Beyond Graph Convolutional Network: An Interpretable Regularizer-centered Optimization Framework
This work addresses the need for interpretability and design guidance in GCNs for researchers and practitioners in graph machine learning, though it is incremental as it builds on existing GCN methods.
The authors tackled the lack of a general framework for interpreting and designing Graph Convolutional Networks (GCNs) by proposing an interpretable regularizer-centered optimization framework that explains various GCNs and introduces a dual-regularizer GCN (tsGCN) to capture topological and semantic structures, achieving superior performance in classification tasks on eight public datasets.
Graph convolutional networks (GCNs) have been attracting widespread attentions due to their encouraging performance and powerful generalizations. However, few work provide a general view to interpret various GCNs and guide GCNs' designs. In this paper, by revisiting the original GCN, we induce an interpretable regularizer-centerd optimization framework, in which by building appropriate regularizers we can interpret most GCNs, such as APPNP, JKNet, DAGNN, and GNN-LF/HF. Further, under the proposed framework, we devise a dual-regularizer graph convolutional network (dubbed tsGCN) to capture topological and semantic structures from graph data. Since the derived learning rule for tsGCN contains an inverse of a large matrix and thus is time-consuming, we leverage the Woodbury matrix identity and low-rank approximation tricks to successfully decrease the high computational complexity of computing infinite-order graph convolutions. Extensive experiments on eight public datasets demonstrate that tsGCN achieves superior performance against quite a few state-of-the-art competitors w.r.t. classification tasks.