SGAT: Simplicial Graph Attention Network
This work addresses the challenge of modeling complex semantics in heterogeneous graphs for applications like node classification, representing an incremental improvement over existing metapath-based methods.
The paper tackles the problem of learning from heterogeneous graphs by proposing SGAT, a simplicial complex approach to capture high-order interactions among nodes, and demonstrates that it outperforms other state-of-the-art methods in node classification tasks.
Heterogeneous graphs have multiple node and edge types and are semantically richer than homogeneous graphs. To learn such complex semantics, many graph neural network approaches for heterogeneous graphs use metapaths to capture multi-hop interactions between nodes. Typically, features from non-target nodes are not incorporated into the learning procedure. However, there can be nonlinear, high-order interactions involving multiple nodes or edges. In this paper, we present Simplicial Graph Attention Network (SGAT), a simplicial complex approach to represent such high-order interactions by placing features from non-target nodes on the simplices. We then use attention mechanisms and upper adjacencies to generate representations. We empirically demonstrate the efficacy of our approach with node classification tasks on heterogeneous graph datasets and further show SGAT's ability in extracting structural information by employing random node features. Numerical experiments indicate that SGAT performs better than other current state-of-the-art heterogeneous graph learning methods.