Simple Multigraph Convolution Networks
This work addresses computational bottlenecks in multigraph analysis for researchers and practitioners, though it appears incremental as it builds on existing polynomial expansion methods.
The paper tackles the problem of inefficient cross-view interaction in multigraph convolution methods by proposing SMGCN, which extracts consistent cross-view topologies and uses them in polynomial expansion to reduce computational complexity, achieving state-of-the-art performance on ACM and DBLP benchmark datasets.
Existing multigraph convolution methods either ignore the cross-view interaction among multiple graphs, or induce extremely high computational cost due to standard cross-view polynomial operators. To alleviate this problem, this paper proposes a Simple MultiGraph Convolution Networks (SMGCN) which first extracts consistent cross-view topology from multigraphs including edge-level and subgraph-level topology, then performs polynomial expansion based on raw multigraphs and consistent topologies. In theory, SMGCN utilizes the consistent topologies in polynomial expansion rather than standard cross-view polynomial expansion, which performs credible cross-view spatial message-passing, follows the spectral convolution paradigm, and effectively reduces the complexity of standard polynomial expansion. In the simulations, experimental results demonstrate that SMGCN achieves state-of-the-art performance on ACM and DBLP multigraph benchmark datasets. Our codes are available at https://github.com/frinkleko/SMGCN.