← 研踪 PaperTrailarXiv:2611.16169 · v1
Feature-Aware Edge Sampling for Approximate One-Step Laplacian Propagation
首次提交 2026-11-12 09:59
版本更新 2026-11-12 09:59
雷达观测 2026-11-13 14:16
摘要
This paper studies how to approximate one-step combinatorial Laplacian messages in graph neural networks using edge sampling. We propose a spanning tree based hybrid sampler that combines feature-conditioned message scores and effective-resistance leverage scores, derive the expected one-step message error and obtain the optimal sampling probabilities and error frontier for a given expected edge budget. Preliminary experiments on synthetic community graphs show that message error decreases, while classification accuracy increases slightly, as the edge budget grows, and performance of the hybrid sampler is in between of optimal selection uniform random sampling. We leave multi-step propagation and evaluation on larger and real graphs for future work.
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-12 09:59 · 最新观测版本
Feature-Aware Edge Sampling for Approximate One-Step Laplacian Propagation
This paper studies how to approximate one-step combinatorial Laplacian messages in graph neural networks using edge sampling. We propose a spanning tree based hybrid sampler that combines feature-conditioned message scores and effective-resistance leverage scores, derive the expected one-step message error and obtain the optimal sampling probabilities and error frontier for a given expected edge budget. Preliminary experiments on synthetic community graphs show that message error decreases, while classification accuracy increases slightly, as the edge budget grows, and performance of the hybrid sampler is in between of optimal selection uniform random sampling. We leave multi-step propagation and evaluation on larger and real graphs for future work.
查看此版本解读 →查看此版本原文 ↗