# Salvaging Federated Learning by Local Adaptation

arXiv: https://arxiv.org/abs/2002.04758 · HTML: https://mlsanity.com/paper/2002.04758/

## Key facts

- Cited by 142 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Feb 2020.

## Built on by (most cited first, 30 of 142)

- [Exploiting Shared Representations for Personalized Federated Learning](https://mlsanity.com/paper/2102.07078/) (2021)
- [Federated Learning on Non-IID Data: A Survey](https://mlsanity.com/paper/2106.06843/) (2021)
- [A Field Guide to Federated Optimization](https://mlsanity.com/paper/2107.06917/) (2021)
- [Heterogeneous Federated Learning: State-of-the-art and Research Challenges](https://mlsanity.com/paper/2307.10616/) (2023)
- [Federated Learning for Open Banking](https://mlsanity.com/paper/2108.10749/) (2021)
- [When the Curious Abandon Honesty: Federated Learning Is Not Private](https://mlsanity.com/paper/2112.02918/) (2021)
- [Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learning](https://mlsanity.com/paper/2108.10241/) (2021)
- [Parameterized Knowledge Transfer for Personalized Federated Learning](https://mlsanity.com/paper/2111.02862/) (2021)
- [Federated Reconstruction: Partially Local Federated Learning](https://mlsanity.com/paper/2102.03448/) (2021)
- [FedCLIP: Fast Generalization and Personalization for CLIP in Federated Learning](https://mlsanity.com/paper/2302.13485/) (2023)
- [Eluding Secure Aggregation in Federated Learning via Model Inconsistency](https://mlsanity.com/paper/2111.07380/) (2021)
- [What Do We Mean by Generalization in Federated Learning?](https://mlsanity.com/paper/2110.14216/) (2021)
- [Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing](https://mlsanity.com/paper/2106.04502/) (2021)
- [Personalized Federated Learning through Local Memorization](https://mlsanity.com/paper/2111.09360/) (2021)
- [FedAvg with Fine Tuning: Local Updates Lead to Representation Learning](https://mlsanity.com/paper/2205.13692/) (2022)
- [Federated Continual Learning via Knowledge Fusion: A Survey](https://mlsanity.com/paper/2312.16475/) (2023)
- [Federated Multi-Target Domain Adaptation](https://mlsanity.com/paper/2108.07792/) (2021)
- [Recent Advances on Federated Learning: A Systematic Survey](https://mlsanity.com/paper/2301.01299/) (2023)
- [Optimality and Stability in Federated Learning: A Game-theoretic Approach](https://mlsanity.com/paper/2106.09580/) (2021)
- [Test-Time Robust Personalization for Federated Learning](https://mlsanity.com/paper/2205.10920/) (2022)
- [MetaFed: Federated Learning among Federations with Cyclic Knowledge Distillation for Personalized Healthcare](https://mlsanity.com/paper/2206.08516/) (2022)
- [On Privacy and Personalization in Cross-Silo Federated Learning](https://mlsanity.com/paper/2206.07902/) (2022)
- [CD2-pFed: Cyclic Distillation-guided Channel Decoupling for Model Personalization in Federated Learning](https://mlsanity.com/paper/2204.03880/) (2022)
- [Federated Learning for Healthcare Domain - Pipeline, Applications and Challenges](https://mlsanity.com/paper/2211.07893/) (2022)
- [FedCV: A Federated Learning Framework for Diverse Computer Vision Tasks](https://mlsanity.com/paper/2111.11066/) (2021)
- [Motley: Benchmarking Heterogeneity and Personalization in Federated Learning](https://mlsanity.com/paper/2206.09262/) (2022)
- [Architecture Agnostic Federated Learning for Neural Networks](https://mlsanity.com/paper/2202.07757/) (2022)
- [Personalizing Federated Medical Image Segmentation via Local Calibration](https://mlsanity.com/paper/2207.04655/) (2022)
- [Personalized Federated Learning by Structured and Unstructured Pruning under Data Heterogeneity](https://mlsanity.com/paper/2105.00562/) (2021)
- [Personalized Federated Learning with Adaptive Batchnorm for Healthcare](https://mlsanity.com/paper/2112.00734/) (2021)

## Abstract (arXiv)

Federated learning (FL) is a heavily promoted approach for training ML models on sensitive data, e.g., text typed by users on their smartphones. FL is expressly designed for training on data that are unbalanced and non-iid across the participants. To ensure privacy and integrity of the fedeated model, latest FL approaches use differential privacy or robust aggregation. We look at FL from the local viewpoint of an individual participant and ask: (1) do participants have an incentive to participate in FL? (2) how can participants individually improve the quality of their local models, without re-designing the FL framework and/or involving other participants? First, we show that on standard tasks such as next-word prediction, many participants gain no benefit from FL because the federated model is less accurate on their data than the models they can train locally on their own. Second, we show that differential privacy and robust aggregation make this problem worse by further destroying the accuracy of the federated model for many participants. Then, we evaluate three techniques for local adaptation of federated models: fine-tuning, multi-task learning, and knowledge distillation. We analyze where each is applicable and demonstrate that all participants benefit from local adaptation. Participants whose local models are poor obtain big accuracy improvements over conventional FL. Participants whose local models are better than the federated modeltextemdash and who have no incentive to participate in FL todaytextemdash improve less, but sufficiently to make the adapted federated model better than their local models.