Node Representation Learning in Graph via Node-to-Neighbourhood Mutual Information Maximization

03/23/2022
by   Wei Dong, et al.
0

The key towards learning informative node representations in graphs lies in how to gain contextual information from the neighbourhood. In this work, we present a simple-yet-effective self-supervised node representation learning strategy via directly maximizing the mutual information between the hidden representations of nodes and their neighbourhood, which can be theoretically justified by its link to graph smoothing. Following InfoNCE, our framework is optimized via a surrogate contrastive loss, where the positive selection underpins the quality and efficiency of representation learning. To this end, we propose a topology-aware positive sampling strategy, which samples positives from the neighbourhood by considering the structural dependencies between nodes and thus enables positive selection upfront. In the extreme case when only one positive is sampled, we fully avoid expensive neighbourhood aggregation. Our methods achieve promising performance on various node classification datasets. It is also worth mentioning by applying our loss function to MLP based node encoders, our methods can be orders of faster than existing solutions. Our codes and supplementary materials are available at https://github.com/dongwei156/n2n.

READ FULL TEXT

page 6

page 12

research
02/09/2023

Self-Supervised Node Representation Learning via Node-to-Neighbourhood Alignment

Self-supervised node representation learning aims to learn node represen...
research
10/17/2022

Unifying Graph Contrastive Learning with Flexible Contextual Scopes

Graph contrastive learning (GCL) has recently emerged as an effective le...
research
07/02/2020

Maximizing Cohesion and Separation in Graph Representation Learning: A Distance-aware Negative Sampling Approach

The objective of unsupervised graph representation learning (GRL) is to ...
research
05/31/2022

COIN: Co-Cluster Infomax for Bipartite Graphs

Bipartite graphs are powerful data structures to model interactions betw...
research
10/07/2022

Unsupervised Semantic Representation Learning of Scientific Literature Based on Graph Attention Mechanism and Maximum Mutual Information

Since most scientific literature data are unlabeled, this makes unsuperv...
research
12/08/2022

Alleviating neighbor bias: augmenting graph self-supervise learning with structural equivalent positive samples

In recent years, using a self-supervised learning framework to learn the...
research
09/14/2022

Jointly Contrastive Representation Learning on Road Network and Trajectory

Road network and trajectory representation learning are essential for tr...

Please sign up or login with your details

Forgot password? Click here to reset