发表机构
Université Sorbonne Paris Nord; CNRS; Laboratoire d’Informatique de Paris Nord（索邦巴黎北大学; 法国国家科学研究中心; 巴黎北信息学实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对节点分类GNN，提出分离混合权重与logit定位误差的方法，通过精确质量线性规划和后处理修复，在八个数据集上提升准确率至65.3%，并发现平移主导增益。
AI 中文摘要
许多节点分类图神经网络将线性分类器应用于非负局部消息的混合。误差可能反映混合权重不佳，或可达到的logit集合定位不当，不利于分类器。我们通过精确质量线性规划和两种学习后的后处理修复来分离这些原因。每个重新加权的预测都有等效的中心化logit平移，但只有消息诱导位移集合中的平移可通过重新加权实现。在八个数据集、八个GNN骨干和十个分割上，平均准确率从冻结模型的62.6%提升到重新加权的63.8%和集合条件平移的65.3%。参数匹配的仅节点平移器达到64.6%，表明平移解释了大部分增益，而消息集合提供了较小的额外收益。尽管神谕重新加权可以纠正许多错误，无标签重新加权仅捕获了其中一小部分潜力：局部证据通常存在但难以选择，放宽证据约束比在其中学习更有效。
英文摘要
Many node-classification GNNs apply a linear classifier to a nonnegative mixture of local messages. An error can reflect either poor mixture weights or a reachable logit set poorly positioned for the classifier. We separate these causes with an exact-mass linear program and two learned post-hoc repairs. Every reweighted prediction has an equivalent centered logit translation, but only translations in a message-induced displacement set are realizable by reweighting. Across eight datasets, eight GNN backbones, and ten splits, mean accuracy rises from 62.6% for the frozen models to 63.8% with reweighting and 65.3% with set-conditioned translation. A parameter-matched node-only translator reaches 64.6%, showing that translation explains most of the gain while the message set supplies a smaller additional benefit. Although oracle reweighting can correct many errors, label-free reweighting captures little of this potential: local evidence is often present but hard to select, and relaxing the evidence constraint is more effective than learning within it.
CommentsMLG 2026
