Abstract:
Federated knowledge graph reasoning (FedKGR) aims to perform reasoning over different clients while protecting data privacy, drawing increasing attention to its high prac...Show MoreMetadata
Abstract:
Federated knowledge graph reasoning (FedKGR) aims to perform reasoning over different clients while protecting data privacy, drawing increasing attention to its high practical value. Previous works primarily focus on data heterogeneity, ignoring challenges from limited data scale and primitive negative sample strategies, i.e., random entity replacement, which yield low-quality negatives and zero loss issues. Meanwhile, generative adversarial networks (GANs) are widely used in different fields to generate high-quality negative samples, but no work has been developed for FedKGR. To this end, we propose a plug-and-play Entity-aware Adversarial Negative sampling strategy for FedKGR, termed FedEAN. Specifically, we are the first to adopt GANs to generate high-quality negative samples in different clients. It takes the target triplet in each batch as input and outputs high-quality negative samples, which guaranteed by the joint training of the generator and discriminator. Moreover, we design an entity-aware adaptive negative sampling mechanism based on the similarity of entity representations before and after server aggregation, which can persevere the entity global consistency across clients during training. Extensive experiments demonstrate that FedEAN excels with various FedKGR backbones, demonstrating its ability to construct high-quality negative samples and address the zero-loss issue.
Published in: IEEE Transactions on Knowledge and Data Engineering ( Volume: 36, Issue: 12, December 2024)
Funding Agency:
School of Computer, National University of Defense Technology, Changsha, China
Lingyuan Meng is working toward the master's degreewith the National University of Defense Technology (NUDT) with excellent grades and competition awards. His current research interests include knowledge graph reasoning, graph neural networks, and contrastive learning.
Lingyuan Meng is working toward the master's degreewith the National University of Defense Technology (NUDT) with excellent grades and competition awards. His current research interests include knowledge graph reasoning, graph neural networks, and contrastive learning.View more
School of Computer, National University of Defense Technology, Changsha, China
Ke Liang received the BSc degree from Beihang University (BUAA) and the MSc degree from the Pennsylvania State University (PSU). He is currently working toward the PhD degree with the National University of Defense Technology (NUDT). His current research interests include knowledge graph reasoning, graph learning, and medical image processing.
Ke Liang received the BSc degree from Beihang University (BUAA) and the MSc degree from the Pennsylvania State University (PSU). He is currently working toward the PhD degree with the National University of Defense Technology (NUDT). His current research interests include knowledge graph reasoning, graph learning, and medical image processing.View more
School of Computer, National University of Defense Technology, Changsha, China
Hao Yu (Student Member, IEEE) received the BEng degree in computer science from Inner Mongolia University, Hohhot, China, in 2019, and the MASc degree in cyberspace science and technology from the Beijing Institute of Technology, Beijing, China, in 2022. He is currently working toward the PhD degree with the National University of Defense Technology (NUDT). His current research focuses on AI security and federated learnin...Show More
Hao Yu (Student Member, IEEE) received the BEng degree in computer science from Inner Mongolia University, Hohhot, China, in 2019, and the MASc degree in cyberspace science and technology from the Beijing Institute of Technology, Beijing, China, in 2022. He is currently working toward the PhD degree with the National University of Defense Technology (NUDT). His current research focuses on AI security and federated learnin...View more
School of Computer, National University of Defense Technology, Changsha, China
Yue Liu received the graduate degree from Northeastern University, Qinhuangdao, Hebei, China. He is currently working toward the master's degree with the College of Computers, National University of Defense Technology, China. He was recommended for admission to the National University of Defense Technology (NUDT) with excellent grades and technological innovation capability. His current research interests include graph ne...Show More
Yue Liu received the graduate degree from Northeastern University, Qinhuangdao, Hebei, China. He is currently working toward the master's degree with the College of Computers, National University of Defense Technology, China. He was recommended for admission to the National University of Defense Technology (NUDT) with excellent grades and technological innovation capability. His current research interests include graph ne...View more
College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China
Sihang Zhou (Member, IEEE) received the PhD degree from the School of Computer, National University of Defense Technology (NUDT), China. He is now lecturer with the College of Intelligence Science and Technology, NUDT. His current research interests include machine learning and medical image analysis. He has published 40+ peer-reviewed papers, including IEEE Transactions on Image Processing, IEEE Transactions on Neural Ne...Show More
Sihang Zhou (Member, IEEE) received the PhD degree from the School of Computer, National University of Defense Technology (NUDT), China. He is now lecturer with the College of Intelligence Science and Technology, NUDT. His current research interests include machine learning and medical image analysis. He has published 40+ peer-reviewed papers, including IEEE Transactions on Image Processing, IEEE Transactions on Neural Ne...View more
School of Computer, National University of Defense Technology, Changsha, China
Meng Liu is working toward the PhD degree with the National University of Defense Technology, China. His research interests include temporal graph learning and deep clustering. He has published several papers in famous conferences and journals, including SIGIR, CIKM, DASFAA, etc.
