发表机构
Seoul National University（首尔大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有GNN量化方法开销大的问题，提出TopGQ框架，通过双轴尺度吸收和TopPIN拓扑分组实现快速后训练量化，量化时间降一个数量级且精度保留。
AI 中文摘要
现有GNN量化方法存在显著的量化开销，严重限制了其在实际场景中的应用。为此，我们提出TopGQ，一种精准的后训练GNN量化框架，可减轻冗余的量化开销。我们提出双轴尺度吸收，通过将一个维度合并到邻接矩阵中，实现沿外部和内部维度的激活量化。在此基础上，我们引入TopPIN，作为节点局部结构的代理，用于在量化过程中对具有相似拓扑的节点进行分组。实验结果表明，TopGQ将量化时间降低了一个数量级，同时保持了精度。
英文摘要
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.
Comments7 pages, 4 figures. Accepted at the 63rd ACM/IEEE Design Automation Conference (DAC 2026)
