Pub Date : 2023-08-01DOI: 10.1109/TBDATA.2023.3300547
Chenxu Wang;Fuli Feng;Yang Zhang;Qifan Wang;Xunhan Hu;Xiangnan He
Historical interactions are the default choice for recommender model training, which typically exhibit high sparsity, i.e., most user-item pairs are unobserved missing data. A standard choice is treating the missing data as negative training samples and estimating interaction likelihood between user-item pairs along with the observed interactions. In this way, some potential interactions are inevitably mislabeled during training, which will hurt the model fidelity, hindering the model to recall the mislabeled items, especially the long-tail ones. In this work, we investigate the mislabeling issue from a new perspective of aleatoric uncertainty , which describes the inherent randomness of missing data. The randomness pushes us to go beyond merely the interaction likelihood and embrace aleatoric uncertainty modeling. Towards this end, we propose a new Aleatoric Uncertainty-aware Recommendation (AUR) framework that consists of a new uncertainty estimator along with a normal recommender model. According to the theory of aleatoric uncertainty, we derive a new recommendation objective to learn the estimator. As the chance of mislabeling reflects the potential of a pair, AUR makes recommendations according to the uncertainty, which is demonstrated to improve the recommendation performance of less popular items without sacrificing the overall performance. We instantiate AUR on three representative recommender models: Matrix Factorization (MF), LightGCN, and VAE from mainstream model architectures. Extensive results on four real-world datasets validate the effectiveness of AUR w.r.t. better recommendation results, especially on long-tail items.
{"title":"Rethinking Missing Data: Aleatoric Uncertainty-Aware Recommendation","authors":"Chenxu Wang;Fuli Feng;Yang Zhang;Qifan Wang;Xunhan Hu;Xiangnan He","doi":"10.1109/TBDATA.2023.3300547","DOIUrl":"https://doi.org/10.1109/TBDATA.2023.3300547","url":null,"abstract":"Historical interactions are the default choice for recommender model training, which typically exhibit high sparsity, i.e., most user-item pairs are unobserved missing data. A standard choice is treating the missing data as negative training samples and estimating interaction likelihood between user-item pairs along with the observed interactions. In this way, some potential interactions are inevitably mislabeled during training, which will hurt the model fidelity, hindering the model to recall the mislabeled items, especially the long-tail ones. In this work, we investigate the mislabeling issue from a new perspective of \u0000<italic>aleatoric uncertainty</i>\u0000, which describes the inherent randomness of missing data. The randomness pushes us to go beyond merely the interaction likelihood and embrace aleatoric uncertainty modeling. Towards this end, we propose a new \u0000<italic>Aleatoric Uncertainty-aware Recommendation</i>\u0000 (AUR) framework that consists of a new uncertainty estimator along with a normal recommender model. According to the theory of aleatoric uncertainty, we derive a new recommendation objective to learn the estimator. As the chance of mislabeling reflects the potential of a pair, AUR makes recommendations according to the uncertainty, which is demonstrated to improve the recommendation performance of less popular items without sacrificing the overall performance. We instantiate AUR on three representative recommender models: Matrix Factorization (MF), LightGCN, and VAE from mainstream model architectures. Extensive results on four real-world datasets validate the effectiveness of AUR w.r.t. better recommendation results, especially on long-tail items.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"9 6","pages":"1607-1619"},"PeriodicalIF":7.2,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138138211","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}
Pub Date : 2023-07-19DOI: 10.1109/TBDATA.2023.3296936
Shu Zhao;Wenyu Wang;Ziwei Du;Jie Chen;Zhen Duan
Recent studies have shown that Graph Neural Networks (GNNs) are vulnerable to well-designed and imperceptible adversarial attack. Attacks utilizing gradient information are widely used in the field of attack due to their simplicity and efficiency. However, several challenges are faced by gradient-based attacks: 1) Generate perturbations use white-box attacks (i.e., requiring access to the full knowledge of the model), which is not practical in the real world; 2) It is easy to drop into local optima; and 3) The perturbation budget is not limited and might be detected even if the number of modified edges is small. Faced with the above challenges, this article proposes a black-box adversarial attack method, named NAG-R, which consists of two modules known as N esterov A ccelerated G radient attack module and R ewiring optimization module. Specifically, inspired by adversarial attacks on images, the first module generates perturbations by introducing Nesterov Accelerated Gradient (NAG) to avoid falling into local optima. The second module keeps the fundamental properties of the graph (e.g., the total degree of the graph) unchanged through a rewiring operation, thus ensuring that perturbations are imperceptible. Intensive experiments show that our method has significant attack success and transferability over existing state-of-the-art gradient-based attack methods.
