# BESplit: Bias-Compensated Split Federated Learning with Evidential Aggregation

arXiv: https://arxiv.org/abs/2605.17508 · HTML: https://mlsanity.com/paper/2605.17508/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 54 references that are in the map.
- First posted on arXiv 17 May 2026.

## Builds on (most cited first, 30 of 32)

- [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)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images](https://mlsanity.com/paper/1412.1897/) (2014)
- [Evidential Deep Learning to Quantify Classification Uncertainty](https://mlsanity.com/paper/1806.01768/) (2018)
- [Federated Learning Based on Dynamic Regularization](https://mlsanity.com/paper/2111.04263/) (2021)
- [SplitFed: When Federated Learning Meets Split Learning](https://mlsanity.com/paper/2004.12088/) (2020)
- [Trusted Multi-View Classification with Dynamic Evidential Fusion](https://mlsanity.com/paper/2204.11423/) (2022)
- [Compact Language Models via Pruning and Knowledge Distillation](https://mlsanity.com/paper/2407.14679/) (2024)
- [FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings](https://mlsanity.com/paper/2210.04620/) (2022)
- [Logit Standardization in Knowledge Distillation](https://mlsanity.com/paper/2403.01427/) (2024)
- [Stochastic Controlled Averaging for Federated Learning with Communication Compression](https://mlsanity.com/paper/2308.08165/) (2023)
- [Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey](https://mlsanity.com/paper/2503.15850/) (2025)
- [Reliable Conflictive Multi-View Learning](https://mlsanity.com/paper/2402.16897/) (2024)
- [Hierarchical Split Federated Learning: Convergence Analysis and System Optimization](https://mlsanity.com/paper/2412.07197/) (2024)
- [Post-hoc Uncertainty Learning using a Dirichlet Meta-Model](https://mlsanity.com/paper/2212.07359/) (2022)
- [Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain Shifts](https://mlsanity.com/paper/2312.02567/) (2023)
- [Dirichlet-based Uncertainty Calibration for Active Domain Adaptation](https://mlsanity.com/paper/2302.13824/) (2023)
- [Frequency Attention for Knowledge Distillation](https://mlsanity.com/paper/2403.05894/) (2024)
- [Small Scale Data-Free Knowledge Distillation](https://mlsanity.com/paper/2406.07876/) (2024)
- [Select and Distill: Selective Dual-Teacher Knowledge Transfer for Continual Learning on Vision-Language Models](https://mlsanity.com/paper/2403.09296/) (2024)
- [A Simple Data Augmentation for Feature Distribution Skewed Federated Learning](https://mlsanity.com/paper/2306.09363/) (2023)
- [HASFL: Heterogeneity-aware Split Federated Learning over Edge Computing Systems](https://mlsanity.com/paper/2506.08426/) (2025)
- [Re-thinking Federated Active Learning based on Inter-class Diversity](https://mlsanity.com/paper/2303.12317/) (2023)
- [MergeSFL: Split Federated Learning with Feature Merging and Batch Size Regulation](https://mlsanity.com/paper/2311.13348/) (2023)
- [ParallelSFL: A Novel Split Federated Learning Framework Tackling Heterogeneity Issues](https://mlsanity.com/paper/2410.01256/) (2024)
- [Greedy Algorithm for Multiway Matching with Bounded Regret](https://mlsanity.com/paper/2112.04622/) (2021)
- [Federated Learning with Domain Shift Eraser](https://mlsanity.com/paper/2503.13063/) (2025)
- [Split Learning without Local Weight Sharing to Enhance Client-side Data Privacy](https://mlsanity.com/paper/2212.00250/) (2022)
- [Maximizing Uncertainty for Federated learning via Bayesian Optimisation-based Model Poisoning](https://mlsanity.com/paper/2501.08002/) (2025)

## Abstract (arXiv)

Split Federated Learning (SFL) enables privacy-preserving collaborative training by partitioning models between clients and a server. However, under non-IID data distributions, SFL often suffers from biased optimization and unstable convergence, while existing solutions largely adapt techniques from conventional federated learning. In this work, we observe that the split architecture of SFL inherently alters how client information is represented and coordinated, opening opportunities for bias compensation beyond parameter-level aggregation. Based on this insight, we propose BESplit, an architecture-aware framework that exploits the intrinsic structure of SFL to mitigate non-IID effects. First, to prevent biased local data from dominating global updates, we introduce Evidential Aggregation (EA) to perform fine-grained reweighting of client contributions based on evidential uncertainty. Second, to further reduce distributional skew, we develop Bias-Compensated Collaboration (BCC) to align split-layer representations by pairing complementary clients. Finally, Dual-Teacher Distillation (DTD) is incorporated to synchronize knowledge between decoupled client and server models, enabling independent local inference. Extensive experiments on five benchmark datasets demonstrate that BESplit consistently outperforms state-of-the-art methods in accuracy, convergence stability, and computational efficiency under diverse non-IID settings.