TAMI: Taming Heterogeneity in Temporal Interactions for Temporal Graph Link Prediction

TL;DR

TAMI introduces a framework that effectively handles heterogeneity in temporal interactions, improving link prediction accuracy by better encoding temporal info and preserving historical interactions in dynamic graphs.

Contribution

The paper proposes TAMI, a novel framework with LTE and LHA components, to address heterogeneity in temporal graph link prediction, enhancing existing models' effectiveness.

Findings

Consistently improves link prediction across 16 datasets.

Enhances performance of state-of-the-art temporal graph neural networks.

Effective in both transductive and inductive settings.

Abstract

Temporal graph link prediction aims to predict future interactions between nodes in a graph based on their historical interactions, which are encoded in node embeddings. We observe that heterogeneity naturally appears in temporal interactions, e.g., a few node pairs can make most interaction events, and interaction events happen at varying intervals. This leads to the problems of ineffective temporal information encoding and forgetting of past interactions for a pair of nodes that interact intermittently for their link prediction. Existing methods, however, do not consider such heterogeneity in their learning process, and thus their learned temporal node embeddings are less effective, especially when predicting the links for infrequently interacting node pairs. To cope with the heterogeneity, we propose a novel framework called TAMI, which contains two effective components, namely log time encoding function (LTE) and link history aggregation (LHA). LTE better encodes the temporal information through transforming interaction intervals into more balanced ones, and LHA prevents the historical interactions for each target node pair from being forgotten. State-of-the-art temporal graph neural networks can be seamlessly and readily integrated into TAMI to improve their effectiveness. Experiment results on 13 classic datasets and three newest temporal graph benchmark (TGB) datasets show that TAMI consistently improves the link prediction performance of the underlying models in both transductive and inductive settings. Our code is available at https://github.com/Alleinx/TAMI_temporal_graph.