English

VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs

Machine Learning 2024-03-07 v3 Artificial Intelligence Computer Vision and Pattern Recognition

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 to learn a new powerful graph representation space by directly labeling nodes' diverse local structures for GNN-to-MLP distillation. Specifically, we propose a variant of VQ-VAE to learn a structure-aware tokenizer on graph data that can encode each node's local substructure as a discrete code. The discrete codes constitute a codebook as a new graph representation space that is able to identify different local graph structures of nodes with the corresponding code indices. Then, based on the learned codebook, we propose a new distillation target, namely soft code assignments, to directly transfer the structural knowledge of each node from GNN to MLP. The resulting framework VQGraph achieves new state-of-the-art performance on GNN-to-MLP distillation in both transductive and inductive settings across seven graph datasets. We show that VQGraph with better performance infers faster than GNNs by 828x, and also achieves accuracy improvement over GNNs and stand-alone MLPs by 3.90% and 28.05% on average, respectively. Code: https://github.com/YangLing0818/VQGraph.

Keywords

Cite

@article{arxiv.2308.02117,
  title  = {VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs},
  author = {Ling Yang and Ye Tian and Minkai Xu and Zhongyi Liu and Shenda Hong and Wei Qu and Wentao Zhang and Bin Cui and Muhan Zhang and Jure Leskovec},
  journal= {arXiv preprint arXiv:2308.02117},
  year   = {2024}
}

Comments

ICLR 2024. Code: https://github.com/YangLing0818/VQGraph

R2 v1 2026-06-28T11:47:50.851Z