesting a relevant set of hashtags for a given post. HASHET is based on two independent latent spaces for embedding the text of a post and the hashtags it contains. A mapping process based on a multi-layer perceptron is then used for learning a translation from the semantic features of the text to the latent representation of its hashtags. We evaluated the effectiveness of two language representation models for sentence embedding and tested different search strategies for semantic expansion, finding out that the combined use of BERT (Bidirectional Encoder Representation from Transformer) and a global expansion strategy leads to the best recommendation results. HASHET has been evaluated on two real-world case studies related to the 2016 United States presidential election and COVID-19 pandemic. The results reveal the effectiveness of HASHET in predicting one or more correct hashtags, with an average F-score up to 0.82 and a recommendation hit-rate up to 0.92. Our approach has been compared to the most relevant techniques used in the literature (generative models, unsupervised models, and attention-based supervised models) by achieving up to 15% improvement in F-score for the hashtag recommendation task and 9% for the topic discovery task.
微博平台的使用越来越多，产生了大量的帖子，需要有效的方法来分类和搜索。在Twitter和其他社交媒体平台上，用户利用标签来促进帖子的搜索、分类和传播。对于用户来说，为帖子选择合适的标签并不总是那么容易，因此发布的帖子通常没有标签，或者标签定义不明确。为了解决这个问题，我们提出了一个新的模型，称为HASHET (HAshtag recommendation using Sentence-to-Hashtag Embedding Translation)，旨在为给定的帖子推荐一组相关的HAshtag。HASHET基于两个独立的潜在空间，用于嵌入帖子的文本及其包含的标签。然后使用基于多层感知器的映射过程来学习从文本的语义特征到其标签的潜在表示的翻译。我们评估了两种语言表示模型用于句子嵌入的有效性，并测试了不同的语义扩展搜索策略，发现BERT (Bidirectional Encoder representation from Transformer)和全局扩展策略的结合使用可以获得最佳的推荐结果。HASHET在与2016年美国总统大选和COVID-19大流行有关的两个现实案例研究中进行了评估。结果显示HASHET在预测一个或多个正确标签方面的有效性，平均f值高达0.82，推荐命中率高达0.92。我们的方法已经与文献中使用的最相关的技术(生成模型，无监督模型和基于注意力的监督模型)进行了比较，在标签推荐任务中实现了高达15%的f分数提高，在主题发现任务中实现了9%的f分数提高。
{"title":"Learning Sentence-to-Hashtags Semantic Mapping for Hashtag Recommendation on Microblogs","authors":"Riccardo Cantini, F. Marozzo, Giovanni Bruno, Paolo Trunfio","doi":"10.1145/3466876","DOIUrl":"https://doi.org/10.1145/3466876","url":null,"abstract":"The growing use of microblogging platforms is generating a huge amount of posts that need effective methods to be classified and searched. In Twitter and other social media platforms, hashtags are exploited by users to facilitate the search, categorization, and spread of posts. Choosing the appropriate hashtags for a post is not always easy for users, and therefore posts are often published without hashtags or with hashtags not well defined. To deal with this issue, we propose a new model, called HASHET (HAshtag recommendation using Sentence-to-Hashtag Embedding Translation), aimed at suggesting a relevant set of hashtags for a given post. HASHET is based on two independent latent spaces for embedding the text of a post and the hashtags it contains. A mapping process based on a multi-layer perceptron is then used for learning a translation from the semantic features of the text to the latent representation of its hashtags. We evaluated the effectiveness of two language representation models for sentence embedding and tested different search strategies for semantic expansion, finding out that the combined use of BERT (Bidirectional Encoder Representation from Transformer) and a global expansion strategy leads to the best recommendation results. HASHET has been evaluated on two real-world case studies related to the 2016 United States presidential election and COVID-19 pandemic. The results reveal the effectiveness of HASHET in predicting one or more correct hashtags, with an average F-score up to 0.82 and a recommendation hit-rate up to 0.92. Our approach has been compared to the most relevant techniques used in the literature (generative models, unsupervised models, and attention-based supervised models) by achieving up to 15% improvement in F-score for the hashtag recommendation task and 9% for the topic discovery task.","PeriodicalId":435653,"journal":{"name":"ACM Transactions on Knowledge Discovery from Data (TKDD)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121736247","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Heterogeneous information network (HIN) embedding, aiming to project HIN into a low-dimensional space, has attracted considerable research attention. Most of the existing HIN embedding methods focus on preserving the inherent network structure and semantic correlations in Euclidean spaces. However, one fundamental problem is whether the Euclidean spaces are the intrinsic spaces of HIN? Recent researches find the complex network with hyperbolic geometry can naturally reflect some properties, e.g., hierarchical and power-law structure. In this article, we make an effort toward embedding HIN in hyperbolic spaces. We analyze the structures of three HINs and discover some properties, e.g., the power-law distribution, also exist in HINs. Therefore, we propose a novel HIN embedding model HHNE. Specifically, to capture the structure and semantic relations between nodes, HHNE employs the meta-path guided random walk to sample the sequences for each node. Then HHNE exploits the hyperbolic distance as the proximity measurement. We also derive an effective optimization strategy to update the hyperbolic embeddings iteratively. Since HHNE optimizes different relations in a single space, we further propose the extended model HHNE++. HHNE++ models different relations in different spaces, which enables it to learn complex interactions in HINs. The optimization strategy of HHNE++ is also derived to update the parameters of HHNE++ in a principle manner. The experimental results demonstrate the effectiveness of our proposed models.
