# TopGQ: Fast GNN Post-Training Quantization Leveraging Topology Information

arXiv: https://arxiv.org/abs/2608.30394 · HTML: https://mlsanity.com/paper/2608.30394/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 34 references that are in the map.
- First posted on arXiv 31 Aug 2026.

## Builds on (most cited first, 22 of 22)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs](https://mlsanity.com/paper/2404.00456/) (2024)
- [Graph U-Nets](https://mlsanity.com/paper/1905.05178/) (2019)
- [OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs](https://mlsanity.com/paper/2103.09430/) (2021)
- [Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting](https://mlsanity.com/paper/2103.07719/) (2021)
- [Identity-aware Graph Neural Networks](https://mlsanity.com/paper/2101.10320/) (2021)
- [ROLAND: Graph Learning Framework for Dynamic Graphs](https://mlsanity.com/paper/2208.07239/) (2022)
- [Degree-Quant: Quantization-Aware Training for Graph Neural Networks](https://mlsanity.com/paper/2008.05000/) (2020)
- [Binary Graph Neural Networks](https://mlsanity.com/paper/2012.15823/) (2020)
- [Monolith: Real Time Recommendation System With Collisionless Embedding Table](https://mlsanity.com/paper/2209.07663/) (2022)
- [SGQuant: Squeezing the Last Bit on Graph Neural Networks with Specialized Quantization](https://mlsanity.com/paper/2007.05100/) (2020)
- [Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks](https://mlsanity.com/paper/2109.12872/) (2021)
- [NeutronStream: A Dynamic GNN Training Framework with Sliding Window for Graph Streams](https://mlsanity.com/paper/2312.02473/) (2023)
- [Low-bit Quantization for Deep Graph Neural Networks with Smoothness-aware Message Propagation](https://mlsanity.com/paper/2308.14949/) (2023)
- [Graph Learning Augmented Heterogeneous Graph Neural Network for Social Recommendation](https://mlsanity.com/paper/2109.11898/) (2021)
- [Prioritizing Original News on Facebook](https://mlsanity.com/paper/2102.08465/) (2021)
- [InkStream: Real-time GNN Inference on Streaming Graphs via Incremental Update](https://mlsanity.com/paper/2309.11071/) (2023)

## Abstract (arXiv)

Existing GNN quantization methods suffer from considerable quantization overhead, which severely limits their practical usage in real-world scenarios. To this end, we present TopGQ, an accurate post-training GNN quantization framework, alleviating redundant quantization overhead. We propose dual-axis scale absorption, which enables activation quantization along both the outer and inner dimensions by merging one into the adjacency matrix. On top of that, we introduce TopPIN, a proxy for nodes' local structure, and use it to group nodes with similar topology during quantization. Experimental results show that TopGQ reduces quantization time by an order of magnitude while preserving accuracy.