mlsanityData to 14 Oct 2026

FedAPA: Server-side Gradient-Based Adaptive Personalized Aggregation for Federated Learning on Heterogeneous Data

arXiv 2502.07456 ↗First posted 11 Feb 2025cs.LG cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Personalized federated learning (PFL) tailors models to clients' unique data distributions while preserving privacy. However, existing aggregation-weight-based PFL methods often struggle with heterogeneous data, facing challenges in accuracy, computational efficiency, and communication overhead. We propose FedAPA, a novel PFL method featuring a server-side, gradient-based adaptive aggregation strategy to generate personalized models, by updating aggregation weights based on gradients of client-parameter changes with respect to the aggregation weights in a centralized manner. FedAPA guarantees theoretical convergence and achieves superior accuracy and computational efficiency compared to 10 PFL competitors across three datasets, with competitive communication overhead.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 46 of its 72 references that are in the map. First posted on arXiv 11 Feb 2025.

Builds on

46 of 72 references.

References · 46

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2016HyperNetworkscited by 1,027
  3. 2021Model-Contrastive Federated Learningcited by 766
  4. 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 387
  5. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 352
  6. 2020Personalized Cross-Silo Federated Learning on Non-IID Datacited by 283
  7. 2021Personalized Federated Learning using Hypernetworkscited by 212
  8. 2022FedALA: Adaptive Local Aggregation for Personalized Federated Learningcited by 122
  9. 2023Personalized Federated Learning with Feature Alignment and Classifier Collaborationcited by 97
  10. 2022Layer-wised Model Aggregation for Personalized Federated Learningcited by 96
  11. 2020Personalized Federated Learning for Intelligent IoT Applications: A Cloud-Edge based Frameworkcited by 59
  12. 2023FedGH: Heterogeneous Federated Learning with Generalized Global Headercited by 56
34 more
  1. 2021Adapt to Adaptation: Learning Personalization for Cross-Silo Federated Learningcited by 53
  2. 2023Eliminating Domain Bias for Federated Learning in Representation Spacecited by 38
  3. 2022Decomposed Soft Prompt Guided Fusion Enhancing for Compositional Zero-Shot Learningcited by 37
  4. 2024DiPrompT: Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learningcited by 32
  5. 2020A Novel Perspective to Zero-shot Learning: Towards an Alignment of Manifold Structures via Semantic Feature Expansioncited by 31
  6. 2023SRCD: Semantic Reasoning with Compound Domains for Single-Domain Generalized Object Detectioncited by 28
  7. 2021Personalized Federated Learning with Contextualized Generalizationcited by 23
  8. 2022CaDM: Codec-aware Diffusion Modeling for Neural-enhanced Video Streamingcited by 23
  9. 2022Towards Unbiased Multi-label Zero-Shot Learning with Pyramid and Semantic Attentioncited by 21
  10. 2024Personalized Federated Domain-Incremental Learning based on Adaptive Knowledge Matchingcited by 21
  11. 2019AMS-SFE: Towards an Alignment of Manifold Structures via Semantic Feature Expansion for Zero-shot Learningcited by 19
  12. 2019Adaptive Adjustment with Semantic Feature Space for Zero-Shot Recognitioncited by 18
  13. 2019Position-Aware Convolutional Networks for Traffic Predictioncited by 18
  14. 2022Exploring Optimal Substructure for Out-of-distribution Generalization via Feature-targeted Model Pruningcited by 17
  15. 2023Data Quality-aware Mixed-precision Quantization via Hybrid Reinforcement Learningcited by 17
  16. 2023DRPT: Disentangled and Recurrent Prompt Tuning for Compositional Zero-Shot Learningcited by 17
  17. 2021Learning Robust Visual-semantic Mapping for Zero-shot Learningcited by 16
  18. 2022Efficient Stein Variational Inference for Reliable Distribution-lossless Network Pruningcited by 16
  19. 2019EE-AE: An Exclusivity Enhanced Unsupervised Feature Learning Approachcited by 15
  20. 2023CNS-Net: Conservative Novelty Synthesizing Network for Malware Recognition in an Open-set Scenariocited by 15
  21. 2023Dissecting Arbitrary-scale Super-resolution Capability from Pre-trained Diffusion Generative Modelscited by 15
  22. 2022Fed-FSNet: Mitigating Non-I.I.D. Federated Learning via Fuzzy Synthesizing Networkcited by 14
  23. 2023Non-Exemplar Online Class-incremental Continual Learning via Dual-prototype Self-augment and Refinementcited by 13
  24. 2023Arena: A Learning-based Synchronization Scheme for Hierarchical Federated Learning--Technical Reportcited by 13
  25. 2023Towards Fairer and More Efficient Federated Learning via Multidimensional Personalized Edge Modelscited by 10
  26. 2023MDENet: Multi-modal Dual-embedding Networks for Malware Open-set Recognitioncited by 10
  27. 2022ProCC: Progressive Cross-primitive Compatibility for Open-World Compositional Zero-Shot Learningcited by 9
  28. 2023GBE-MLZSL: A Group Bi-Enhancement Framework for Multi-Label Zero-Shot Learningcited by 8
  29. 2023FreePIH: Training-Free Painterly Image Harmonization with Diffusion Modelcited by 8
  30. 2023Attribute-Aware Representation Rectification for Generalized Zero-Shot Learningcited by 6
  31. 2024TsCA: On the Semantic Consistency Alignment via Conditional Transport for Compositional Zero-Shot Learningcited by 6
  32. 2024On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Surveycited by 5
  33. 2024Dual Expert Distillation Network for Generalized Zero-Shot Learningcited by 4
  34. 2024Epsilon: Exploring Comprehensive Visual-Semantic Projection for Multi-Label Zero-Shot Learningcited by 3

Built on by

Not cited yet.