发表机构
School of Cyber Science and Engineering, Wuhan University（武汉大学网络空间安全学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
PACE针对个性化联邦图学习的客户端异质性问题，提出传播感知协同修正方法，通过紧凑修正增强本地模型，在多数数据集上提升预测性能。
AI 中文摘要
客户端异质性在个性化联邦图学习中既带来机遇也存在风险：其他子图掌握的知识可补充接收方的本地模型，但不兼容的知识迁移会覆盖可靠预测结果。一次性通信加剧了这种矛盾，因为不合适的服务器返回结果无法后续修正。本文提出PACE，将协同知识视为对完整本地预测器的紧凑修正而非替代方案。每个客户端上传一个秩为r的更新载体和传播消息矩的对角草图，服务器利用这些内容构建传播感知、以接收方为锚点的修正，同时接收方保留其完整本地模型。随后采用凸负对数似然校准（CNLL）通过验证节点选择本地和外部logits之间的一个系数；模型参数保持固定且不发送反馈。在秩为6时，6个评估数据集上的个性化返回结果占密集张量字节的9.6%-17.6%。该修正获得非零权重，在5个数据集上提升了准确率和加权F1值；在ogbn-arxiv数据集上，CNLL为该修正分配零预测权重并完全保留本地预测结果。将相同CNLL规则应用于3个引文数据集上的匹配基线无法解释这些增益。因此核心结论是：当接收方证据支持时，小型传输修正可增强完整本地模型，否则保持本地预测不变。
英文摘要
Client heterogeneity creates both an opportunity and a risk in personalized federated graph learning. Knowledge held by other subgraphs may complement a receiver's Local model, but an incompatible transfer can override reliable predictions. One-shot communication sharpens this tension because an unsuitable server return cannot be corrected later. We introduce PACE, which treats collaborative knowledge as a compact correction to a complete Local predictor rather than as its replacement. Each client uploads a rank-r update carrier and a diagonal sketch of propagated message moments. The server uses them to construct a propagation-aware, receiver-anchored correction, while the receiver retains its full Local model. Convex negative-log-likelihood calibration (CNLL) then selects one coefficient between Local and External logits using validation nodes; model parameters remain fixed and no feedback is sent. At Rank-6, personalized returns occupy 9.6-17.6% of dense tensor bytes across the six evaluated datasets. The correction receives nonzero weight and improves both Accuracy and weighted-F1 over Local on five datasets; on ogbn-arxiv, CNLL assigns zero predictive weight to the correction and preserves Local predictions exactly. Applying the same CNLL rule to matched baselines on three citation datasets does not account for these gains. The central result is therefore that a small transported correction can augment a complete Local model when receiver evidence supports it while leaving the Local prediction unchanged otherwise.
Comments15 pages, 4 figures, 12 tables
