Time-Aware Neighbor Sampling for Temporal Graph Networks

12/18/2021
by   Yiwei Wang, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/29/2017

Stochastic Training of Graph Convolutional Networks

Graph convolutional networks (GCNs) are powerful deep neural networks fo...
research
04/16/2021

Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networks

Graph Neural Networks (GNNs) have been widely used for the representatio...
research
10/26/2021

TME-BNA: Temporal Motif-Preserving Network Embedding with Bicomponent Neighbor Aggregation

Evolving temporal networks serve as the abstractions of many real-life d...
research
10/27/2019

Neighbor connectivity of k-ary n-cubes

The neighbor connectivity of a graph G is the least number of vertices s...
research
01/19/2021

Communication-Efficient Sampling for Distributed Training of Graph Convolutional Networks

Training Graph Convolutional Networks (GCNs) is expensive as it needs to...
research
04/30/2020

A more secure IPv6 neighborhood process

The process of neighborhood establishment in an IPv6 network is made out...
research
10/19/2022

Sampling via Rejection-Free Partial Neighbor Search

The Metropolis algorithm involves producing a Markov chain to converge t...

Please sign up or login with your details

Forgot password? Click here to reset