GraLSP: Graph Neural Networks with Local Structural Patterns
This addresses a limitation in GNNs for graph representation learning, with incremental improvements in performance for domain-specific applications.
The paper tackles the problem of graph neural networks (GNNs) failing to identify important local structural patterns in graphs, proposing GraLSP, a framework that incorporates these patterns via random anonymous walks into neighborhood aggregation, resulting in outperforming competitive models in various prediction tasks across multiple datasets.
It is not until recently that graph neural networks (GNNs) are adopted to perform graph representation learning, among which, those based on the aggregation of features within the neighborhood of a node achieved great success. However, despite such achievements, GNNs illustrate defects in identifying some common structural patterns which, unfortunately, play significant roles in various network phenomena. In this paper, we propose GraLSP, a GNN framework which explicitly incorporates local structural patterns into the neighborhood aggregation through random anonymous walks. Specifically, we capture local graph structures via random anonymous walks, powerful and flexible tools that represent structural patterns. The walks are then fed into the feature aggregation, where we design various mechanisms to address the impact of structural features, including adaptive receptive radius, attention and amplification. In addition, we design objectives that capture similarities between structures and are optimized jointly with node proximity objectives. With the adequate leverage of structural patterns, our model is able to outperform competitive counterparts in various prediction tasks in multiple datasets.