{"title":"A Black-Box Adversarial Attack Method via Nesterov Accelerated Gradient and Rewiring Towards Attacking Graph Neural Networks","authors":"Shu Zhao;Wenyu Wang;Ziwei Du;Jie Chen;Zhen Duan","doi":"10.1109/TBDATA.2023.3296936","DOIUrl":"10.1109/TBDATA.2023.3296936","url":null,"abstract":"Recent studies have shown that Graph Neural Networks (GNNs) are vulnerable to well-designed and imperceptible adversarial attack. Attacks utilizing gradient information are widely used in the field of attack due to their simplicity and efficiency. However, several challenges are faced by gradient-based attacks: 1) Generate perturbations use white-box attacks (i.e., requiring access to the full knowledge of the model), which is not practical in the real world; 2) It is easy to drop into local optima; and 3) The perturbation budget is not limited and might be detected even if the number of modified edges is small. Faced with the above challenges, this article proposes a black-box adversarial attack method, named NAG-R, which consists of two modules known as \u0000<bold>N</b>\u0000esterov \u0000<bold>A</b>\u0000ccelerated \u0000<bold>G</b>\u0000radient attack module and \u0000<bold>R</b>\u0000ewiring optimization module. Specifically, inspired by adversarial attacks on images, the first module generates perturbations by introducing Nesterov Accelerated Gradient (NAG) to avoid falling into local optima. The second module keeps the fundamental properties of the graph (e.g., the total degree of the graph) unchanged through a rewiring operation, thus ensuring that perturbations are imperceptible. Intensive experiments show that our method has significant attack success and transferability over existing state-of-the-art gradient-based attack methods.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"9 6","pages":"1586-1597"},"PeriodicalIF":7.2,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62972856","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}
Multi-center analysis has attracted increasing attention in brain disease diagnosis, because it provides effective approaches to improve disease diagnostic performance by making use of the information from different centers. However, in practical multi-center applications, data uncertainty is more common than that in single center, which brings challenge to robust modeling of diagnosis. In this article, we proposed a multi-discriminator active adversarial network (MDAAN) to alleviate the uncertainties at the center, feature, and label levels for multi-center brain disease diagnosis. First, we extract the latent invariant representation of the source center and target center to reduce domain shift by adversarial learning strategy. Second, the proposed method adaptively evaluates the contribution of different source centers in fusion by measuring data distribution difference between source and target center. Moreover, only the hard learning samples in target center are identified to label with low sample annotation cost. Finally, we treat the selected samples as the auxiliary domain to alleviate the negative transfer and improve the robustness of the multi-center model. We extensively compare the proposed approach with several state-of-the-art multi-center methods on the five-center schizophrenia dataset, and the results demonstrate that our method is superior to the previous methods in identifying brain disease.
