mlsanityData to 14 Oct 2026

SDFed: Bridging Local Global Discrepancy via Subspace Refinement and Divergence Control in Federated Prompt Learning

arXiv 2602.08590 ↗First posted 9 Feb 2026cs.LG cs.DBcited by 0

On the map: Multimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP

Abstract (arXiv)

Vision-language pretrained models offer strong transferable representations, yet adapting them in privacy-sensitive multi-party settings is challenging due to the high communication cost of federated optimization and the limited local data on clients. Federated prompt learning mitigates this issue by keeping the VLPM backbone frozen and collaboratively training lightweight prompt parameters. However, existing approaches typically enforce a unified prompt structure and length across clients, which is inadequate under practical client heterogeneity in both data distributions and system resources, and may further introduce conflicts between globally shared and locally optimal knowledge. To address these challenges, we propose SDFed, a heterogeneous federated prompt learning framework that bridges Local-Global Discrepancy via Subspace Refinement and Divergence Control. SDFed maintains a fixed-length global prompt for efficient aggregation while allowing each client to learn a variable-length local prompt to better match its data characteristics and capacity. To mitigate local-global conflicts and facilitate effective knowledge transfer, SDFed introduces a subspace refinement method for local prompts and an information retention and divergence control strategy that preserves key local information while maintaining appropriate separability between global and local representations. Extensive experiments on several datasets demonstrate that SDFed consistently improves performance and robustness in heterogeneous federated settings.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 22 of its 55 references that are in the map. First posted on arXiv 9 Feb 2026.

Builds on

22 of 55 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Federated Learning from Vision-Language Foundation Models: Theoretical Analysis and Method29 Sep
  2. 2024Harmonizing Generalization and Personalization in Federated Prompt Learning16 May

Other references · 20

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  4. 2013Describing Textures in the Wildcited by 2,125
  5. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
  6. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
  7. 2021Model-Contrastive Federated Learningcited by 766
  8. 2018Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoisingcited by 218
  9. 2022FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correctioncited by 181
  10. 2021FedScale: Benchmarking Model and System Performance of Federated Learning at Scalecited by 136
  11. 2022PromptFL: Let Federated Participants Cooperatively Learn Prompts Instead of Models -- Federated Learning in Age of Foundation Modelcited by 134
  12. 2023FedGH: Heterogeneous Federated Learning with Generalized Global Headercited by 56
8 more
  1. 2023Efficient Model Personalization in Federated Learning via Client-Specific Prompt Generationcited by 54
  2. 2024Global and Local Prompts Cooperation via Optimal Transport for Federated Learningcited by 46
  3. 2022Multi-Level Branched Regularization for Federated Learningcited by 34
  4. 2023GPT-FL: Generative Pre-trained Model-Assisted Federated Learningcited by 24
  5. 2023HeteFedRec: Federated Recommender Systems with Model Heterogeneitycited by 20
  6. 2023PFLlib: A Beginner-Friendly and Comprehensive Personalized Federated Learning Library and Benchmarkcited by 17
  7. 2024Modeling Inter-Intra Heterogeneity for Graph Federated Learningcited by 12
  8. 2025HtFLlib: A Comprehensive Heterogeneous Federated Learning Library and Benchmarkcited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion
  2. 2025FLIP: Towards Comprehensive and Reliable Evaluation of Federated Prompt Learning
  3. 2024Federated Domain Generalization via Prompt Learning and Aggregation
  4. 2025An Empirical Study of Federated Prompt Learning for Vision Language Model
  5. 2026Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach
  6. 2025FedMGP: Personalized Federated Learning with Multi-Group Text-Visual Prompts
  7. 2025FedDEAP: Adaptive Dual-Prompt Tuning for Multi-Domain Federated Learning
  8. 2024Mixture of Experts Made Personalized: Federated Prompt Learning for Vision-Language Models