Meng Liu is working toward the PhD degree with the National University of Defense Technology, China. His research interests include temporal graph learning and deep clustering. He has published several papers in famous conferences and journals, including SIGIR, CIKM, DASFAA, etc.View more
School of Computer, National University of Defense Technology, Changsha, China
Xinwang Liu (Senior Member, IEEE) received the PhD degree from the National University of Defense Technology (NUDT), China. He is now a professor with the School of Computer, NUDT. His current research interests include kernel learning and unsupervised feature learning. He has published 60+ peer-reviewed papers, including those in highly regarded journals and conferences such as IEEE Transactions on Pattern Analysis and M...Show More
Xinwang Liu (Senior Member, IEEE) received the PhD degree from the National University of Defense Technology (NUDT), China. He is now a professor with the School of Computer, NUDT. His current research interests include kernel learning and unsupervised feature learning. He has published 60+ peer-reviewed papers, including those in highly regarded journals and conferences such as IEEE Transactions on Pattern Analysis and M...View more
Contents School of Computer, National University of Defense Technology, Changsha, China
Lingyuan Meng is working toward the master's degreewith the National University of Defense Technology (NUDT) with excellent grades and competition awards. His current research interests include knowledge graph reasoning, graph neural networks, and contrastive learning.
Lingyuan Meng is working toward the master's degreewith the National University of Defense Technology (NUDT) with excellent grades and competition awards. His current research interests include knowledge graph reasoning, graph neural networks, and contrastive learning.View more
School of Computer, National University of Defense Technology, Changsha, China
Ke Liang received the BSc degree from Beihang University (BUAA) and the MSc degree from the Pennsylvania State University (PSU). He is currently working toward the PhD degree with the National University of Defense Technology (NUDT). His current research interests include knowledge graph reasoning, graph learning, and medical image processing.
Ke Liang received the BSc degree from Beihang University (BUAA) and the MSc degree from the Pennsylvania State University (PSU). He is currently working toward the PhD degree with the National University of Defense Technology (NUDT). His current research interests include knowledge graph reasoning, graph learning, and medical image processing.View more
School of Computer, National University of Defense Technology, Changsha, China
Hao Yu (Student Member, IEEE) received the BEng degree in computer science from Inner Mongolia University, Hohhot, China, in 2019, and the MASc degree in cyberspace science and technology from the Beijing Institute of Technology, Beijing, China, in 2022. He is currently working toward the PhD degree with the National University of Defense Technology (NUDT). His current research focuses on AI security and federated learning. He has authored several papers in top-level journals and conferences, such as IEEE Transactions on Information Forensics and Security, IEEE Transactions on Dependable and Secure Computing, and ACM MM, etc.
