mlsanityData to 14 Oct 2026

Adaptive Bayesian Partner Selection for Federated Clinical Centers

arXiv 2609.16446 ↗First posted 15 Sep 2026cs.LG cs.DCcited by 0

Not on the map. Why?

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.

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

23 of 44 references.

References · 23

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  3. 2022LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scalecited by 906
  4. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 851
  5. 2021Model-Contrastive Federated Learningcited by 766
  6. 2019Data Shapley: Equitable Valuation of Data for Machine Learningcited by 629
  7. 2021Federated Learning Based on Dynamic Regularizationcited by 562
  8. 2019Federated Learning with Personalization Layerscited by 541
  9. 2017Soft-DTW: a Differentiable Loss Function for Time-Seriescited by 271
  10. 2019A Study of BFLOAT16 for Deep Learning Trainingcited by 232
  11. 2021FedKD: Communication Efficient Federated Learning via Knowledge Distillationcited by 187
  12. 2019BrainTorrent: A Peer-to-Peer Environment for Decentralized Federated Learningcited by 117
11 more
  1. 2020Multi-Armed Bandit Based Client Scheduling for Federated Learningcited by 57
  2. 2024From Challenges and Pitfalls to Recommendations and Opportunities: Implementing Federated Learning in Healthcarecited by 16
  3. 2023Backdoor Attacks in Peer-to-Peer Federated Learningcited by 9
  4. 2023Greedy Shapley Client Selection for Communication-Efficient Federated Learningcited by 7
  5. 2022Securing Federated Learning against Overwhelming Collusive Attackerscited by 5
  6. 2023Efficient Node Selection in Private Personalized Decentralized Learningcited by 4
  7. 2024Tackling Selfish Clients in Federated Learningcited by 3
  8. 2024Maverick-Aware Shapley Valuation for Client Selection in Federated Learningcited by 2
  9. 2025FedDiverse: Tackling Data Heterogeneity in Federated Learning with Diversity-Driven Client Selectioncited by 1
  10. 2025Enhancing Federated Survival Analysis through Peer-Driven Client Reputation in Healthcarecited by 1
  11. 2025Distribution-Controlled Client Selection to Improve Federated Learning Strategiescited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Conflict-Aware Client Selection for Multi-Server Federated Learning
  2. 2024Ranking-based Client Selection with Imitation Learning for Efficient Federated Learning
  3. 2022Federated Offline Reinforcement Learning
  4. 2026FedEHR-Agents: Federated Agentic Optimization for Automated EHR Modeling
  5. 2026Hybrid Federated and Split Learning for Privacy Preserving Clinical Prediction and Treatment Optimization
  6. 2026Federated Client Selection under Partial Visibility: A POMDP Approach with Spatio-Temporal Attention
  7. 2025Federated Learning: A Survey on Privacy-Preserving Collaborative Intelligence
  8. 2026Understanding Trajectory Heterogeneity in Federated World Model Learning