{"title":"Embedding Heterogeneous Information Network in Hyperbolic Spaces","authors":"Yiding Zhang, Xiao Wang, Nian Liu, C. Shi","doi":"10.1145/3468674","DOIUrl":"https://doi.org/10.1145/3468674","url":null,"abstract":"Heterogeneous information network (HIN) embedding, aiming to project HIN into a low-dimensional space, has attracted considerable research attention. Most of the existing HIN embedding methods focus on preserving the inherent network structure and semantic correlations in Euclidean spaces. However, one fundamental problem is whether the Euclidean spaces are the intrinsic spaces of HIN? Recent researches find the complex network with hyperbolic geometry can naturally reflect some properties, e.g., hierarchical and power-law structure. In this article, we make an effort toward embedding HIN in hyperbolic spaces. We analyze the structures of three HINs and discover some properties, e.g., the power-law distribution, also exist in HINs. Therefore, we propose a novel HIN embedding model HHNE. Specifically, to capture the structure and semantic relations between nodes, HHNE employs the meta-path guided random walk to sample the sequences for each node. Then HHNE exploits the hyperbolic distance as the proximity measurement. We also derive an effective optimization strategy to update the hyperbolic embeddings iteratively. Since HHNE optimizes different relations in a single space, we further propose the extended model HHNE++. HHNE++ models different relations in different spaces, which enables it to learn complex interactions in HINs. The optimization strategy of HHNE++ is also derived to update the parameters of HHNE++ in a principle manner. The experimental results demonstrate the effectiveness of our proposed models.","PeriodicalId":435653,"journal":{"name":"ACM Transactions on Knowledge Discovery from Data (TKDD)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133826485","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cross-network anchor link discovery is an important research problem and has many applications in heterogeneous social network. Existing schemes of cross-network anchor link discovery can provide reasonable link discovery results, but the quality of these results depends on the features of the platform. Therefore, there is no theoretical guarantee to the stability. This article employs user embedding feature to model the relationship between cross-platform accounts, that is, the more similar the user embedding features are, the more similar the two accounts are. The similarity of user embedding features is determined by the distance of the user features in the latent space. Based on the user embedding features, this article proposes an embedding representation-based method Con&Net(Content and Network) to solve cross-network anchor link discovery problem. Con&Net combines the user’s profile features, user-generated content (UGC) features, and user’s social structure features to measure the similarity of two user accounts. Con&Net first trains the user’s profile features to get profile embedding. Then it trains the network structure of the nodes to get structure embedding. It connects the two features through vector concatenating, and calculates the cosine similarity of the vector based on the embedding vector. This cosine similarity is used to measure the similarity of the user accounts. Finally, Con&Net predicts the link based on similarity for account pairs across the two networks. A large number of experiments in Sina Weibo and Twitter networks show that the proposed method Con&Net is better than state-of-the-art method. The area under the curve (AUC) value of the receiver operating characteristic (ROC) curve predicted by the anchor link is 11% higher than the baseline method, and Precision@30 is 25% higher than the baseline method.
