Gaussian-Induced Convolution for Graphs


  • Jiatao Jiang Nanjing University of Science and Technology
  • Zhen Cui Nanjing University of Science and Technology
  • Chunyan Xu Nanjing University of Science and Technology
  • Jian Yang Nanjing University of Science and Technology



Learning representation on graph plays a crucial role in numerous tasks of pattern recognition. Different from gridshaped images/videos, on which local convolution kernels can be lattices, however, graphs are fully coordinate-free on vertices and edges. In this work, we propose a Gaussianinduced convolution (GIC) framework to conduct local convolution filtering on irregular graphs. Specifically, an edgeinduced Gaussian mixture model is designed to encode variations of subgraph region by integrating edge information into weighted Gaussian models, each of which implicitly characterizes one component of subgraph variations. In order to coarsen a graph, we derive a vertex-induced Gaussian mixture model to cluster vertices dynamically according to the connection of edges, which is approximately equivalent to the weighted graph cut. We conduct our multi-layer graph convolution network on several public datasets of graph classification. The extensive experiments demonstrate that our GIC is effective and can achieve the state-of-the-art results.




How to Cite

Jiang, J., Cui, Z., Xu, C., & Yang, J. (2019). Gaussian-Induced Convolution for Graphs. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 4007-4014.



AAAI Technical Track: Machine Learning