Lune

KDD2026Top-tier venue

Disagreement-Aware Subgraph Federated Learning via Uncertainty-Guided Local-Global Alignment

Keao Xi, Nannan Wu, Yiming Zhao, Wenjun Wang

Abstract

Subgraph federated learning (subgraph FL) enables collaborative graph neural network training without sharing raw graph data, but suffers from severe Non-IID distributions and structural fragmentation. In such settings, Non-IID distributions induce pronounced client specialization, where each client excels in a subset of nodes but remains insufficiently trained on others. However, existing similarity-based aggregation and distillation methods fail to balance client specialization and global generalization, often reinforcing dominant local representations and impairing generalization on under-represented nodes, or over-incorporating global knowledge and thereby disrupting well-optimized local specialization. In this paper, we propose FedDUA, a novel disagreement-aware and uncertainty-guided framework for subgraph FL. Specifically, FedDUA first models cross-client semantic disagreement via a lightweight semantic anchor graph and derives adaptive aggregation weights for reliable global federated knowledge. On the client side, FedDUA introduces an uncertainty-aware local-global semantic alignment mechanism that selectively reinforces representations of confident nodes while guiding uncertain nodes with aggregated global knowledge, thereby balancing local specialization and global generalization. Extensive experiments on six real-world datasets demonstrate that FedDUA consistently outperforms the state-of-the-art subgraph FL methods across varying numbers of clients. Further analyses validate the robustness and effectiveness of the proposed disagreement modeling and uncertainty-aware local-global semantic alignment strategies.

Ask Lune

Know where this paper stands in minutes, not an afternoon.

Lune can read the top-tier papers that cite it and the ones closest to it, and tells you what it claims, what came after and where it falls short, each point cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

its abstract · related work

Get the answer

Free to start. No credit card required.

Related papers

  1. Personalized Subgraph Federated Learning with Differentiable Auxiliary ProjectionsWei Zhuo, Zhaohuan Zhan, Han YuNeurIPS 2025 · 1 citation
  2. Heterogeneity-Aware Knowledge Sharing for Graph Federated LearningWentao Yu, Sheng Wan, Shuo Chen, Bo Han et al.ICML 2026 · 1 citation
  3. FedSPA: Generalizable Federated Graph Learning under Homophily HeterogeneityZihan Tan, Guancheng Wan, Wenke Huang, He Li et al.CVPR 2025
  4. FedSDR: Federated Graph Learning with Structural Noise Detection and ReconstructionJiaqi Liu, Zihan Tan, Guancheng Wan, Wenke Huang et al.CVPR 2026
  5. FedAFD: Multimodal Federated Learning via Adversarial Fusion and DistillationMin Tan, Junchao Ma, Yinfu FENG, Jiajun Ding et al.CVPR 2026 · 1 citation
Dusk over the sea between two cliffs drawn in fine vertical lines