SPAGAN: Shortest Path Graph Attention Network
This work provides an incremental improvement in graph representation learning for researchers and practitioners working with graph-structured data, particularly in classification tasks.
This paper introduces SPAGAN, a novel Graph Convolutional Network (GCN) model that uses path-based attention to explicitly consider shortest paths between nodes and their higher-order neighbors. SPAGAN achieves superior performance compared to state-of-the-art methods on downstream classification tasks across several standard datasets.
Graph convolutional networks (GCN) have recently demonstrated their potential in analyzing non-grid structure data that can be represented as graphs. The core idea is to encode the local topology of a graph, via convolutions, into the feature of a center node. In this paper, we propose a novel GCN model, which we term as Shortest Path Graph Attention Network (SPAGAN). Unlike conventional GCN models that carry out node-based attentions within each layer, the proposed SPAGAN conducts path-based attention that explicitly accounts for the influence of a sequence of nodes yielding the minimum cost, or shortest path, between the center node and its higher-order neighbors. SPAGAN therefore allows for a more informative and intact exploration of the graph structure and further {a} more effective aggregation of information from distant neighbors into the center node, as compared to node-based GCN methods. We test SPAGAN on the downstream classification task on several standard datasets, and achieve performances superior to the state of the art. Code is publicly available at https://github.com/ihollywhy/SPAGAN.