{"title":"Multi-Discriminator Active Adversarial Network for Multi-Center Brain Disease Diagnosis","authors":"Qi Zhu;Qiming Yang;Mingming Wang;Xiangyu Xu;Yuwu Lu;Wei Shao;Daoqiang Zhang","doi":"10.1109/TBDATA.2023.3294000","DOIUrl":"10.1109/TBDATA.2023.3294000","url":null,"abstract":"Multi-center analysis has attracted increasing attention in brain disease diagnosis, because it provides effective approaches to improve disease diagnostic performance by making use of the information from different centers. However, in practical multi-center applications, data uncertainty is more common than that in single center, which brings challenge to robust modeling of diagnosis. In this article, we proposed a multi-discriminator active adversarial network (MDAAN) to alleviate the uncertainties at the center, feature, and label levels for multi-center brain disease diagnosis. First, we extract the latent invariant representation of the source center and target center to reduce domain shift by adversarial learning strategy. Second, the proposed method adaptively evaluates the contribution of different source centers in fusion by measuring data distribution difference between source and target center. Moreover, only the hard learning samples in target center are identified to label with low sample annotation cost. Finally, we treat the selected samples as the auxiliary domain to alleviate the negative transfer and improve the robustness of the multi-center model. We extensively compare the proposed approach with several state-of-the-art multi-center methods on the five-center schizophrenia dataset, and the results demonstrate that our method is superior to the previous methods in identifying brain disease.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"9 6","pages":"1575-1585"},"PeriodicalIF":7.2,"publicationDate":"2023-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62972246","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}
Pub Date : 2023-07-07DOI: 10.1109/TBDATA.2023.3293279
Rui Song;Bin Xiao;Yubo Song;Songtao Guo;Yuanyuan Yang
Data immutability, transparency and decentralization of blockchain make it widely used in various fields, such as Internet of things, finance, energy and healthcare. With the advent of the Big Data era, various companies and organizations urgently need data from other parties for data analysis and mining to provide better services. Therefore, data sharing and data exchange have become an enormous industry. Traditional centralized data platforms face many problems, such as privacy leakage, high transaction costs and lack of interoperability. Introducing blockchain into this field can address these problems, while providing decentralized data storage and exchange, access control, identity authentication and copyright protection. Although many impressive blockchain-based schemes for data sharing or data exchange scenarios have been presented in recent years, there is still a lack of review and summary of work in this area. In this paper, we conduct a detailed survey of blockchain-based data sharing and data exchange platforms, discussing the latest technical architectures and research results in this field. In particular, we first survey the current blockchain-based data sharing solutions and provide a detailed analysis of system architecture, access control, interoperability, and security. We then review blockchain-based data exchange systems and data marketplaces, discussing trading process, monetization, copyright protection and other related topics.
{"title":"A Survey of Blockchain-Based Schemes for Data Sharing and Exchange","authors":"Rui Song;Bin Xiao;Yubo Song;Songtao Guo;Yuanyuan Yang","doi":"10.1109/TBDATA.2023.3293279","DOIUrl":"10.1109/TBDATA.2023.3293279","url":null,"abstract":"Data immutability, transparency and decentralization of blockchain make it widely used in various fields, such as Internet of things, finance, energy and healthcare. With the advent of the Big Data era, various companies and organizations urgently need data from other parties for data analysis and mining to provide better services. Therefore, data sharing and data exchange have become an enormous industry. Traditional centralized data platforms face many problems, such as privacy leakage, high transaction costs and lack of interoperability. Introducing blockchain into this field can address these problems, while providing decentralized data storage and exchange, access control, identity authentication and copyright protection. Although many impressive blockchain-based schemes for data sharing or data exchange scenarios have been presented in recent years, there is still a lack of review and summary of work in this area. In this paper, we conduct a detailed survey of blockchain-based data sharing and data exchange platforms, discussing the latest technical architectures and research results in this field. In particular, we first survey the current blockchain-based data sharing solutions and provide a detailed analysis of system architecture, access control, interoperability, and security. We then review blockchain-based data exchange systems and data marketplaces, discussing trading process, monetization, copyright protection and other related topics.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"9 6","pages":"1477-1495"},"PeriodicalIF":7.2,"publicationDate":"2023-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62972060","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}
Pub Date : 2023-07-03DOI: 10.1109/TBDATA.2023.3291563
Qian Li;Shu Guo;Jia Wu;Jianxin Li;Jiawei Sheng;Hao Peng;Lihong Wang
Event extraction (EE), which acquires structural event knowledge from texts, can be divided into two sub-tasks: event type classification and element extraction (namely identifying triggers and arguments under different role patterns). As different event types always own distinct extraction schemas (i.e., role patterns), previous work on EE usually follows an isolated learning paradigm, performing element extraction independently for different event types. It ignores meaningful associations among event types and argument roles, leading to relatively poor performance for less frequent types/roles. This paper proposes a novel neural association framework for the EE task. Given a document, it first performs type classification via constructing a document-level event graph to associate sentence nodes of different types and adopting a document-awared graph attention network to learn sentence embeddings. Then, element extraction is achieved by building a new schema of argument roles, with a type-awared parameter inheritance mechanism to enhance role preference for extracted elements. As such, our model takes into account type and role associations during EE, enabling implicit information sharing among them. Experimental results show that our approach consistently outperforms most state-of-the-art EE methods in both sub-tasks, especially at least 2.51% and 1.12% improvement of the event trigger identification and argument role classification sub-tasks. Particularly, for types/roles with less training data, the performance is superior to the existing methods.