跨网络锚链接发现是一个重要的研究问题，在异构社会网络中有着广泛的应用。现有的跨网锚点链接发现方案可以提供合理的链接发现结果，但这些结果的质量取决于平台的特点。因此，对其稳定性没有理论上的保证。本文采用用户嵌入特征对跨平台账号之间的关系进行建模，即用户嵌入特征越相似，两个账号越相似。用户嵌入特征的相似度由用户特征在潜在空间中的距离决定。本文基于用户嵌入的特点，提出了一种基于嵌入表示的方法Con&Net(Content and Network)来解决跨网络锚链接发现问题。Con&Net结合用户的个人资料特征、用户生成内容(UGC)特征和用户的社会结构特征来衡量两个用户账户的相似性。Con&Net首先训练用户的配置文件特征以获得配置文件嵌入。然后对节点的网络结构进行训练，得到结构嵌入。它通过向量拼接将两个特征连接起来，并基于嵌入向量计算向量的余弦相似度。余弦相似度用于度量用户帐户的相似度。最后，Con&Net根据两个网络上帐户对的相似性预测链接。在新浪微博和Twitter网络上进行的大量实验表明，本文提出的方法Con&Net优于现有的方法。锚链预测的受试者工作特征(ROC)曲线下面积(AUC)值比基线法高11%，Precision@30比基线法高25%。
{"title":"Con&Net: A Cross-Network Anchor Link Discovery Method Based on Embedding Representation","authors":"Xueyuan Wang, Hongpo Zhang, Zongmin Wang, Yaqiong Qiao, Jiangtao Ma, Honghua Dai","doi":"10.1145/3469083","DOIUrl":"https://doi.org/10.1145/3469083","url":null,"abstract":"Cross-network anchor link discovery is an important research problem and has many applications in heterogeneous social network. Existing schemes of cross-network anchor link discovery can provide reasonable link discovery results, but the quality of these results depends on the features of the platform. Therefore, there is no theoretical guarantee to the stability. This article employs user embedding feature to model the relationship between cross-platform accounts, that is, the more similar the user embedding features are, the more similar the two accounts are. The similarity of user embedding features is determined by the distance of the user features in the latent space. Based on the user embedding features, this article proposes an embedding representation-based method Con&Net(Content and Network) to solve cross-network anchor link discovery problem. Con&Net combines the user’s profile features, user-generated content (UGC) features, and user’s social structure features to measure the similarity of two user accounts. Con&Net first trains the user’s profile features to get profile embedding. Then it trains the network structure of the nodes to get structure embedding. It connects the two features through vector concatenating, and calculates the cosine similarity of the vector based on the embedding vector. This cosine similarity is used to measure the similarity of the user accounts. Finally, Con&Net predicts the link based on similarity for account pairs across the two networks. A large number of experiments in Sina Weibo and Twitter networks show that the proposed method Con&Net is better than state-of-the-art method. The area under the curve (AUC) value of the receiver operating characteristic (ROC) curve predicted by the anchor link is 11% higher than the baseline method, and Precision@30 is 25% higher than the baseline method.","PeriodicalId":435653,"journal":{"name":"ACM Transactions on Knowledge Discovery from Data (TKDD)","volume":"135 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133239394","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Recommender algorithms combining knowledge graph and graph convolutional network are becoming more and more popular recently. Specifically, attributes describing the items to be recommended are often used as additional information. These attributes along with items are highly interconnected, intrinsically forming a Knowledge Graph (KG). These algorithms use KGs as an auxiliary data source to alleviate the negative impact of data sparsity. However, these graph convolutional network based algorithms do not distinguish the importance of different neighbors of entities in the KG, and according to Pareto’s principle, the important neighbors only account for a small proportion. These traditional algorithms can not fully mine the useful information in the KG. To fully release the power of KGs for building recommender systems, we propose in this article KRAN, a Knowledge Refining Attention Network, which can subtly capture the characteristics of the KG and thus boost recommendation performance. We first introduce a traditional attention mechanism into the KG processing, making the knowledge extraction more targeted, and then propose a refining mechanism to improve the traditional attention mechanism to extract the knowledge in the KG more effectively. More precisely, KRAN is designed to use our proposed knowledge-refining attention mechanism to aggregate and obtain the representations of the entities (both attributes and items) in the KG. Our knowledge-refining attention mechanism first measures the relevance between an entity and it’s neighbors in the KG by attention coefficients, and then further refines the attention coefficients using a “richer-get-richer” principle, in order to focus on highly relevant neighbors while eliminating less relevant neighbors for noise reduction. In addition, for the item cold start problem, we propose KRAN-CD, a variant of KRAN, which further incorporates pre-trained KG embeddings to handle cold start items. Experiments show that KRAN and KRAN-CD consistently outperform state-of-the-art baselines across different settings.
