通过拓扑信息优化图神经网络量化，速度提升十倍且精度不变。
TopGQ: Fast GNN Post-Training Quantization Leveraging Topology Information
- 利用邻接矩阵融合尺度，实现内外维度联合量化
- 量化时间减少一个数量级，精度几乎无损
- 适合部署时需快速压缩模型的图学习应用
现有图神经网络（GNN）量化方法存在显著的量化开销，严重限制了其在真实场景中的应用。为此，我们提出TopGQ，一种高精度的后训练GNN量化框架，有效缓解冗余量化开销。我们提出双轴尺度吸收机制，通过将一个尺度合并至邻接矩阵，实现沿外维和内维的激活量化。此外，引入拓扑代理指标TopPIN，用于量化过程中按节点局部结构相似性分组。实验表明，TopGQ将量化时间降低一个数量级，同时保持模型精度。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。