Problem
Research questions and friction points this paper is trying to address.
GNN quantization
quantization overhead
practical usage
TopGQ: Fast GNN Post-Training Quantization Leveraging Topology Information
🤖 AI Summary
为解决GNN量化方法的高开销问题，TopGQ通过双轴尺度吸收和拓扑信息分组节点的方法，显著减少了量化时间同时保持了准确性。
📝 Abstract
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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
post-training quantization
dual-axis scale absorption
topology information
TopPIN
🔎 Similar Papers
No similar papers found.
