Learning from the Dark: Boosting Graph Convolutional Neural Networks with Diverse Negative Samples

by   Wei Duan, et al.

Graph Convolutional Neural Networks (GCNs) has been generally accepted to be an effective tool for node representations learning. An interesting way to understand GCNs is to think of them as a message passing mechanism where each node updates its representation by accepting information from its neighbours (also known as positive samples). However, beyond these neighbouring nodes, graphs have a large, dark, all-but forgotten world in which we find the non-neighbouring nodes (negative samples). In this paper, we show that this great dark world holds a substantial amount of information that might be useful for representation learning. Most specifically, it can provide negative information about the node representations. Our overall idea is to select appropriate negative samples for each node and incorporate the negative information contained in these samples into the representation updates. Moreover, we show that the process of selecting the negative samples is not trivial. Our theme therefore begins by describing the criteria for a good negative sample, followed by a determinantal point process algorithm for efficiently obtaining such samples. A GCN, boosted by diverse negative samples, then jointly considers the positive and negative information when passing messages. Experimental evaluations show that this idea not only improves the overall performance of standard representation learning but also significantly alleviates over-smoothing problems.


Graph Convolutional Neural Networks with Diverse Negative Samples via Decomposed Determinant Point Processes

Graph convolutional networks (GCNs) have achieved great success in graph...

Schema-Aware Deep Graph Convolutional Networks for Heterogeneous Graphs

Graph convolutional network (GCN) based approaches have achieved signifi...

Label Aware Graph Convolutional Network -- Not All Edges Deserve Your Attention

Graph classification is practically important in many domains. To solve ...

Relation-aware Graph Attention Model With Adaptive Self-adversarial Training

This paper describes an end-to-end solution for the relationship predict...

SCE: Scalable Network Embedding from Sparsest Cut

Large-scale network embedding is to learn a latent representation for ea...

A Non-Negative Factorization approach to node pooling in Graph Convolutional Neural Networks

The paper discusses a pooling mechanism to induce subsampling in graph s...

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

The objective of unsupervised graph representation learning (GRL) is to ...

Please sign up or login with your details

Forgot password? Click here to reset