Papers › VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization
VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization
Mucong Ding, Kezhi Kong, Jingling Li, Chen Zhu, John P Dickerson, Furong Huang, Tom Goldstein
Most state-of-the-art Graph Neural Networks (GNNs) can be defined as a form of graph convolution which can be realized by message passing between direct neighbors or beyond. To scale such GNNs to large graphs, various neighbor-, layer-, or subgraph-sampling techniques are proposed to alleviate the "neighbor explosion" problem by considering only a small subset of messages passed to the nodes in a mini-batch. However, sampling-based methods are difficult to apply to GNNs that utilize many-hops-away or global context each layer, show unstable performance for different tasks and datasets, and do not speed up model inference. We propose a principled and fundamentally different approach, VQ-GNN, a universal framework to scale up any convolution-based GNNs using Vector Quantization (VQ) without compromising the performance. In contrast to sampling-based techniques, our approach can effectively preserve all the messages passed to a mini-batch of nodes by learning and updating a small number of quantized reference vectors of global node representations, using VQ within each GNN layer. Our framework avoids the "neighbor explosion" problem of GNNs using quantized representations combined with a low-rank version of the graph convolution matrix. We show that such a compact low-rank version of the gigantic convolution matrix is sufficient both theoretically and experimentally. In company with VQ, we design a novel approximated message passing algorithm and a nontrivial back-propagation rule for our framework. Experiments on various types of GNN backbones demonstrate the scalability and competitive performance of our framework on large-graph node classification and link prediction benchmarks.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Link Property Prediction | ogbl-collab | VQ-GNN (SAGE-Mean) | Test Hits@50 | 0.4673 ± 0.0164 . | #29 of 34 | Archive leaderboard | report |
| Link Property Prediction | ogbl-collab | VQ-GNN (GCN) | Test Hits@50 | 0.4316 ± 0.0134 | #31 of 34 | Archive leaderboard | report |
| Link Property Prediction | ogbl-collab | VQ-GNN (GAT) | Test Hits@50 | 0.4102 ± 0.0099 | #32 of 34 | Archive leaderboard | report |
| Node Classification | PPI | VQ-GNN (GAT) | F1 | 97.37 | #15 of 24 | Archive leaderboard | report |
| Node Classification | VQ-GNN (SAGE-Mean) | Accuracy | 94.5 ± .0024 | #12 of 16 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections