# Bold but Cautious: Unlocking the Potential of Personalized Federated Learning through Cautiously Aggressive Collaboration

arXiv: https://arxiv.org/abs/2309.11103 · HTML: https://mlsanity.com/paper/2309.11103/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 41 references that are in the map.
- First posted on arXiv 20 Sep 2023.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification](https://mlsanity.com/paper/1909.06335/) (2019)
- [SNIP: Single-shot Network Pruning based on Connection Sensitivity](https://mlsanity.com/paper/1810.02340/) (2018)
- [Model-Contrastive Federated Learning](https://mlsanity.com/paper/2103.16257/) (2021)
- [Ensemble Distillation for Robust Model Fusion in Federated Learning](https://mlsanity.com/paper/2006.07242/) (2020)
- [Ditto: Fair and Robust Federated Learning Through Personalization](https://mlsanity.com/paper/2012.04221/) (2020)
- [The Future of Digital Health with Federated Learning](https://mlsanity.com/paper/2003.08119/) (2020)
- [Personalized Federated Learning with Moreau Envelopes](https://mlsanity.com/paper/2006.08848/) (2020)
- [FedBN: Federated Learning on Non-IID Features via Local Batch Normalization](https://mlsanity.com/paper/2102.07623/) (2021)
- [Importance Estimation for Neural Network Pruning](https://mlsanity.com/paper/1906.10771/) (2019)
- [Federated Learning with Personalization Layers](https://mlsanity.com/paper/1912.00818/) (2019)
- [Exploiting Shared Representations for Personalized Federated Learning](https://mlsanity.com/paper/2102.07078/) (2021)
- [FedProto: Federated Prototype Learning across Heterogeneous Clients](https://mlsanity.com/paper/2105.00243/) (2021)
- [Personalized Cross-Silo Federated Learning on Non-IID Data](https://mlsanity.com/paper/2007.03797/) (2020)
- [Personalized Federated Learning with First Order Model Optimization](https://mlsanity.com/paper/2012.08565/) (2020)
- [Federated Learning for Open Banking](https://mlsanity.com/paper/2108.10749/) (2021)
- [FedVision: An Online Visual Object Detection Platform Powered by Federated Learning](https://mlsanity.com/paper/2001.06202/) (2020)
- [Federated Learning with Partial Model Personalization](https://mlsanity.com/paper/2204.03809/) (2022)
- [Layer-wised Model Aggregation for Personalized Federated Learning](https://mlsanity.com/paper/2205.03993/) (2022)
- [Adapt to Adaptation: Learning Personalization for Cross-Silo Federated Learning](https://mlsanity.com/paper/2110.08394/) (2021)
- [Efficient Personalized Federated Learning via Sparse Model-Adaptation](https://mlsanity.com/paper/2305.02776/) (2023)
- [Multi-Level Branched Regularization for Federated Learning](https://mlsanity.com/paper/2207.06936/) (2022)
- [Personalized Federated Learning With Graph](https://mlsanity.com/paper/2203.00829/) (2022)
- [Personalized Federated Learning with Contextualized Generalization](https://mlsanity.com/paper/2106.13044/) (2021)
- [PATS: Sensitivity-aware Noisy Learning for Pretrained Language Models](https://mlsanity.com/paper/2210.12403/) (2022)

