mlsanityData to 7 Oct 2026

FedTopo: Relation-Level Topology Sharing for Model-Heterogeneous Federated Learning

arXiv 2607.26801 ↗First posted 29 Jul 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) enables collaborative learning over decentralized data silos without centralizing raw data. However, heterogeneous local architectures often induce non-aligned representation spaces, making it difficult to transfer global knowledge across silos. Existing paradigms share this knowledge as model parameters, distilled predictions, or class prototypes, yet all encode it in an absolute space that must be aligned across clients. Heterogeneous backbones break this alignment, so the shared knowledge becomes unreliable and misleads local training. We propose FedTopo, a relation-level framework that encodes global knowledge as class relation topology, capturing how classes relate within each client rather than where they lie in feature space. Each client builds its relation topology from local prototypes and uploads it with class statistics. The server then aggregates these relations in a reliability-aware manner that down-weights weakly supported ones, and broadcasts the global topology to clients. The global topology guides local training by emphasizing topology-similar negative classes. Experiments on three datasets under eight heterogeneous backbones show that FedTopo consistently outperforms parameter-, distillation-, and prototype-sharing baselines, with low communication and no inference overhead. Our code is available at https://github.com/Zhaoyang-Ma/FedTopo.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 28 of its 38 references that are in the map. First posted on arXiv 29 Jul 2026.

Builds on

28 of 38 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  4. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  5. 2014Going Deeper with Convolutionscited by 4,231
  6. 2019Advances and Open Problems in Federated Learningcited by 3,021
  7. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  8. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 836
  9. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 678
  10. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 537
  11. 2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 454
  12. 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 385
16 more
  1. 2021Data-Free Knowledge Distillation for Heterogeneous Federated Learningcited by 380
  2. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 349
  3. 2020HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clientscited by 334
  4. 2020Think Locally, Act Globally: Federated Learning with Local and Global Representationscited by 322
  5. 2018Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Datacited by 242
  6. 2021FedKD: Communication Efficient Federated Learning via Knowledge Distillationcited by 185
  7. 2020Federated Mutual Learningcited by 70
  8. 2023FedGH: Heterogeneous Federated Learning with Generalized Global Headercited by 56
  9. 2024FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learningcited by 47
  10. 2024Federated Model Heterogeneous Matryoshka Representation Learningcited by 21
  11. 2023HeteFedRec: Federated Recommender Systems with Model Heterogeneitycited by 20
  12. 2024An Upload-Efficient Scheme for Transferring Knowledge From a Server-Side Pre-trained Generator to Clients in Heterogeneous Federated Learningcited by 17
  13. 2022FedKNOW: Federated Continual Learning with Signature Task Knowledge Integration at Edgecited by 10
  14. 2025HtFLlib: A Comprehensive Heterogeneous Federated Learning Library and Benchmarkcited by 7
  15. 2025FedSKD: Aggregation-free Model-heterogeneous Federated Learning via Multi-dimensional Similarity Knowledge Distillation for Medical Image Classificationcited by 1
  16. 2025FedRE: A Representation Entanglement Framework for Model-Heterogeneous Federated Learningcited by 1

Built on by

Not cited yet.