Hao Yu (Student Member, IEEE) received the BEng degree in computer science from Inner Mongolia University, Hohhot, China, in 2019, and the MASc degree in cyberspace science and technology from the Beijing Institute of Technology, Beijing, China, in 2022. He is currently working toward the PhD degree with the National University of Defense Technology (NUDT). His current research focuses on AI security and federated learning. He has authored several papers in top-level journals and conferences, such as IEEE Transactions on Information Forensics and Security, IEEE Transactions on Dependable and Secure Computing, and ACM MM, etc.View more
School of Computer, National University of Defense Technology, Changsha, China
Yue Liu received the graduate degree from Northeastern University, Qinhuangdao, Hebei, China. He is currently working toward the master's degree with the College of Computers, National University of Defense Technology, China. He was recommended for admission to the National University of Defense Technology (NUDT) with excellent grades and technological innovation capability. His current research interests include graph neural networks, deep clustering, and self-supervised learning.
Yue Liu received the graduate degree from Northeastern University, Qinhuangdao, Hebei, China. He is currently working toward the master's degree with the College of Computers, National University of Defense Technology, China. He was recommended for admission to the National University of Defense Technology (NUDT) with excellent grades and technological innovation capability. His current research interests include graph neural networks, deep clustering, and self-supervised learning.View more
College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China
Sihang Zhou (Member, IEEE) received the PhD degree from the School of Computer, National University of Defense Technology (NUDT), China. He is now lecturer with the College of Intelligence Science and Technology, NUDT. His current research interests include machine learning and medical image analysis. He has published 40+ peer-reviewed papers, including IEEE Transactions on Image Processing, IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Medical Imaging, Information Fusion, Medical Image Analysis, AAAI, MICCAI, etc.
Sihang Zhou (Member, IEEE) received the PhD degree from the School of Computer, National University of Defense Technology (NUDT), China. He is now lecturer with the College of Intelligence Science and Technology, NUDT. His current research interests include machine learning and medical image analysis. He has published 40+ peer-reviewed papers, including IEEE Transactions on Image Processing, IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Medical Imaging, Information Fusion, Medical Image Analysis, AAAI, MICCAI, etc.View more
School of Computer, National University of Defense Technology, Changsha, China
Meng Liu is working toward the PhD degree with the National University of Defense Technology, China. His research interests include temporal graph learning and deep clustering. He has published several papers in famous conferences and journals, including SIGIR, CIKM, DASFAA, etc.
Meng Liu is working toward the PhD degree with the National University of Defense Technology, China. His research interests include temporal graph learning and deep clustering. He has published several papers in famous conferences and journals, including SIGIR, CIKM, DASFAA, etc.View more
School of Computer, National University of Defense Technology, Changsha, China
Xinwang Liu (Senior Member, IEEE) received the PhD degree from the National University of Defense Technology (NUDT), China. He is now a professor with the School of Computer, NUDT. His current research interests include kernel learning and unsupervised feature learning. He has published 60+ peer-reviewed papers, including those in highly regarded journals and conferences such as IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Transactions on Knowledge and Data Engineering, IEEE Transactions on Image Processing, IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Multimedia, IEEE Transactions on Information Forensics and Security, ICML, NeurIPS, ICCV, CVPR, AAAI, IJCAI, etc. He serves as the associated editor of IEEE Transactions on Neural Networks and Learning Systems and Information Fusion Journal.
Xinwang Liu (Senior Member, IEEE) received the PhD degree from the National University of Defense Technology (NUDT), China. He is now a professor with the School of Computer, NUDT. His current research interests include kernel learning and unsupervised feature learning. He has published 60+ peer-reviewed papers, including those in highly regarded journals and conferences such as IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Transactions on Knowledge and Data Engineering, IEEE Transactions on Image Processing, IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Multimedia, IEEE Transactions on Information Forensics and Security, ICML, NeurIPS, ICCV, CVPR, AAAI, IJCAI, etc. He serves as the associated editor of IEEE Transactions on Neural Networks and Learning Systems and Information Fusion Journal.View more
