有效电阻与组织特异性相互作用组中的图神经网络可靠性
Effective Resistance and Graph Neural Network Reliability in Tissue-Specific Interactomes
- University of Montana（蒙大拿大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究利用有效电阻作为信号，在24个组织特异性相互作用组中探究其与图神经网络节点损失的关系，发现残差信号可解释额外损失，且效应随深度增强。
AI中文摘要：
蛋白质功能注释不仅需要知道模型预测什么，还需要知道哪些预测不可信。我们探究组织特异性相互作用结构是否携带该信息。我们候选的信号是有效电阻，此前曾用于通过重连来缓解过压缩问题。在24个组织特异性相互作用组中，该信号受逆度支配，且随着共表达过滤网络增长，退化加剧，Spearman相关系数为-0.955。在所有24个网络中，与该极限的残差偏离超过了保持度数的零模型图。在控制预测熵、度数、注释基数、局部结构和仅特征难度后，在减去排列基线后，该残差在24个留出网络中的19个中解释了额外的每节点损失，且在每个深度均如此，效应随深度单调增强。增量达到控制变量未解释方差的0.37%，是排列基线的5.6倍，而在保持度数的零模型世界中重新训练模型时仅为1.5倍。选择性预测改进甚微。该信号可复现；度数退化限制了它。
英文摘要：
Protein function annotation needs to know which predictions to distrust, not only what a model predicts. We ask whether tissue-specific interaction structure carries that information. Our candidate signal is effective resistance, used previously to relieve over-squashing by rewiring. Across 24 tissue-specific interactomes it is dominated by inverse degree, and the degeneration deepens as the co-expression filtered network grows, with a Spearman correlation of -0.955. The residual departure from that limit exceeds degree-preserving null graphs in all 24 networks. Controlling for predictive entropy, degree, annotation cardinality, local structure and feature-only difficulty, the residual explains additional per-node loss in 19 of 24 held-out networks once a permutation floor is subtracted, at every depth, and the effect strengthens monotonically with depth. The increment reaches 0.37% of the variance the controls leave unexplained, 5.6 times a permutation floor, against 1.5 times when the model is retrained in a degree-preserving null world. Selective prediction improves negligibly. The signal is reproducible; degree degeneration bounds it.