## Built on by (most cited first, 23 of 23)

- [PFLlib: A Beginner-Friendly and Comprehensive Personalized Federated Learning Library and Benchmark](https://mlsanity.com/paper/2312.04992/) (2023)
- [Decoupling General and Personalized Knowledge in Federated Learning via Additive and Low-Rank Decomposition](https://mlsanity.com/paper/2406.19931/) (2024)
- [S2FGL: Spatial Spectral Federated Graph Learning](https://mlsanity.com/paper/2507.02409/) (2025)
- [Free Lunch for Federated Remote Sensing Target Fine-Grained Classification: A Parameter-Efficient Framework](https://mlsanity.com/paper/2401.01493/) (2024)
- [Federated Distillation for Medical Image Classification: Towards Trustworthy Computer-Aided Diagnosis](https://mlsanity.com/paper/2407.02261/) (2024)
- [Behavioral Anomaly Detection in Distributed Systems via Federated Contrastive Learning](https://mlsanity.com/paper/2506.19246/) (2025)
- [The Diversity Bonus: Learning from Dissimilar Distributed Clients in Personalized Federated Learning](https://mlsanity.com/paper/2407.15464/) (2024)
- [Towards Layer-Wise Personalized Federated Learning: Adaptive Layer Disentanglement via Conflicting Gradients](https://mlsanity.com/paper/2410.02845/) (2024)
- [Tackling Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformation](https://mlsanity.com/paper/2407.16139/) (2024)
- [DualFed: Enjoying both Generalization and Personalization in Federated Learning via Hierachical Representations](https://mlsanity.com/paper/2407.17754/) (2024)
- [Enhancing Visual Representation with Textual Semantics: Textual Semantics-Powered Prototypes for Heterogeneous Federated Learning](https://mlsanity.com/paper/2503.13543/) (2025)
- [Leave it to the Specialist: Repair Sparse LLMs with Sparse Fine-Tuning via Sparsity Evolution](https://mlsanity.com/paper/2505.24037/) (2025)
- [Tackling Resource-Constrained and Data-Heterogeneity in Federated Learning with Double-Weight Sparse Pack](https://mlsanity.com/paper/2601.01840/) (2026)
- [Choice Outweighs Effort: Facilitating Complementary Knowledge Fusion in Federated Learning via Re-calibration and Merit-discrimination](https://mlsanity.com/paper/2508.17954/) (2025)
- [FedBiF: Communication-Efficient Federated Learning via Bits Freezing](https://mlsanity.com/paper/2509.10161/) (2025)
- [Towards Robust Personalized Federated Learning: Vulnerability Assessment and Defense Co-Design](https://mlsanity.com/paper/2606.22782/) (2026)
- [Recovering Global Data Distribution Locally in Federated Learning](https://mlsanity.com/paper/2409.14063/) (2024)
- [Addressing the Collaboration Dilemma in Low-Data Federated Learning via Transient Sparsity](https://mlsanity.com/paper/2506.00932/) (2025)
- [Learning to Collaborate Over Graphs: A Selective Federated Multi-Task Learning Approach](https://mlsanity.com/paper/2506.10102/) (2025)
- [FedPSA: Modeling Behavioral Staleness in Asynchronous Federated Learning](https://mlsanity.com/paper/2602.15337/) (2026)
- [Fed-GAME: Personalized Federated Learning with Graph Attention Mixture-of-Experts For Time-Series Forecasting](https://mlsanity.com/paper/2603.01363/) (2026)
- [From Coordinate Matching to Structural Alignment: Rethinking Prototype Alignment in Heterogeneous Federated Learning](https://mlsanity.com/paper/2605.05959/) (2026)
- [FM2: Unified Federated Foundation Models for Heterogeneous Multimodal Medical Imaging](https://mlsanity.com/paper/2607.13386/) (2026)

## Abstract (arXiv)

Personalized federated learning (PFL) reduces the impact of non-independent and identically distributed (non-IID) data among clients by allowing each client to train a personalized model when collaborating with others. A key question in PFL is to decide which parameters of a client should be localized or shared with others. In current mainstream approaches, all layers that are sensitive to non-IID data (such as classifier layers) are generally personalized. The reasoning behind this approach is understandable, as localizing parameters that are easily influenced by non-IID data can prevent the potential negative effect of collaboration. However, we believe that this approach is too conservative for collaboration. For example, for a certain client, even if its parameters are easily influenced by non-IID data, it can still benefit by sharing these parameters with clients having similar data distribution. This observation emphasizes the importance of considering not only the sensitivity to non-IID data but also the similarity of data distribution when determining which parameters should be localized in PFL. This paper introduces a novel guideline for client collaboration in PFL. Unlike existing approaches that prohibit all collaboration of sensitive parameters, our guideline allows clients to share more parameters with others, leading to improved model performance. Additionally, we propose a new PFL method named FedCAC, which employs a quantitative metric to evaluate each parameter's sensitivity to non-IID data and carefully selects collaborators based on this evaluation. Experimental results demonstrate that FedCAC enables clients to share more parameters with others, resulting in superior performance compared to state-of-the-art methods, particularly in scenarios where clients have diverse distributions.