{"title":"KRAN: Knowledge Refining Attention Network for Recommendation","authors":"Zhenyu Zhang, Lei Zhang, Dingqi Yang, Liu Yang","doi":"10.1145/3470783","DOIUrl":"https://doi.org/10.1145/3470783","url":null,"abstract":"Recommender algorithms combining knowledge graph and graph convolutional network are becoming more and more popular recently. Specifically, attributes describing the items to be recommended are often used as additional information. These attributes along with items are highly interconnected, intrinsically forming a Knowledge Graph (KG). These algorithms use KGs as an auxiliary data source to alleviate the negative impact of data sparsity. However, these graph convolutional network based algorithms do not distinguish the importance of different neighbors of entities in the KG, and according to Pareto’s principle, the important neighbors only account for a small proportion. These traditional algorithms can not fully mine the useful information in the KG. To fully release the power of KGs for building recommender systems, we propose in this article KRAN, a Knowledge Refining Attention Network, which can subtly capture the characteristics of the KG and thus boost recommendation performance. We first introduce a traditional attention mechanism into the KG processing, making the knowledge extraction more targeted, and then propose a refining mechanism to improve the traditional attention mechanism to extract the knowledge in the KG more effectively. More precisely, KRAN is designed to use our proposed knowledge-refining attention mechanism to aggregate and obtain the representations of the entities (both attributes and items) in the KG. Our knowledge-refining attention mechanism first measures the relevance between an entity and it’s neighbors in the KG by attention coefficients, and then further refines the attention coefficients using a “richer-get-richer” principle, in order to focus on highly relevant neighbors while eliminating less relevant neighbors for noise reduction. In addition, for the item cold start problem, we propose KRAN-CD, a variant of KRAN, which further incorporates pre-trained KG embeddings to handle cold start items. Experiments show that KRAN and KRAN-CD consistently outperform state-of-the-art baselines across different settings.","PeriodicalId":435653,"journal":{"name":"ACM Transactions on Knowledge Discovery from Data (TKDD)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122825776","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jianfei Yin, Ruili Wang, Yeqing Guo, Yizhe Bai, Shunda Ju, Weili Liu, J. Huang
This article proposes a deep learning solution to the online portfolio selection problem based on learning a latent structure directly from a price time series. It introduces a novel wealth flow matrix for representing a latent structure that has special regular conditions to encode the knowledge about the relative strengths of assets in portfolios. Therefore, a wealth flow model (WFM) is proposed to learn wealth flow matrices and maximize portfolio wealth simultaneously. Compared with existing approaches, our work has several distinctive benefits: (1) the learning of wealth flow matrices makes our model more generalizable than models that only predict wealth proportion vectors, and (2) the exploitation of wealth flow matrices and the exploration of wealth growth are integrated into our deep reinforcement algorithm for the WFM. These benefits, in combination, lead to a highly-effective approach for generating reasonable investment behavior, including short-term trend following, the following of a few losers, no self-investment, and sparse portfolios. Extensive experiments on five benchmark datasets from real-world stock markets confirm the theoretical advantage of the WFM, which achieves the Pareto improvements in terms of multiple performance indicators and the steady growth of wealth over the state-of-the-art algorithms.
{"title":"Wealth Flow Model: Online Portfolio Selection Based on Learning Wealth Flow Matrices","authors":"Jianfei Yin, Ruili Wang, Yeqing Guo, Yizhe Bai, Shunda Ju, Weili Liu, J. Huang","doi":"10.1145/3464308","DOIUrl":"https://doi.org/10.1145/3464308","url":null,"abstract":"This article proposes a deep learning solution to the online portfolio selection problem based on learning a latent structure directly from a price time series. It introduces a novel wealth flow matrix for representing a latent structure that has special regular conditions to encode the knowledge about the relative strengths of assets in portfolios. Therefore, a wealth flow model (WFM) is proposed to learn wealth flow matrices and maximize portfolio wealth simultaneously. Compared with existing approaches, our work has several distinctive benefits: (1) the learning of wealth flow matrices makes our model more generalizable than models that only predict wealth proportion vectors, and (2) the exploitation of wealth flow matrices and the exploration of wealth growth are integrated into our deep reinforcement algorithm for the WFM. These benefits, in combination, lead to a highly-effective approach for generating reasonable investment behavior, including short-term trend following, the following of a few losers, no self-investment, and sparse portfolios. Extensive experiments on five benchmark datasets from real-world stock markets confirm the theoretical advantage of the WFM, which achieves the Pareto improvements in terms of multiple performance indicators and the steady growth of wealth over the state-of-the-art algorithms.","PeriodicalId":435653,"journal":{"name":"ACM Transactions on Knowledge Discovery from Data (TKDD)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115736463","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：