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 TR-GAT 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.

2020). Most previous methods (Li et al. 2017;Wang et al. 2018;Goel, Ma, and Tan 2019) adopted the pairwise prediction, where the features of two persons are extracted, fused, and classified to predict between-person relations. These methods handled multiple pairwise relations in the same image independently, ignoring the higher-order constraints. Recently, Li et al. (Li et al. 2020) tried to address this problem with graph neural networks, which constructed a social