Graph Neighborhood Attentive Pooling

TL;DR

This paper introduces GAP, a novel context-sensitive graph representation learning method that uses attentive pooling to focus on different neighborhood parts, outperforming state-of-the-art baselines in link prediction and clustering.

Contribution

GAP is a new algorithm that learns to attend to different parts of a node's neighborhood without extra features or community detection, improving graph learning tasks.

Findings

GAP outperforms 10 SOTA methods in link prediction by up to 9%.

GAP improves clustering accuracy by up to 20%.

GAP demonstrates consistent superiority across three real-world datasets.

Abstract

Network representation learning (NRL) is a powerful technique for learning low-dimensional vector representation of high-dimensional and sparse graphs. Most studies explore the structure and metadata associated with the graph using random walks and employ an unsupervised or semi-supervised learning schemes. Learning in these methods is context-free, because only a single representation per node is learned. Recently studies have argued on the sufficiency of a single representation and proposed a context-sensitive approach that proved to be highly effective in applications such as link prediction and ranking. However, most of these methods rely on additional textual features that require RNNs or CNNs to capture high-level features or rely on a community detection algorithm to identify multiple contexts of a node. In this study, without requiring additional features nor a community detection algorithm, we propose a novel context-sensitive algorithm called GAP that learns to attend on different parts of a node's neighborhood using attentive pooling networks. We show the efficacy of GAP using three real-world datasets on link prediction and node clustering tasks and compare it against 10 popular and state-of-the-art (SOTA) baselines. GAP consistently outperforms them and achieves up to ~9% and ~20% gain over the best performing methods on link prediction and clustering tasks, respectively.