Multi-Relation Aware Temporal Interaction Network Embedding

TL;DR

This paper introduces MRATE, a novel embedding method for temporal interaction networks that incorporates multiple relation types and sequence similarities, improving the understanding of complex dynamic interactions.

Contribution

The paper proposes a multi-relation aware embedding approach that considers various interaction relations and sequence similarities, enhancing temporal network analysis.

Findings

MRATE outperforms existing methods on three datasets.

Incorporating multiple relation types improves embedding quality.

Hierarchical attention mechanisms effectively aggregate interaction impacts.

Abstract

Temporal interaction networks are formed in many fields, e.g., e-commerce, online education, and social network service. Temporal interaction network embedding can effectively mine the information in temporal interaction networks, which is of great significance to the above fields. Usually, the occurrence of an interaction affects not only the nodes directly involved in the interaction (interacting nodes), but also the neighbor nodes of interacting nodes. However, existing temporal interaction network embedding methods only use historical interaction relations to mine neighbor nodes, ignoring other relation types. In this paper, we propose a multi-relation aware temporal interaction network embedding method (MRATE). Based on historical interactions, MRATE mines historical interaction relations, common interaction relations, and interaction sequence similarity relations to obtain the neighbor based embeddings of interacting nodes. The hierarchical multi-relation aware aggregation method in MRATE first employs graph attention networks (GATs) to aggregate the interaction impacts propagated through a same relation type and then combines the aggregated interaction impacts from multiple relation types through the self-attention mechanism. Experiments are conducted on three public temporal interaction network datasets, and the experimental results show the effectiveness of MRATE.