mlsanityData to 7 Oct 2026

FedSSA: Semantic Similarity-based Aggregation for Efficient Model-Heterogeneous Personalized Federated Learning

arXiv 2312.09006 ↗First posted 14 Dec 2023cs.LG cs.DCcited by 10

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) is a privacy-preserving collaboratively machine learning paradigm. Traditional FL requires all data owners (a.k.a. FL clients) to train the same local model. This design is not well-suited for scenarios involving data and/or system heterogeneity. Model-Heterogeneous Personalized FL (MHPFL) has emerged to address this challenge. Existing MHPFL approaches often rely on a public dataset with the same nature as the learning task, or incur high computation and communication costs. To address these limitations, we propose the Federated Semantic Similarity Aggregation (FedSSA) approach for supervised classification tasks, which splits each client's model into a heterogeneous (structure-different) feature extractor and a homogeneous (structure-same) classification header. It performs local-to-global knowledge transfer via semantic similarity-based header parameter aggregation. In addition, global-to-local knowledge transfer is achieved via an adaptive parameter stabilization strategy which fuses the seen-class parameters of historical local headers with that of the latest global header for each client. FedSSA does not rely on public datasets, while only requiring partial header parameter transmission to save costs. Theoretical analysis proves the convergence of FedSSA. Extensive experiments present that FedSSA achieves up to 3.62% higher accuracy, 15.54 times higher communication efficiency, and 15.52 times higher computational efficiency compared to 7 state-of-the-art MHPFL baselines.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 38 of its 58 references that are in the map. First posted on arXiv 14 Dec 2023.

Builds on

38 of 58 references.

References · 38

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Advances and Open Problems in Federated Learningcited by 3,021
  3. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 678
  4. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 537
  5. 2019Federated Learning with Personalization Layerscited by 533
  6. 2021Towards Personalized Federated Learningcited by 462
  7. 2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 454
  8. 2021Data-Free Knowledge Distillation for Heterogeneous Federated Learningcited by 380
  9. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 349
  10. 2021Federated Learning on Non-IID Data: A Surveycited by 345
  11. 2020Think Locally, Act Globally: Federated Learning with Local and Global Representationscited by 322
  12. 2018Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Datacited by 242
26 more
  1. 2019Model Pruning Enables Efficient Federated Learning on Edge Devicescited by 219
  2. 2021Personalized Federated Learning using Hypernetworkscited by 210
  3. 2021FedKD: Communication Efficient Federated Learning via Knowledge Distillationcited by 185
  4. 2021FedBABU: Towards Enhanced Representation for Federated Image Classificationcited by 180
  5. 2020Distillation-Based Semi-Supervised Federated Learning for Communication-Efficient Collaborative Training with Non-IID Private Datacited by 125
  6. 2022Federated Learning with Partial Model Personalizationcited by 114
  7. 2021Parameterized Knowledge Transfer for Personalized Federated Learningcited by 108
  8. 2019Cronus: Robust and Heterogeneous Collaborative Learning with Black-Box Knowledge Transfercited by 91
  9. 2022Heterogeneous Ensemble Knowledge Transfer for Training Large Models in Federated Learningcited by 81
  10. 2020Practical One-Shot Federated Learning for Cross-Silo Settingcited by 76
  11. 2020Federated Mutual Learningcited by 70
  12. 2021FedAUX: Leveraging Unlabeled Auxiliary Data in Federated Learningcited by 67
  13. 2023FedGH: Heterogeneous Federated Learning with Generalized Global Headercited by 56
  14. 2022Federated Graph Neural Networks: Overview, Techniques and Challengescited by 52
  15. 2021FedGEMS: Federated Learning of Larger Server Models via Selective Knowledge Fusioncited by 49
  16. 2019Wireless Federated Distillation for Distributed Edge Learning with Heterogeneous Datacited by 39
  17. 2021FedZKT: Zero-Shot Knowledge Transfer towards Resource-Constrained Federated Learning with Heterogeneous On-Device Modelscited by 31
  18. 2022Architecture Agnostic Federated Learning for Neural Networkscited by 30
  19. 2021FedMatch: Federated Learning Over Heterogeneous Question Answering Datacited by 23
  20. 2022FedClassAvg: Local Representation Learning for Personalized Federated Learning on Heterogeneous Neural Networkscited by 23
  21. 2022Adaptive Memory Networks with Self-supervised Learning for Unsupervised Anomaly Detectioncited by 18
  22. 2020Cooperative Learning via Federated Distillation over Fading Channelscited by 16
  23. 2022Completely Heterogeneous Federated Learningcited by 9
  24. 2023pFedES: Model Heterogeneous Personalized Federated Learning with Feature Extractor Sharingcited by 9
  25. 2020Lottery Hypothesis based Unsupervised Pre-training for Model Compression in Federated Learningcited by 5
  26. 2023A Survey of Historical Learning: Learning Models with Learning Historycited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 6; 2026: 2.

10 papers.

  1. 2024Federated Model Heterogeneous Matryoshka Representation Learningcited by 21
  2. 2025Class-wise Balancing Data Replay for Federated Class-Incremental Learningcited by 9
  3. 2025Federated Out-of-Distribution Generalization: A Causal Augmentation Viewcited by 4
  4. 2024pFedAFM: Adaptive Feature Mixture for Batch-Level Personalization in Heterogeneous Federated Learningcited by 3
  5. 2025Efficient Federated Learning with Timely Update Disseminationcited by 2
  6. 2025FedSKD: Aggregation-free Model-heterogeneous Federated Learning via Multi-dimensional Similarity Knowledge Distillation for Medical Image Classificationcited by 1
  7. 2025Advances and Challenges in Semantic Textual Similarity: A Comprehensive Surveycited by 1
  8. 2025Towards Initialization-Agnostic Clustering with Iterative Adaptive Resonance Theorycited by 0
  9. 2026From Coordinate Matching to Structural Alignment: Rethinking Prototype Alignment in Heterogeneous Federated Learningcited by 0
  10. 2026vFedProtoQNAS: Prototype-Guided Personalized Quantum Neural Architecture Search for Virtual Federated Learningcited by 0