Graph Neighborhood Attentive Pooling
This addresses the need for more effective and efficient context-sensitive network representation learning for applications like link prediction and clustering, offering a novel approach that avoids reliance on external data or complex preprocessing.
The paper tackles the problem of learning context-sensitive node representations in graphs without requiring additional features or community detection, proposing the GAP algorithm which uses attentive pooling networks to attend to different parts of a node's neighborhood. The result shows that GAP outperforms 10 state-of-the-art baselines, achieving up to ~9% gain in link prediction and ~20% gain in node clustering tasks.
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.