{"title":"Event Extraction by Associating Event Types and Argument Roles","authors":"Qian Li;Shu Guo;Jia Wu;Jianxin Li;Jiawei Sheng;Hao Peng;Lihong Wang","doi":"10.1109/TBDATA.2023.3291563","DOIUrl":"10.1109/TBDATA.2023.3291563","url":null,"abstract":"Event extraction (EE), which acquires structural event knowledge from texts, can be divided into two sub-tasks: event type classification and element extraction (namely identifying triggers and arguments under different role patterns). As different event types always own distinct extraction schemas (i.e., role patterns), previous work on EE usually follows an isolated learning paradigm, performing element extraction independently for different event types. It ignores meaningful associations among event types and argument roles, leading to relatively poor performance for less frequent types/roles. This paper proposes a novel neural association framework for the EE task. Given a document, it first performs type classification via constructing a document-level event graph to associate sentence nodes of different types and adopting a document-awared graph attention network to learn sentence embeddings. Then, element extraction is achieved by building a new schema of argument roles, with a type-awared parameter inheritance mechanism to enhance role preference for extracted elements. As such, our model takes into account type and role associations during EE, enabling implicit information sharing among them. Experimental results show that our approach consistently outperforms most state-of-the-art EE methods in both sub-tasks, especially at least 2.51% and 1.12% improvement of the event trigger identification and argument role classification sub-tasks. Particularly, for types/roles with less training data, the performance is superior to the existing methods.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"9 6","pages":"1549-1560"},"PeriodicalIF":7.2,"publicationDate":"2023-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88360714","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}
Pub Date : 2023-07-03DOI: 10.1109/TBDATA.2023.3291547
Ha Xuan Tran;Thuc Duy Le;Jiuyong Li;Lin Liu;Jixue Liu;Yanchang Zhao;Tony Waters
An emerging problem in Disability Employment Services (DES) is recommending to people with disability the right skill to upgrade and the right upgrade level to achieve maximum improvement in their employment success. This problem requires causal reasoning to estimate the individual causal effect of possible factors on the outcome to determine the most effective intervention. In this paper, we propose a causal graph based framework to solve the intervention recommendation problem for survival outcome (job retention time) and non-survival outcome (employment status). For an individual, a personalized causal graph is predicted for them. It indicates which factors affect the outcome and their causal effects at different intervention levels. Based on the causal graph, we can determine the most effective intervention for an individual, i.e., the one that can generate a maximum outcome increase. Experiments with two case studies show that our framework can help people with disability increase their employment success. Evaluations with public datasets also show the advantage of our framework in other applications.
{"title":"Personalized Interventions to Increase the Employment Success of People With Disability","authors":"Ha Xuan Tran;Thuc Duy Le;Jiuyong Li;Lin Liu;Jixue Liu;Yanchang Zhao;Tony Waters","doi":"10.1109/TBDATA.2023.3291547","DOIUrl":"10.1109/TBDATA.2023.3291547","url":null,"abstract":"An emerging problem in Disability Employment Services (DES) is recommending to people with disability the right skill to upgrade and the right upgrade level to achieve maximum improvement in their employment success. This problem requires causal reasoning to estimate the individual causal effect of possible factors on the outcome to determine the most effective intervention. In this paper, we propose a causal graph based framework to solve the intervention recommendation problem for survival outcome (job retention time) and non-survival outcome (employment status). For an individual, a personalized causal graph is predicted for them. It indicates which factors affect the outcome and their causal effects at different intervention levels. Based on the causal graph, we can determine the most effective intervention for an individual, i.e., the one that can generate a maximum outcome increase. Experiments with two case studies show that our framework can help people with disability increase their employment success. Evaluations with public datasets also show the advantage of our framework in other applications.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"9 6","pages":"1561-1574"},"PeriodicalIF":7.2,"publicationDate":"2023-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62972344","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}
Visual affordance recognition is an important research topic in robotics, human-computer interaction, and other computer vision tasks. In recent years, deep learning-based affordance recognition methods have achieved remarkable performance. However, there is no unified and intensive survey of these methods up to now. Therefore, this article reviews and investigates existing deep learning-based affordance recognition methods from a comprehensive perspective, hoping to pursue greater acceleration in this research domain. Specifically, this article first classifies affordance recognition into five tasks, delves into the methodologies of each task, and explores their rationales and essential relations. Second, several representative affordance recognition datasets are investigated carefully. Third, based on these datasets, this article provides a comprehensive performance comparison and analysis of the current affordance recognition methods, reporting the results of different methods on the same datasets and the results of each method on different datasets. Finally, this article summarizes the progress of affordance recognition, outlines the existing difficulties and provides corresponding solutions, and discusses its future application trends.
