Time-Aware Neighbor Sampling for Temporal Graph Networks

TL;DR

This paper introduces TNS, a novel time-aware neighbor sampling method for temporal graphs that adaptively learns to select relevant neighbors, improving prediction accuracy without added computational cost.

Contribution

The paper proposes TNS, an end-to-end trainable neighbor sampling technique that leverages temporal information to enhance temporal graph network performance.

Findings

TNS significantly improves edge prediction accuracy.

TNS enhances node classification results.

The method operates efficiently without increasing complexity.

Abstract

We present a new neighbor sampling method on temporal graphs. In a temporal graph, predicting different nodes' time-varying properties can require the receptive neighborhood of various temporal scales. In this work, we propose the TNS (Time-aware Neighbor Sampling) method: TNS learns from temporal information to provide an adaptive receptive neighborhood for every node at any time. Learning how to sample neighbors is non-trivial, since the neighbor indices in time order are discrete and not differentiable. To address this challenge, we transform neighbor indices from discrete values to continuous ones by interpolating the neighbors' messages. TNS can be flexibly incorporated into popular temporal graph networks to improve their effectiveness without increasing their time complexity. TNS can be trained in an end-to-end manner. It needs no extra supervision and is automatically and implicitly guided to sample the neighbors that are most beneficial for prediction. Empirical results on multiple standard datasets show that TNS yields significant gains on edge prediction and node classification.