联邦图神经网络中的结构性负迁移：诊断、因果探究与发散感知缓解的局限性
Structural Negative Transfer in Federated Graph Neural Networks: Diagnosis, Causal Investigation, and the Limits of Divergence-Aware Mitigation
浏览论文内容
中文总结 AI 辅助
本研究诊断联邦图神经网络中的结构性负迁移，发现结构异常客户端因加入联邦损失过半准确率，度发散是弱相关信号，但因果干预和修复方案均未验证其有效性。
中文摘要 AI 辅助
联邦学习允许多个参与方在不汇集原始数据的情况下，通过交换本地训练的模型更新来共同训练一个共享模型。联邦平均假设，当参与方的数据大致相似时，对本地模型进行平均是解决一个共享问题的合理方式。关于非独立同分布（non-IID）联邦学习的研究表明，该假设能够承受标签和特征分布上的差异。我们探究该假设是否能够承受另一种特定于图神经网络的差异，即客户端图在标签或特征分布上并无不同，而是在结构本身存在差异，这要求相同的共享权重在根本不同的拓扑上运行。我们将由此产生的损害称为结构性负迁移。在一个由真实引文网络和合成结构代理组成的联邦中，一个结构上非典型的客户端仅因加入联邦就损失了其可达到准确率的一半以上。在一个初始的六客户端联邦中，两个无需标签、可在训练前计算的结构统计量与这种损害强烈相关。扩展到二十个客户端后显示，度发散仍与损害相关，尽管相关性较弱，并且在去除域对比后依然存在。谱发散未能复现，我们将其追溯到一个由用于留一法统计的参考池组成引起的混杂因素。一项隔离拓扑的因果干预未发现显著效应。一种度归一化机制在二十四个随机种子上保持一致，但在校正后并未解释该损害。五种候选修复方案中最佳的一种仅在应用匹配的结构盲对照之前优于调优基线，之后其增益消失。幸存下来的是一种适度的、部分复现的、特定于度的信号，该信号尚不能作为大规模验证的预测因子。
英文摘要
Federated learning lets multiple participants train a shared model without pooling raw data, by exchanging locally trained model updates instead. Federated averaging assumes that averaging local models is a reasonable way to solve one shared problem when participants' data are broadly similar. Work on non-IID federated learning has shown that this assumption can withstand differences in label and feature distributions. We ask whether it survives a different strain specific to graph neural networks, where client graphs differ not in label or feature distribution but in structure itself, requiring the same shared weights to operate over fundamentally different topologies. We call the resulting harm structural negative transfer. In a federation of real citation networks and synthetic structural proxies, a structurally atypical client lost more than half its achievable accuracy simply by joining. In an initial six-client federation, two label-free structural statistics computable before training were strongly associated with this harm. Expanding to twenty clients showed that degree divergence remained associated with harm, although more weakly, and survived removal of domain contrast. Spectral divergence did not replicate, which we trace to a confound caused by the composition of the reference pool used for leave-one-out statistics. A causal intervention isolating topology found no significant effect. A degree-normalization mechanism held across twenty-four seeds but did not explain the harm when corrected. The best of five candidate fixes beat a tuned baseline only until a matched, structurally blind control was applied, after which the gain disappeared. What survives is a modest, partially replicated, degree-specific signal that is not yet a validated predictor at scale.
发表机构
- PES University（PES大学）
机构由 AI 辅助整理，请以论文原文为准。
