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

• URL: http://arxiv.org/abs/2608.15639v2
• Date: Thu, 20 Aug 2026 05:39:47 GMT
• Title: When Is Shallow Enough? Adaptive Split Federated Learning with Client-Specific Sufficiency Estimation
• Abstract summary: Under client heterogeneity, the conventional static split strategy may be suboptimal.<n>We propose textscFedSGA, a textbfSufficiency-textbfGuided textbfAdaptive split textbfFederated learning framework.
• Score: 8.3131553967982
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: \textit{Split 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 \textsc{FedSGA}, a \textbf{S}ufficiency-\textbf{G}uided \textbf{A}daptive split \textbf{Fed}erated 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 \textsc{FedSGA} in improving model performance compared with state-of-the-art methods while reducing unnecessary client-side computation.

Related papers

• BESplit: Bias-Compensated Split Federated Learning with Evidential Aggregation [2.5015678499211407]
  Split Federated Learning (SFL) enables privacy-preserving collaborative training by partitioning models between clients and a server.<n>Under non-IID data distributions, SFL often suffers from biased optimization and unstable convergence.<n>We propose BESplit, an architecture-aware framework that exploits the intrinsic structure of SFL to mitigate non-IID effects.
  arXiv  Detail & Related papers  (2026-05-17T15:42:33Z)
• Enhancing Federated Quadruplet Learning: Stochastic Client Selection and Embedding Stability Analysis [2.298932494750101]
  Federated Learning (FL) enables decentralised model training across distributed clients without requiring data centralisation.<n>We propose FedQuad, a novel method that explicitly enforces minimising intra-class representations while enabling inter-class splits across clients.
  arXiv  Detail & Related papers  (2026-05-08T15:34:41Z)
• Replacing Parameters with Preferences: Federated Alignment of Heterogeneous Vision-Language Models [63.70401095689976]
  Vision-Language Models (VLMs) have broad potential in privacy-sensitive domains such as healthcare and finance.<n>We propose MoR, a federated alignment framework that combines GRPO with Mixture-of-Rewards for heterogeneousVLMs.<n>MoR consistently outperforms federated alignment baselines in generalization and cross-client adaptability.
  arXiv  Detail & Related papers  (2026-05-05T07:02:50Z)
• Client-Centric Federated Adaptive Optimization [78.30827455292827]
  Federated Learning (FL) is a distributed learning paradigm where clients collaboratively train a model while keeping their own data private.<n>We propose Federated-Centric Adaptive Optimization, which is a class of novel federated optimization approaches.
  arXiv  Detail & Related papers  (2025-01-17T04:00:50Z)
• Asynchronous Federated Stochastic Optimization for Heterogeneous Objectives Under Arbitrary Delays [1.9766522384767224]
  underlineAsynchunderlineRonous underlineExact underlineAveraging (textscAREA)<n>textscAREA communicates model residuals rather than gradient estimates, reducing exposure to gradient inversion.<n>We are first to obtain rates that scale with the average client update frequency rather than the minimum or maximum, indicating increased robustness to outliers.
  arXiv  Detail & Related papers  (2024-05-16T14:22:49Z)
• Personalized Federated Learning via Sequential Layer Expansion in Representation Learning [0.0]
  Federated learning ensures the privacy of clients by conducting distributed training on individual client devices and sharing only the model weights with a central server. We propose a new representation learning-based approach that suggests decoupling the entire deep learning model into more densely divided parts with the application of suitable scheduling methods.
  arXiv  Detail & Related papers  (2024-04-27T06:37:19Z)
• Effectively Heterogeneous Federated Learning: A Pairing and Split Learning Based Approach [16.093068118849246]
  This paper presents a novel split federated learning (SFL) framework that pairs clients with different computational resources. A greedy algorithm is proposed by reconstructing the optimization of training latency as a graph edge selection problem. Simulation results show the proposed method can significantly improve the FL training speed and achieve high performance.
  arXiv  Detail & Related papers  (2023-08-26T11:10:54Z)
• Towards Instance-adaptive Inference for Federated Learning [80.38701896056828]
  Federated learning (FL) is a distributed learning paradigm that enables multiple clients to learn a powerful global model by aggregating local training. In this paper, we present a novel FL algorithm, i.e., FedIns, to handle intra-client data heterogeneity by enabling instance-adaptive inference in the FL framework. Our experiments show that our FedIns outperforms state-of-the-art FL algorithms, e.g., a 6.64% improvement against the top-performing method with less than 15% communication cost on Tiny-ImageNet.
  arXiv  Detail & Related papers  (2023-08-11T09:58:47Z)
• Provably Personalized and Robust Federated Learning [47.50663360022456]
  We propose simple algorithms which identify clusters of similar clients and train a personalized modelper-cluster. The convergence rates of our algorithmsally match those obtained if we knew the true underlying clustering of the clients and are provably robust in the Byzantine setting.
  arXiv  Detail & Related papers  (2023-06-14T09:37:39Z)
• Personalized Federated Learning under Mixture of Distributions [98.25444470990107]
  We propose a novel approach to Personalized Federated Learning (PFL), which utilizes Gaussian mixture models (GMM) to fit the input data distributions across diverse clients. FedGMM possesses an additional advantage of adapting to new clients with minimal overhead, and it also enables uncertainty quantification. Empirical evaluations on synthetic and benchmark datasets demonstrate the superior performance of our method in both PFL classification and novel sample detection.
  arXiv  Detail & Related papers  (2023-05-01T20:04:46Z)
• FilFL: Client Filtering for Optimized Client Participation in Federated Learning [71.46173076298957]
  Federated learning enables clients to collaboratively train a model without exchanging local data. Clients participating in the training process significantly impact the convergence rate, learning efficiency, and model generalization. We propose a novel approach, client filtering, to improve model generalization and optimize client participation and training.
  arXiv  Detail & Related papers  (2023-02-13T18:55:31Z)
• Efficient Distribution Similarity Identification in Clustered Federated Learning via Principal Angles Between Client Data Subspaces [59.33965805898736]
  Clustered learning has been shown to produce promising results by grouping clients into clusters. Existing FL algorithms are essentially trying to group clients together with similar distributions. Prior FL algorithms attempt similarities indirectly during training.
  arXiv  Detail & Related papers  (2022-09-21T17:37:54Z)
• AdaSplit: Adaptive Trade-offs for Resource-constrained Distributed Deep Learning [18.3841463794885]
  Split learning (SL) reduces client compute load by splitting the model training between client and server. AdaSplit enables efficiently scaling SL to low resource scenarios by reducing bandwidth consumption and improving performance across heterogeneous clients.
  arXiv  Detail & Related papers  (2021-12-02T23:33:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.