Poster
in
Workshop: Geometry-grounded Representation Learning and Generative Modeling
Transferability for Graph Convolutional Networks
Christian Koke · Abhishek Saroha · Yuesong Shen · Marvin Eisenberger · Michael Bronstein · Daniel Cremers
Keywords: [ Proofs ] [ Spectral Graph Theory ] [ Spectral Methods ] [ transferability ]
This work develops a general transferability theory for graph convolutional networks; applicable to architectures based on both undirected- as well as recently introduced directed convolutional filters. Transferability is considered between graphs that are similar from the perspective of information diffusion. A detailed theoretical investigation establishes which filters render networks stable with respect to this novel approach to transferability. Illustrative examples (including graph-coarsening) showcase how newly established results may inform the design of transferable architectures in practice. Numerical experiments on real-world data validate the theoretical findings and complement the mathematical analysis.