VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs

arXiv:2308.02117v3 Announce Type: replace
Abstract: GNN-to-MLP distillation aims to utilize knowledge distillation (KD) to learn computationally-efficient multi-layer perceptron (student MLP) on graph data by mimicking the output representations of teacher GNN. Existing methods mainly make the MLP to mimic the GNN predictions over a few class labels. However, the class space may not be expressive enough for covering numerous diverse local graph structures, thus limiting the performance of knowledge transfer from GNN to MLP. To address this issue, we propose …

arxiv cs.ai cs.cv cs.lg gnns graph graph representation representation space type