mlsanityData to 14 Oct 2026

Towards Instance-adaptive Inference for Federated Learning

arXiv 2308.06051 ↗First posted 11 Aug 2023cs.LG cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) is a distributed learning paradigm that enables multiple clients to learn a powerful global model by aggregating local training. However, the performance of the global model is often hampered by non-i.i.d. distribution among the clients, requiring extensive efforts to mitigate inter-client data heterogeneity. Going beyond inter-client data heterogeneity, we note that intra-client heterogeneity can also be observed on complex real-world data and seriously deteriorate FL performance. In this paper, we present a novel FL algorithm, i.e., FedIns, to handle intra-client data heterogeneity by enabling instance-adaptive inference in the FL framework. Instead of huge instance-adaptive models, we resort to a parameter-efficient fine-tuning method, i.e., scale and shift deep features (SSF), upon a pre-trained model. Specifically, we first train an SSF pool for each client, and aggregate these SSF pools on the server side, thus still maintaining a low communication cost. To enable instance-adaptive inference, for a given instance, we dynamically find the best-matched SSF subsets from the pool and aggregate them to generate an adaptive SSF specified for the instance, thereby reducing the intra-client as well as the inter-client heterogeneity. Extensive experiments show that our FedIns outperforms state-of-the-art FL algorithms, e.g., a 6.64% improvement against the top-performing method with less than 15% communication cost on Tiny-ImageNet. Our code and models will be publicly released.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 35 of its 44 references that are in the map. First posted on arXiv 11 Aug 2023.

Builds on

35 of 44 references.

References · 35

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  4. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  5. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  6. 2022Visual Prompt Tuningcited by 1,681
  7. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
  8. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,331
  9. 2021ViLT: Vision-and-Language Transformer Without Convolution or Region Supervisioncited by 1,230
  10. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  11. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
  12. 2021Towards a Unified View of Parameter-Efficient Transfer Learningcited by 872
23 more
  1. 2021Model-Contrastive Federated Learningcited by 766
  2. 2020It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learnerscited by 669
  3. 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
  4. 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 568
  5. 2021Compacter: Efficient Low-Rank Hypercomplex Adapter Layerscited by 460
  6. 2019Federated Learning in Mobile Edge Networks: A Comprehensive Surveycited by 408
  7. 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 387
  8. 2020HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clientscited by 337
  9. 2021Pre-Trained Models: Past, Present and Futurecited by 319
  10. 2022Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuningcited by 294
  11. 2022FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correctioncited by 181
  12. 2021Local Learning Matters: Rethinking Data Heterogeneity in Federated Learningcited by 114
  13. 2021Preservation of the Global Knowledge by Not-True Distillation in Federated Learningcited by 87
  14. 2021Task Transformer Network for Joint MRI Reconstruction and Super-Resolutioncited by 58
  15. 2022Pro-tuning: Unified Prompt Tuning for Vision Taskscited by 53
  16. 2023Learning Federated Visual Prompt in Null Space for MRI Reconstructioncited by 40
  17. 2019Blending-target Domain Adaptation by Adversarial Meta-Adaptation Networkscited by 37
  18. 2021Zoo-Tuning: Adaptive Transfer from a Zoo of Modelscited by 35
  19. 2021Specificity-Preserving Federated Learning for MR Image Reconstructioncited by 35
  20. 2022Acceleration of Federated Learning with Alleviated Forgetting in Local Trainingcited by 29
  21. 2022Learning Instance-Specific Adaptation for Cross-Domain Segmentationcited by 13
  22. 2022Addressing Heterogeneity in Federated Learning via Distributional Transformationcited by 6
  23. 2022Prompt-driven efficient Open-set Semi-supervised Learningcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 2; 2026: 1.

7 papers.

  1. 2023FedRA: A Random Allocation Strategy for Federated Tuning to Unleash the Power of Heterogeneous Clientscited by 19
  2. 2023CLIP-guided Federated Learning on Heterogeneous and Long-Tailed Datacited by 9
  3. 2025Robust Asymmetric Heterogeneous Federated Learning with Corrupted Clientscited by 5
  4. 2024Feature Diversification and Adaptation for Federated Domain Generalizationcited by 4
  5. 2024MLLM-LLaVA-FL: Multimodal Large Language Model Assisted Federated Learningcited by 3
  6. 2025Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalizationcited by 0
  7. 2026From Data Heterogeneity to Convergence: A Data-Centric Review of Federated Learningcited by 0