Time-Aware Neighbor Sampling for Temporal Graph Networks
This work addresses the challenge of efficiently handling temporal information in graph networks for applications like social network analysis or recommendation systems, though it is incremental as it builds on existing temporal graph network frameworks.
The paper tackles the problem of predicting time-varying properties in temporal graphs by proposing TNS, a time-aware neighbor sampling method that adaptively selects receptive neighborhoods for each node at any time, resulting in significant gains on edge prediction and node classification across multiple standard datasets.
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.