Attending Over Triads for Learning Signed Network Embedding

Network embedding, which aims at learning distributed representations for nodes in networks, is a critical task with wide downstream applications. Most existing studies focus on networks with a single type of edges, whereas in many cases, the edges of networks can be derived from two opposite relationships, yielding signed networks. This paper studies network embedding for the signed network, and a novel approach called \textbf{TEA} is proposed. Similar to existing methods, \textbf{TEA} learns node representations by predicting the sign of each edge in the network. However, many existing methods only consider the local structural information (i.e., the representations of nodes in an edge) for prediction, which can be biased especially for sparse networks. By contrast, \textbf{TEA} seeks to leverage the high-order structures by drawing inspirations from the Social Balance Theory. More specifically, for an edge linking two nodes, \textbf{TEA} predicts the edge sign by treating the paths connecting the two nodes as features. Meanwhile, an attention mechanism is proposed, which assigns different weights to the paths and further weighted combines them for more precise prediction. We conduct experiments on several real-world signed networks, and the results prove the effectiveness of \textbf{TEA} over many strong baseline approaches.