Reviewed Version (pdf): https://openreview.net/references/pdf?id=GPeowpvbL3
Keywords: Graph Representation Learning, Disentangled Representation Learning
Abstract: Graph Neural Networks (GNNs) learn effective node/graph representations by aggregating the attributes of neighboring nodes, which commonly derives a single representation mixing the information of graph structure and node attributes. However, these two kinds of information might be semantically inconsistent and could be useful for different tasks. In this paper, we aim at learning node/graph representations with Structure-Attribute Disentanglement (GraphSAD). We propose to disentangle graph structure and node attributes into two distinct sets of representations, and such disentanglement can be done in either the input or the embedding space. We further design a metric to quantify the extent of such a disentanglement. Extensive experiments on multiple datasets show that our approach can indeed disentangle the semantics of graph structure and node attributes, and it achieves superior performance on both node and graph classification tasks.
One-sentence Summary: This work seeks to learn structure-attribute disentangled node/graph representations and measure such disentanglement quantitatively.
Supplementary Material: zip
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics