# When Is Shallow Enough? Adaptive Split Federated Learning with Client-Specific Sufficiency Estimation

arXiv: https://arxiv.org/abs/2608.15639 · HTML: https://mlsanity.com/paper/2608.15639/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 59 references that are in the map.
- First posted on arXiv 16 Aug 2026.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [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)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [SplitFed: When Federated Learning Meets Split Learning](https://mlsanity.com/paper/2004.12088/) (2020)
- [AdaptSFL: Adaptive Split Federated Learning in Resource-constrained Edge Networks](https://mlsanity.com/paper/2403.13101/) (2024)
- [FedGH: Heterogeneous Federated Learning with Generalized Global Header](https://mlsanity.com/paper/2303.13137/) (2023)
- [Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning](https://mlsanity.com/paper/2210.02326/) (2022)
- [Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversity](https://mlsanity.com/paper/2405.16585/) (2024)
- [Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data Domains](https://mlsanity.com/paper/2403.09048/) (2024)
- [MergeSFL: Split Federated Learning with Feature Merging and Batch Size Regulation](https://mlsanity.com/paper/2311.13348/) (2023)
- [FedCiR: Client-Invariant Representation Learning for Federated Non-IID Features](https://mlsanity.com/paper/2308.15786/) (2023)
- [Multi-Source Collaborative Gradient Discrepancy Minimization for Federated Domain Generalization](https://mlsanity.com/paper/2401.10272/) (2024)
- [ParallelSFL: A Novel Split Federated Learning Framework Tackling Heterogeneity Issues](https://mlsanity.com/paper/2410.01256/) (2024)
- [Federated Learning with Domain Shift Eraser](https://mlsanity.com/paper/2503.13063/) (2025)
- [Towards Straggler-Resilient Split Federated Learning: An Unbalanced Update Approach](https://mlsanity.com/paper/2510.21155/) (2025)
- [Multi-Source to Multi-Target Decentralized Federated Domain Adaptation](https://mlsanity.com/paper/2304.12422/) (2023)
- [UFDA: Universal Federated Domain Adaptation with Practical Assumptions](https://mlsanity.com/paper/2311.15570/) (2023)
- [R-SFLLM: Jamming Resilient Framework for Split Federated Learning with Large Language Models](https://mlsanity.com/paper/2407.11654/) (2024)
- [FedAlign: Federated Domain Generalization with Cross-Client Feature Alignment](https://mlsanity.com/paper/2501.15486/) (2025)
- [Robust and Communication-Efficient Federated Domain Adaptation via Random Features](https://mlsanity.com/paper/2311.04686/) (2023)
- [Breaking the Memory Wall for Heterogeneous Federated Learning via Model Splitting](https://mlsanity.com/paper/2410.11577/) (2024)
- [Ampere: Communication-Efficient and High-Accuracy Split Federated Learning](https://mlsanity.com/paper/2507.07130/) (2025)
- [SplitFT: An Adaptive Federated Split Learning System For LLMs Fine-Tuning](https://mlsanity.com/paper/2604.26388/) (2026)

## Abstract (arXiv)

textitSplit Federated Learning (SFL) enables distributed model training by splitting networks between the server and clients. However, under client heterogeneity, the conventional static split strategy may be suboptimal because clients can differ in data distributions, adaptation dynamics, and representation learning progress, making a single split point insufficient to accommodate client-specific training states. In this paper, we propose textscFedSGA, a Sufficiency-Guided Adaptive split Federated learning framework that addresses this question through client-specific shallow sufficiency estimation. First, we introduce a client-specific adaptation channel based on private prompt tokens, which tracks local adaptation dynamics separately from the shared backbone and provides a lightweight signal for detecting whether client adaptation remains active. To further avoid repeated online probing over multiple candidate depths, we design a shallow sufficiency estimator that combines cross-client semantic alignment, temporal interface stability, and prompt-state variation to estimate whether the shallowest split is already sufficient. Finally, we introduce a split-compatible interface harmonization module that projects activations from different split depths into a shared semantic space, improving the comparability of heterogeneous client interfaces before server-side prediction. Extensive experiments on multiple heterogeneous benchmarks demonstrate the effectiveness of textscFedSGA in improving model performance compared with state-of-the-art methods while reducing unnecessary client-side computation.