Knowledge graph completion (KGC) has become a focus of attention across deep learning community owing to its excellent contribution to numerous downstream tasks. Although recently have witnessed a surge of work on KGC, they are still insufficient to accurately capture complex relations, since they adopt the single and static representations. In this work, we propose a novel Disentangled Knowledge Graph Attention Network (DisenKGAT) for KGC, which leverages both micro-disentanglement and macro-disentanglement to exploit representations behind Knowledge graphs (KGs). To achieve micro-disentanglement, we put forward a novel relation-aware aggregation to learn diverse component representation. For macro-disentanglement, we leverage mutual information as a regularization to enhance independence. With the assistance of disentanglement, our model is able to generate adaptive representations in terms of the given scenario. Besides, our work has strong robustness and flexibility to adapt to various score functions. Extensive experiments on public benchmark datasets have been conducted to validate the superiority of DisenKGAT over existing methods in terms of both accuracy and explainability.
CLIP-PAE: Projection-Augmentation Embedding to Extract Relevant Features for a Disentangled, Interpretable, and Controllable Text-Guided Face Manipulation
Adaptive Disentangled Representation Learning for Incomplete Multi-View Multi-Label Classification
College of Science, National University of Defense Technology（国防科技大学科学学院）；College of Artificial Intelligence, Harbin Institute of Technology（哈尔滨工业大学人工智能学院）；School of Software and Microelectronics, Peking University（北京大学软件与微电子学院）
DisPositioNet: Disentangled Pose and Identity in Semantic Image Manipulation
Technical University of Munich（慕尼黑工业大学）；Munich Center for Machine Learning（慕尼黑机器学习中心）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Google（谷歌）；Johns Hopkins University（约翰斯·霍普金斯大学）
Causal Disentanglement for Regulating Social Influence Bias in Social Recommendation
School of Electrical and Data Engineering, University of Technology Sydney（悉尼科技大学电气与数据工程学院）；School of Artificial Intelligence, Chongqing University of Arts and Sciences（重庆文理学院人工智能学院）
GJDNet: Robust Graph Neural Networks via Joint Disentangled Learning Against Adversarial Attacks
School of Computer Science and Technology, Chongqing University of Posts and Telecommunications（重庆邮电大学计算机科学与技术学院）；School of Cyber Security and Information Law, Chongqing University of Posts and Telecommunications（重庆邮电大学网络安全与信息法学院）；Computational Communication Research Center, Beijing Normal University（北京师范大学计算通信研究中心）；School of Journalism and Communication, Beijing Normal University（北京师范大学新闻传播学院）；School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）
Department of Computer Science and Engineering, University of Texas at Arlington, United States（德克萨斯理工大学计算机科学与工程系，美国）；School of Computing, University of Georgia, United States（佐治亚大学计算机学院，美国）
Proactive Disentangled Modeling of Trigger-Object Pairings for Backdoor Defense
Department of Intelligent Systems and Robotics, University of West Florida（智能系统与机器人系，西佛罗里达大学）；Florida Institute For Human and Machine Cognition (IHMC)（佛罗里达人类与机器认知研究所）；Center for Cybersecurity, University of West Florida（网络安全中心，西佛罗里达大学）
