Attention mechanism in graph neural networks is designed to assign larger weights to important neighbor nodes for better representation. However, what graph attention learns is not understood well, particularly when graphs are noisy. In this paper, we propose a self-supervised graph attention network (SuperGAT), an improved graph attention model for noisy graphs. Specifically, we exploit two attention forms compatible with a self-supervised task to predict edges, whose presence and absence contain the inherent information about the importance of the relationships between nodes. By encoding edges, SuperGAT learns more expressive attention in distinguishing mislinked neighbors. We find two graph characteristics influence the effectiveness of attention forms and self-supervision: homophily and average degree. Thus, our recipe provides guidance on which attention design to use when those two graph characteristics are known. Our experiment on 17 real-world datasets demonstrates that our recipe generalizes across 15 datasets of them, and our models designed by recipe show improved performance over baselines.
Training Verification-Friendly Neural Networks via Neuron Behavior Consistency
Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；University of Chinese Academy of Sciences（中国科学院大学）；RealAI（瑞莱智慧）；Nanjing Institute of Software Technology（南京软件技术研究院）；Singapore Management University（新加坡管理大学）；Southwest University（西南大学）；The University of Liverpool（利物浦大学）
FaIRCoP: Facial Image Retrieval using Contrastive Personalization
Indraprastha Institute of Information Technology, Delhi（德里英德拉普拉斯塔信息技术学院）；Indian Institute of Technology, Roorkee（鲁尔基印度理工学院）；International Institute of Information Technology, Hyderabad（海得拉巴国际信息技术学院）
Collaborate to Adapt: Source-Free Graph Domain Adaptation via Bi-directional Adaptation
National University of Singapore（新加坡国立大学）；Zhejiang University（浙江大学）；Alibaba Group（阿里巴巴集团）；Zhejiang Lab（之江实验室）；Hangzhou Yugu Technology Co., Ltd.（杭州玉谷科技有限公司）
PEARL: Prototype-Enhanced Alignment for Label-Efficient Representation Learning with Deployment-Driven Insights from Digital Governance Communication Systems
Department of Politics and Public Administration（政治与公共行政系）；The University of Hong Kong（香港大学）；Department of Applied Social Sciences（应用社会科学系）；The Hong Kong Polytechnic University（香港理工大学）；School of Physical Science and Technology（物理科学与技术学院）
Learning Propagation Geometry from Message-Passing Feedback
The Chinese University of Hong Kong（香港中文大学）；The Education University of Hong Kong（香港教育大学）；National University of Defense Technology（国防科技大学）；Hebei University of Technology（河北工业大学）；City University of Hong Kong（香港城市大学）；Huazhong University of Science and Technology（华中科技大学）
CAGNN: Cluster-Aware Graph Neural Networks for Unsupervised Graph Representation Learning
Center for Research on Intelligent Perception and Computing, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所智能感知与计算研究中心）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；School of Computer Science, Beijing University of Posts and Telecommunications（北京邮电大学计算机学院）；Alibaba Group（阿里巴巴集团）
$\texttt{SynC}$: Synergistic Boosting of Structure and Representation for Deep Graph Clustering
School of Computer Science and Technology/the School of Artificial Intelligence, China University of Mining and Technology（计算机科学与技术学院/人工智能学院，中国矿业大学）；Mine Digitization Engineering Research Center of Ministry of Education（教育部矿山数字化工程研究中心）；College of Intelligence and Computing, Tianjin University（智能与计算学院，天津大学）；Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China), Hefei University of Technology（大数据知识工程重点实验室（教育部），合肥工业大学）
Without Paired Labeled Data: End-to-End Self-Supervised Learning for Drone-view Geo-Localization
State Key Laboratory for Strength and Vibration of Mechanical Structures（强度与振动机械结构国家重点实验室）；Shaanxi Key Laboratory of Environment and Control for Flight Vehicle（陕西省飞行器环境与控制重点实验室）；School of Aerospace Engineering（航空航天工程学院）；Xi’an Jiaotong University（西安交通大学）；Institute of Automation（自动化研究所）；Chinese Academy of Sciences（中国科学院）；School of Artificial Intelligence（人工智能学院）；University of Chinese Academy of Sciences（中国科学院大学）；Peng Cheng Laboratory（鹏城实验室）
