Research in Collaborative Learning Does Not Serve Cross-Silo Federated Learning in Practice
Not on the map. Why?
Abstract (arXiv)
Cross-silo federated learning (FL) is a promising approach to enable cross-organization collaboration in machine learning model development without directly sharing private data. Despite growing organizational interest driven by data protection regulations such as GDPR and HIPAA, the adoption of cross-silo FL remains limited in practice. In this paper, we conduct an interview study to understand the practical challenges associated with cross-silo FL adoption. With interviews spanning a diverse set of stakeholders such as user organizations, software providers, and academic researchers, we uncover various barriers, from concerns about model performance to questions of incentives and trust between participating organizations. Our study shows that cross-silo FL faces a set of challenges that have yet to be well-captured by existing research in the area and are quite distinct from other forms of federated learning such as cross-device FL. We end with a discussion on future research directions that can help overcome these challenges.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 97 of its 180 references that are in the map. First posted on arXiv 14 Oct 2025.
Builds on
97 of 180 references.
References · 97
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2019Advances and Open Problems in Federated Learningcited by 3,021
- 2018Federated Optimization in Heterogeneous Networkscited by 2,971
- 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
- 2022Editing Models with Task Arithmeticcited by 1,076
- 2019Towards Federated Learning at Scale: System Designcited by 826
- 2018Split learning for health: Distributed deep learning without sharing raw patient datacited by 391
- 2020Personalized Cross-Silo Federated Learning on Non-IID Datacited by 282
- 2018Distributed learning of deep neural network over multiple agentscited by 277
- 2018Applied Federated Learning: Improving Google Keyboard Query Suggestionscited by 202
- 2019Client-Edge-Cloud Hierarchical Federated Learningcited by 202
- 2021Federated Learning with Buffered Asynchronous Aggregationcited by 188
38 more
- 2022Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Modelscited by 187
- 2022Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challengescited by 137
- 2022FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settingscited by 121
- 2024Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLMcited by 106
- 2022Vertical Federated Learning: Concepts, Advances and Challengescited by 104
- 2019Hierarchical Federated Learning Across Heterogeneous Cellular Networkscited by 98
- 2021Asynchronous Federated Learning on Heterogeneous Devices: A Surveycited by 93
- 2021Papaya: Practical, Private, and Scalable Federated Learningcited by 89
- 2023Decentralized Federated Learning: A Survey and Perspectivecited by 86
- 2023Multimodal Federated Learning via Contrastive Representation Ensemblecited by 85
- 2021Federated Evaluation and Tuning for On-Device Personalization: System Design & Applicationscited by 84
- 2019SAFA: a Semi-Asynchronous Protocol for Fast Federated Learning with Low Overheadcited by 82
- 2022NVIDIA FLARE: Federated Learning from Simulation to Real-Worldcited by 78
- 2023Federated Learning for Medical Image Analysis: A Surveycited by 77
- 2020Practical One-Shot Federated Learning for Cross-Silo Settingcited by 76
- 2022Fishing for User Data in Large-Batch Federated Learning via Gradient Magnificationcited by 72
- 2024FDLoRA: Personalized Federated Learning of Large Language Model via Dual LoRA Tuningcited by 57
- 2021Adapt to Adaptation: Learning Personalization for Cross-Silo Federated Learningcited by 53
- 2021Hierarchical Federated Learning with Quantization: Convergence Analysis and System Designcited by 47
- 2022Preserving Privacy in Federated Learning with Ensemble Cross-Domain Knowledge Distillationcited by 45
- 2022Closing the Generalization Gap of Cross-silo Federated Medical Image Segmentationcited by 41
- 2022FedX: Unsupervised Federated Learning with Cross Knowledge Distillationcited by 40
- 2023Generalizable Heterogeneous Federated Cross-Correlation and Instance Similarity Learningcited by 39
- 2022Cross-Silo Federated Learning: Challenges and Opportunitiescited by 38
- 2022Mechanisms that Incentivize Data Sharing in Federated Learningcited by 38
- 2020Throughput-Optimal Topology Design for Cross-Silo Federated Learningcited by 37
- 2020FOCUS: Dealing with Label Quality Disparity in Federated Learningcited by 36
- 2022On Privacy and Personalization in Cross-Silo Federated Learningcited by 36
- 2022Faster Adaptive Federated Learningcited by 35
- 2023Cross-Silo Prototypical Calibration for Federated Learning with Non-IID Datacited by 35
- 2022Federated Learning for Healthcare Domain - Pipeline, Applications and Challengescited by 34
- 2024An Aggregation-Free Federated Learning for Tackling Data Heterogeneitycited by 33
- 2020FedCVT: Semi-supervised Vertical Federated Learning with Cross-view Trainingcited by 32
- 2022Motley: Benchmarking Heterogeneity and Personalization in Federated Learningcited by 31
- 2021End-to-End Speech Recognition from Federated Acoustic Modelscited by 30
- 2021Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Lossescited by 30
- 2023Can Public Large Language Models Help Private Cross-device Federated Learning?cited by 30
- 2021SemiFed: Semi-supervised Federated Learning with Consistency and Pseudo-Labelingcited by 29
50 most cited of 97 All 97 (JSON)
Built on by
Citing papers per year: 2026: 3.
3 papers.