Social Relation Reasoning Based on Triangular Constraints

Social networks are essentially in a graph structure where persons act as nodes and the edges connecting nodes denote social relations. The prediction of social relations, therefore, relies on the context in graphs to model the higher-order constraints among relations, which has not been exploited sufficiently by previous works, however. In this paper, we formulate the paradigm of the higher-order constraints in social relations into triangular relational closed-loop structures, i.e., triangular constraints, and further introduce the triangular reasoning graph attention network (TRGAT). Our TRGAT employs the attention mechanism to aggregate features with triangular constraints in the graph, thereby exploiting the higher-order context to reason social relations iteratively. Besides, to acquire better feature representations of persons, we introduce node contrastive learning into relation reasoning. Experimental results show that our method outperforms existing approaches significantly, with higher accuracy and better consistency in generating social relation graphs.

Authors

• Yunfei Guo National Laboratory of Pattern Recognition (NLPR), Institute of Automation of Chinese Academy of Sciences, Beijing 100190, China School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China
• Fei Yin National Laboratory of Pattern Recognition (NLPR), Institute of Automation of Chinese Academy of Sciences, Beijing 100190, China School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China
• Wei Feng Xi'an Jiaotong University
• Xudong Yan T Lab, Tencent Map, Tencent Technology (Beijing) Co., Ltd., Beijing 100193, China
• Tao Xue T Lab, Tencent Map, Tencent Technology (Beijing) Co., Ltd., Beijing 100193, China
• Shuqi Mei T Lab, Tencent, Beijing, China
• Cheng-Lin Liu School of Artificial Intelligence, University of Chinese Academy of Sciences, State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institution of Automation, Chinese Academy of Sciences

Keywords

• CV: Scene Analysis & Understanding
• CV: Visual Reasoning & Symbolic Representations