{"title":"A Survey of Visual Affordance Recognition Based on Deep Learning","authors":"Dongpan Chen;Dehui Kong;Jinghua Li;Shaofan Wang;Baocai Yin","doi":"10.1109/TBDATA.2023.3291558","DOIUrl":"10.1109/TBDATA.2023.3291558","url":null,"abstract":"Visual affordance recognition is an important research topic in robotics, human-computer interaction, and other computer vision tasks. In recent years, deep learning-based affordance recognition methods have achieved remarkable performance. However, there is no unified and intensive survey of these methods up to now. Therefore, this article reviews and investigates existing deep learning-based affordance recognition methods from a comprehensive perspective, hoping to pursue greater acceleration in this research domain. Specifically, this article first classifies affordance recognition into five tasks, delves into the methodologies of each task, and explores their rationales and essential relations. Second, several representative affordance recognition datasets are investigated carefully. Third, based on these datasets, this article provides a comprehensive performance comparison and analysis of the current affordance recognition methods, reporting the results of different methods on the same datasets and the results of each method on different datasets. Finally, this article summarizes the progress of affordance recognition, outlines the existing difficulties and provides corresponding solutions, and discusses its future application trends.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"9 6","pages":"1458-1476"},"PeriodicalIF":7.2,"publicationDate":"2023-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62972396","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}
Multivariate time series forecasting has wide applications such as traffic flow prediction, supermarket commodity demand forecasting and etc., and a large number of forecasting models have been developed. Given these models, a natural question has been raised: what theoretical limits of forecasting accuracy can these models achieve? Recent works of urban human mobility prediction have made progress on the maximum predictability that any algorithm can achieve. However, existing approaches on maximum predictability on the multivariate time series fully ignore the interrelationship between multiple variables. In this article, we propose a methodology to measure the upper limit of predictability for multivariate time series with multivariate constraint relations. The key of the proposed methodology is a novel entropy, named Multivariate Constraint Sample Entropy ( McSE ), to incorporate the multivariate constraint relations for better predictability. We conduct a systematic evaluation over eight datasets and compare existing methods with our proposed predictability and find that we get a higher predictability. We also find that the forecasting algorithms that capture the multivariate constraint relation information, such as GNN, can achieve higher accuracy, confirming the importance of multivariate constraint relations for predictability.
{"title":"Multivariate Time-Series Forecasting Model: Predictability Analysis and Empirical Study","authors":"Qinpei Zhao;Guangda Yang;Kai Zhao;Jiaming Yin;Weixiong Rao;Lei Chen","doi":"10.1109/TBDATA.2023.3288693","DOIUrl":"10.1109/TBDATA.2023.3288693","url":null,"abstract":"Multivariate time series forecasting has wide applications such as traffic flow prediction, supermarket commodity demand forecasting and etc., and a large number of forecasting models have been developed. Given these models, a natural question has been raised: what theoretical limits of forecasting accuracy can these models achieve? Recent works of urban human mobility prediction have made progress on the maximum predictability that any algorithm can achieve. However, existing approaches on maximum predictability on the multivariate time series fully ignore the interrelationship between multiple variables. In this article, we propose a methodology to measure the upper limit of predictability for multivariate time series with multivariate constraint relations. The key of the proposed methodology is a novel entropy, named Multivariate Constraint Sample Entropy (\u0000<italic>McSE</i>\u0000), to incorporate the multivariate constraint relations for better predictability. We conduct a systematic evaluation over eight datasets and compare existing methods with our proposed predictability and find that we get a higher predictability. We also find that the forecasting algorithms that capture the multivariate constraint relation information, such as GNN, can achieve higher accuracy, confirming the importance of multivariate constraint relations for predictability.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"9 6","pages":"1536-1548"},"PeriodicalIF":7.2,"publicationDate":"2023-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62972293","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}
Causal structure learning has been extensively studied and widely used in machine learning and various applications. To achieve an ideal performance, existing causal structure learning algorithms often need to centralize a large amount of data from multiple data sources. However, in the privacy-preserving setting, it is impossible to centralize data from all sources and put them together as a single dataset. To preserve data privacy, federated learning as a new learning paradigm has attached much attention in machine learning in recent years. In this paper, we study a privacy-aware causal structure learning problem in the federated setting and propose a novel federated PC (FedPC) algorithm with two new strategies for preserving data privacy without centralizing data. Specifically, we first propose a novel layer-wise aggregation strategy for a seamless adaptation of the PC algorithm into the federated learning paradigm for federated skeleton learning, then we design an effective strategy for learning consistent separation sets for federated edge orientation. The extensive experiments validate that FedPC is effective for causal structure learning in federated learning setting.
