GTEA: Inductive Representation Learning on Temporal Interaction Graphs via Temporal Edge Aggregation

TL;DR

GTEA introduces a novel framework for inductive learning on temporal interaction graphs by modeling continuous-time dynamics and integrating node and edge attributes, enhancing representation learning.

Contribution

It presents a new approach combining sequence modeling, time encoding, and self-attention for improved temporal and structural graph representations.

Findings

GTEA outperforms existing models on five real-world datasets.

The framework effectively captures complex temporal interaction patterns.

Self-attention improves neighbor relevance weighting.

Abstract

In this paper, we propose the Graph Temporal Edge Aggregation (GTEA) framework for inductive learning on Temporal Interaction Graphs (TIGs). Different from previous works, GTEA models the temporal dynamics of interaction sequences in the continuous-time space and simultaneously takes advantage of both rich node and edge/ interaction attributes in the graph. Concretely, we integrate a sequence model with a time encoder to learn pairwise interactional dynamics between two adjacent nodes.This helps capture complex temporal interactional patterns of a node pair along the history, which generates edge embeddings that can be fed into a GNN backbone. By aggregating features of neighboring nodes and the corresponding edge embeddings, GTEA jointly learns both topological and temporal dependencies of a TIG. In addition, a sparsity-inducing self-attention scheme is incorporated for neighbor aggregation, which highlights more important neighbors and suppresses trivial noises for GTEA. By jointly optimizing the sequence model and the GNN backbone, GTEA learns more comprehensive node representations capturing both temporal and graph structural characteristics. Extensive experiments on five large-scale real-world datasets demonstrate the superiority of GTEA over other inductive models.