# Adaptive Bayesian Partner Selection for Federated Clinical Centers

arXiv: https://arxiv.org/abs/2609.16446 · HTML: https://mlsanity.com/paper/2609.16446/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 44 references that are in the map.
- First posted on arXiv 15 Sep 2026.

## Builds on (most cited first, 23 of 23)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale](https://mlsanity.com/paper/2208.07339/) (2022)
- [Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification](https://mlsanity.com/paper/1909.06335/) (2019)
- [Model-Contrastive Federated Learning](https://mlsanity.com/paper/2103.16257/) (2021)
- [Data Shapley: Equitable Valuation of Data for Machine Learning](https://mlsanity.com/paper/1904.02868/) (2019)
- [Federated Learning Based on Dynamic Regularization](https://mlsanity.com/paper/2111.04263/) (2021)
- [Federated Learning with Personalization Layers](https://mlsanity.com/paper/1912.00818/) (2019)
- [Soft-DTW: a Differentiable Loss Function for Time-Series](https://mlsanity.com/paper/1703.01541/) (2017)
- [A Study of BFLOAT16 for Deep Learning Training](https://mlsanity.com/paper/1905.12322/) (2019)
- [FedKD: Communication Efficient Federated Learning via Knowledge Distillation](https://mlsanity.com/paper/2108.13323/) (2021)
- [BrainTorrent: A Peer-to-Peer Environment for Decentralized Federated Learning](https://mlsanity.com/paper/1905.06731/) (2019)
- [Multi-Armed Bandit Based Client Scheduling for Federated Learning](https://mlsanity.com/paper/2007.02315/) (2020)
- [From Challenges and Pitfalls to Recommendations and Opportunities: Implementing Federated Learning in Healthcare](https://mlsanity.com/paper/2409.09727/) (2024)
- [Backdoor Attacks in Peer-to-Peer Federated Learning](https://mlsanity.com/paper/2301.09732/) (2023)
- [Greedy Shapley Client Selection for Communication-Efficient Federated Learning](https://mlsanity.com/paper/2312.09108/) (2023)
- [Securing Federated Learning against Overwhelming Collusive Attackers](https://mlsanity.com/paper/2209.14093/) (2022)
- [Efficient Node Selection in Private Personalized Decentralized Learning](https://mlsanity.com/paper/2301.12755/) (2023)
- [Tackling Selfish Clients in Federated Learning](https://mlsanity.com/paper/2407.15402/) (2024)
- [Maverick-Aware Shapley Valuation for Client Selection in Federated Learning](https://mlsanity.com/paper/2405.12590/) (2024)
- [FedDiverse: Tackling Data Heterogeneity in Federated Learning with Diversity-Driven Client Selection](https://mlsanity.com/paper/2504.11216/) (2025)
- [Enhancing Federated Survival Analysis through Peer-Driven Client Reputation in Healthcare](https://mlsanity.com/paper/2505.16190/) (2025)
- [Distribution-Controlled Client Selection to Improve Federated Learning Strategies](https://mlsanity.com/paper/2509.20877/) (2025)

## Abstract (arXiv)

Federated learning (FL) in healthcare faces pronounced heterogeneity and temporal concept drift across clinical centers, where evolving patient populations and care practices shift data distributions. Existing approaches rely on persistent global communication, incurring substantial bandwidth overhead while risking negative transfer from poorly aligned peers. We propose Adaptive Bayesian Partner Selection (ABPS), a peer-to-peer framework that governs who collaborates, when, and at what cost. Each center maintains a Beta-Bernoulli posterior over prospective peers' Shapley marginal utility, ranks candidates with an Upper Confidence Bound (UCB) criterion, and forms collaborations through a lightweight propose-reject mechanism, with the option to abstain from communication when no mutually beneficial partner exists. The framework admits a stochastic decision interpretation, yielding finite-sample concentration guarantees and O(kappa log T) regret in partner selection, along with conditions under which intentional isolation is optimal under negative transfer. Lightweight extensions (head personalization, bfloat16 quantized communication, and a tunable active-set size) further improve efficiency, and a goal-aware metadata filter enables institution-specific collaboration strategies. On binary in-hospital mortality prediction over the first 24 hours of an ICU stay, with 230 non-IID clinical centers drawn from MIMIC-IV, the full ABPS-X variant matches the strongest federated baseline (FedDyn, AUROC 0.758) at 0.09x the communication cost of FedAvg, with reduced variability. A diversity-driven configuration activates intentional isolation for a substantial fraction of centers. These results show that adaptive, utility-aware collaboration reduces communication without sacrificing accuracy when centers are numerous and small, offering a scalable paradigm for healthcare FL.