{"title":"Towards Privacy-Aware Causal Structure Learning in Federated Setting","authors":"Jianli Huang;Xianjie Guo;Kui Yu;Fuyuan Cao;Jiye Liang","doi":"10.1109/TBDATA.2023.3285477","DOIUrl":"10.1109/TBDATA.2023.3285477","url":null,"abstract":"Causal structure learning has been extensively studied and widely used in machine learning and various applications. To achieve an ideal performance, existing causal structure learning algorithms often need to centralize a large amount of data from multiple data sources. However, in the privacy-preserving setting, it is impossible to centralize data from all sources and put them together as a single dataset. To preserve data privacy, federated learning as a new learning paradigm has attached much attention in machine learning in recent years. In this paper, we study a privacy-aware causal structure learning problem in the federated setting and propose a novel federated PC (FedPC) algorithm with two new strategies for preserving data privacy without centralizing data. Specifically, we first propose a novel layer-wise aggregation strategy for a seamless adaptation of the PC algorithm into the federated learning paradigm for federated skeleton learning, then we design an effective strategy for learning consistent separation sets for federated edge orientation. The extensive experiments validate that FedPC is effective for causal structure learning in federated learning setting.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"9 6","pages":"1525-1535"},"PeriodicalIF":7.2,"publicationDate":"2023-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77771046","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}
Pub Date : 2023-06-08DOI: 10.1109/TBDATA.2023.3284270
Zhen Liu;Wenbo Zuo;Dongning Zhang;Xiaodong Feng
Anomalous links such as noisy links or adversarial edges widely exist in real-world networks, which may undermine the credibility of the network study, e.g., community detection in social networks. Therefore, anomalous links need to be removed from the polluted network by a detector. Due to the co-existence of normal links and anomalous links, how to identify anomalous links in a polluted network is a challenging issue. By designing a robust graph structure embedding framework, also called RGSE, the link-level feature representations that are generated from both global embedding view and local stable view can be used for anomalous link detection on contaminated graphs. Comparison experiments on a variety of datasets demonstrate that the new model and its variants achieve up to an average 5.2% improvement with respect to the accuracy of anomalous link detection against the traditional graph representation models. Further analyses also provide interpretable evidence to support the model's superiority.
{"title":"RGSE: Robust Graph Structure Embedding for Anomalous Link Detection","authors":"Zhen Liu;Wenbo Zuo;Dongning Zhang;Xiaodong Feng","doi":"10.1109/TBDATA.2023.3284270","DOIUrl":"10.1109/TBDATA.2023.3284270","url":null,"abstract":"Anomalous links such as noisy links or adversarial edges widely exist in real-world networks, which may undermine the credibility of the network study, e.g., community detection in social networks. Therefore, anomalous links need to be removed from the polluted network by a detector. Due to the co-existence of normal links and anomalous links, how to identify anomalous links in a polluted network is a challenging issue. By designing a robust graph structure embedding framework, also called RGSE, the link-level feature representations that are generated from both global embedding view and local stable view can be used for anomalous link detection on contaminated graphs. Comparison experiments on a variety of datasets demonstrate that the new model and its variants achieve up to an average 5.2% improvement with respect to the accuracy of anomalous link detection against the traditional graph representation models. Further analyses also provide interpretable evidence to support the model's superiority.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"9 5","pages":"1420-1429"},"PeriodicalIF":7.2,"publicationDate":"2023-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46406222","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}
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：