# How to Collaborate: Towards Maximizing the Generalization Performance in Cross-Silo Federated Learning

arXiv: https://arxiv.org/abs/2401.13236 · HTML: https://mlsanity.com/paper/2401.13236/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 68 references that are in the map.
- First posted on arXiv 24 Jan 2024.

## Builds on (most cited first, 30 of 39)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Optimization Methods for Large-Scale Machine Learning](https://mlsanity.com/paper/1606.04838/) (2016)
- [FedBN: Federated Learning on Non-IID Features via Local Batch Normalization](https://mlsanity.com/paper/2102.07623/) (2021)
- [Federated Learning on Non-IID Data Silos: An Experimental Study](https://mlsanity.com/paper/2102.02079/) (2021)
- [Federated Learning with Personalization Layers](https://mlsanity.com/paper/1912.00818/) (2019)
- [Dataset Condensation with Gradient Matching](https://mlsanity.com/paper/2006.05929/) (2020)
- [An Efficient Framework for Clustered Federated Learning](https://mlsanity.com/paper/2006.04088/) (2020)
- [Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraints](https://mlsanity.com/paper/1910.01991/) (2019)
- [Towards Personalized Federated Learning](https://mlsanity.com/paper/2103.00710/) (2021)
- [Agnostic Federated Learning](https://mlsanity.com/paper/1902.00146/) (2019)
- [Personalized Cross-Silo Federated Learning on Non-IID Data](https://mlsanity.com/paper/2007.03797/) (2020)
- [Gradient Matching for Domain Generalization](https://mlsanity.com/paper/2104.09937/) (2021)
- [Salvaging Federated Learning by Local Adaptation](https://mlsanity.com/paper/2002.04758/) (2020)
- [Federated Learning with Partial Model Personalization](https://mlsanity.com/paper/2204.03809/) (2022)
- [Federated Learning over Wireless Networks: Convergence Analysis and Resource Allocation](https://mlsanity.com/paper/1910.13067/) (2019)
- [Convergence Time Optimization for Federated Learning over Wireless Networks](https://mlsanity.com/paper/2001.07845/) (2020)
- [What Do We Mean by Generalization in Federated Learning?](https://mlsanity.com/paper/2110.14216/) (2021)
- [Model-sharing Games: Analyzing Federated Learning Under Voluntary Participation](https://mlsanity.com/paper/2010.00753/) (2020)
- [Generalization bounds for deep convolutional neural networks](https://mlsanity.com/paper/1905.12600/) (2019)
- [Federated Learning over Wireless Device-to-Device Networks: Algorithms and Convergence Analysis](https://mlsanity.com/paper/2101.12704/) (2021)
- [A Unified Analysis of Federated Learning with Arbitrary Client Participation](https://mlsanity.com/paper/2205.13648/) (2022)
- [Optimality and Stability in Federated Learning: A Game-theoretic Approach](https://mlsanity.com/paper/2106.09580/) (2021)
- [An Incentive Mechanism for Federated Learning in Wireless Cellular network: An Auction Approach](https://mlsanity.com/paper/2009.10269/) (2020)
- [One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning](https://mlsanity.com/paper/2103.03228/) (2021)
- [Cross-Silo Federated Learning: Challenges and Opportunities](https://mlsanity.com/paper/2206.12949/) (2022)
- [Dynamic Clustering in Federated Learning](https://mlsanity.com/paper/2012.03788/) (2020)
- [Fairness and Accuracy in Federated Learning](https://mlsanity.com/paper/2012.10069/) (2020)

## Built on by (most cited first, 2 of 2)

- [pFedWN: A Personalized Federated Learning Framework for D2D Wireless Networks with Heterogeneous Data](https://mlsanity.com/paper/2501.09822/) (2025)
- [Friends in Unexpected Places: Enhancing Local Fairness in Federated Learning through Clustering](https://mlsanity.com/paper/2407.19331/) (2024)

## Abstract (arXiv)

Federated learning (FL) has attracted vivid attention as a privacy-preserving distributed learning framework. In this work, we focus on cross-silo FL, where clients become the model owners after training and are only concerned about the model's generalization performance on their local data. Due to the data heterogeneity issue, asking all the clients to join a single FL training process may result in model performance degradation. To investigate the effectiveness of collaboration, we first derive a generalization bound for each client when collaborating with others or when training independently. We show that the generalization performance of a client can be improved only by collaborating with other clients that have more training data and similar data distribution. Our analysis allows us to formulate a client utility maximization problem by partitioning clients into multiple collaborating groups. A hierarchical clustering-based collaborative training (HCCT) scheme is then proposed, which does not need to fix in advance the number of groups. We further analyze the convergence of HCCT for general non-convex loss functions which unveils the effect of data similarity among clients. Extensive simulations show that HCCT achieves better generalization performance than baseline schemes, whereas it degenerates to independent training and conventional FL in specific scenarios.