mlsanityData to 14 Oct 2026

Personalized Subgraph Federated Learning with Differentiable Auxiliary Projections

arXiv 2505.23864 ↗First posted 29 May 2025cs.LG cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) on graph-structured data typically faces non-IID challenges, particularly in scenarios where each client holds a distinct subgraph sampled from a global graph. In this paper, we introduce Federated learning with Auxiliary projections (FedAux), a personalized subgraph FL framework that learns to align, compare, and aggregate heterogeneously distributed local models without sharing raw data or node embeddings. In FedAux, each client jointly trains (i) a local GNN and (ii) a learnable auxiliary projection vector (APV) that differentiably projects node embeddings onto a 1D space. A soft-sorting operation followed by a lightweight 1D convolution refines these embeddings in the ordered space, enabling the APV to effectively capture client-specific information. After local training, these APVs serve as compact signatures that the server uses to compute inter-client similarities and perform similarity-weighted parameter mixing, yielding personalized models while preserving cross-client knowledge transfer. Moreover, we provide rigorous theoretical analysis to establish the convergence and rationality of our design. Empirical evaluations across diverse graph benchmarks demonstrate that FedAux substantially outperforms existing baselines in both accuracy and personalization performance. The code is available at https://github.com/JhuoW/FedAux.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 31 of its 48 references that are in the map. First posted on arXiv 29 May 2025.

Builds on

31 of 48 references.

References · 31

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  3. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  4. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  5. 2018Federated Learning with Non-IID Datacited by 1,108
  6. 2020Adaptive Federated Optimizationcited by 1,046
  7. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  8. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
  9. 2015Image-based Recommendations on Styles and Substitutescited by 706
  10. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
  11. 2021Federated Learning Based on Dynamic Regularizationcited by 562
  12. 2019Federated Learning with Personalization Layerscited by 541
19 more
  1. 2021Towards Personalized Federated Learningcited by 464
  2. 2021Subgraph Federated Learning with Missing Neighbor Generationcited by 132
  3. 2021Federated Graph Classification over Non-IID Graphscited by 114
  4. 2023Stochastic Controlled Averaging for Federated Learning with Communication Compressioncited by 101
  5. 2020Non-Local Graph Neural Networkscited by 91
  6. 2022Federated Learning on Non-IID Graphs via Structural Knowledge Sharingcited by 88
  7. 2020GraphFL: A Federated Learning Framework for Semi-Supervised Node Classification on Graphscited by 64
  8. 2022Personalized Subgraph Federated Learningcited by 54
  9. 2024FedGTA: Topology-aware Averaging for Federated Graph Learningcited by 44
  10. 2019Towards Federated Graph Learning for Collaborative Financial Crimes Detectioncited by 33
  11. 2024Efficient Graph Similarity Computation with Alignment Regularizationcited by 26
  12. 2022FedGCN: Convergence-Communication Tradeoffs in Federated Training of Graph Convolutional Networkscited by 24
  13. 2024Partitioning Message Passing for Graph Fraud Detectioncited by 23
  14. 2024FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preferencecited by 16
  15. 2022FedEgo: Privacy-preserving Personalized Federated Graph Learning with Ego-graphscited by 12
  16. 2024FedGT: Federated Node Classification with Scalable Graph Transformercited by 5
  17. 2024Commute Graph Neural Networkscited by 5
  18. 2024FedNE: Surrogate-Assisted Federated Neighbor Embedding for Dimensionality Reductioncited by 1
  19. 2025FedGrAINS: Personalized SubGraph Federated Learning with Adaptive Neighbor Samplingcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026PACE: Propagation-Aware Collaborative Correction for One-Shot Personalized Federated Graph Learningcited by 0