A Graph Convolutional Network Composition Framework for Semi-supervised Classification
This work provides a flexible framework for composing GCN variants, which is incremental and useful for researchers and practitioners in graph-based machine learning.
The authors tackled the problem of designing new graph convolutional network (GCN) variants for semi-supervised classification by proposing a composition framework using building blocks, and found that several new variants are as competitive as or better than the original GCN in empirical evaluations on benchmark datasets.
Graph convolutional networks (GCNs) have gained popularity due to high performance achievable on several downstream tasks including node classification. Several architectural variants of these networks have been proposed and investigated with experimental studies in the literature. Motivated by a recent work on simplifying GCNs, we study the problem of designing other variants and propose a framework to compose networks using building blocks of GCN. The framework offers flexibility to compose and evaluate different networks using feature and/or label propagation networks, linear or non-linear networks, with each composition having different computational complexity. We conduct a detailed experimental study on several benchmark datasets with many variants and present observations from our evaluation. Our empirical experimental results suggest that several newly composed variants are useful alternatives to consider because they are as competitive as, or better than the original GCN.