Distilling A Universal Expert from Clustered Federated Learning

• URL: http://arxiv.org/abs/2506.20285v1
• Date: Wed, 25 Jun 2025 09:44:39 GMT
• Title: Distilling A Universal Expert from Clustered Federated Learning
• Authors: Zeqi Leng, Chunxu Zhang, Guodong Long, Riting Xia, Bo Yang,
• Abstract summary: Clustered Federated Learning (CFL) addresses the challenges posed by non-IID data by training multiple group- or cluster-specific expert models.<n>This paper introduces a novel FL framework that distills a universal expert model from the knowledge of multiple clusters.
• Score: 23.801864975543122
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Clustered Federated Learning (CFL) addresses the challenges posed by non-IID data by training multiple group- or cluster-specific expert models. However, existing methods often overlook the shared information across clusters, which represents the generalizable knowledge valuable to all participants in the Federated Learning (FL) system. To overcome this limitation, this paper introduces a novel FL framework that distills a universal expert model from the knowledge of multiple clusters. This universal expert captures globally shared information across all clients and is subsequently distributed to each client as the initialization for the next round of model training. The proposed FL framework operates in three iterative steps: (1) local model training at each client, (2) cluster-specific model aggregation, and (3) universal expert distillation. This three-step learning paradigm ensures the preservation of fine-grained non-IID characteristics while effectively incorporating shared knowledge across clusters. Compared to traditional gradient-based aggregation methods, the distillation-based model aggregation introduces greater flexibility in handling model heterogeneity and reduces conflicts among cluster-specific experts. Extensive experimental results demonstrate the superior performance of the proposed method across various scenarios, highlighting its potential to advance the state of CFL by balancing personalized and shared knowledge more effectively.

Related papers

• Hierarchical Knowledge Structuring for Effective Federated Learning in Heterogeneous Environments [0.6144680854063939]
  Federated learning enables collaborative model training across distributed entities while maintaining individual data privacy.<n>Recent efforts leverage logit-based knowledge aggregation and distillation to overcome these issues.<n>We propose a Hierarchical Knowledge Structuring (HKS) framework that formulates sample logits into a multi-granularity codebook.
  arXiv  Detail & Related papers  (2025-04-04T15:06:02Z)
• Interaction-Aware Gaussian Weighting for Clustered Federated Learning [58.92159838586751]
  Federated Learning (FL) emerged as a decentralized paradigm to train models while preserving privacy.<n>We propose a novel clustered FL method, FedGWC (Federated Gaussian Weighting Clustering), which groups clients based on their data distribution.<n>Our experiments on benchmark datasets show that FedGWC outperforms existing FL algorithms in cluster quality and classification accuracy.
  arXiv  Detail & Related papers  (2025-02-05T16:33:36Z)
• Personalized Federated Learning with Adaptive Feature Aggregation and Knowledge Transfer [0.0]
  Federated Learning (FL) is popular as a privacy-preserving machine learning paradigm for generating a single model on decentralized data. We propose a new method personalized Federated learning with Adaptive Feature Aggregation and Knowledge Transfer (FedAFK) We conduct extensive experiments on three datasets in two widely-used heterogeneous settings and show the superior performance of our proposed method over thirteen state-of-the-art baselines.
  arXiv  Detail & Related papers  (2024-10-19T11:32:39Z)
• Federated Cross-Training Learners for Robust Generalization under Data Heterogeneity [27.97181776470323]
  Federated learning benefits from cross-training strategies, which enables models to train on data from distinct sources to improve generalization capability.<n>We argue that knowledge distillation from the personalized view preserves client-specific characteristics and expands the local knowledge base.<n>We show that FedCT alleviates knowledge from both local and global views, which enables it outperform state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-05-30T13:27:30Z)
• Multi-level Personalized Federated Learning on Heterogeneous and Long-Tailed Data [10.64629029156029]
  We introduce an innovative personalized Federated Learning framework, Multi-level Personalized Federated Learning (MuPFL) MuPFL integrates three pivotal modules: Biased Activation Value Dropout (BAVD), Adaptive Cluster-based Model Update (ACMU) and Prior Knowledge-assisted Fine-tuning (PKCF) Experiments on diverse real-world datasets show that MuPFL consistently outperforms state-of-the-art baselines, even under extreme non-i.i.d. and long-tail conditions.
  arXiv  Detail & Related papers  (2024-05-10T11:52:53Z)
• An Aggregation-Free Federated Learning for Tackling Data Heterogeneity [50.44021981013037]
  Federated Learning (FL) relies on the effectiveness of utilizing knowledge from distributed datasets. Traditional FL methods adopt an aggregate-then-adapt framework, where clients update local models based on a global model aggregated by the server from the previous training round. We introduce FedAF, a novel aggregation-free FL algorithm.
  arXiv  Detail & Related papers  (2024-04-29T05:55:23Z)
• Contrastive encoder pre-training-based clustered federated learning for heterogeneous data [17.580390632874046]
  Federated learning (FL) enables distributed clients to collaboratively train a global model while preserving their data privacy. We propose contrastive pre-training-based clustered federated learning (CP-CFL) to improve the model convergence and overall performance of FL systems.
  arXiv  Detail & Related papers  (2023-11-28T05:44:26Z)
• Unlocking the Potential of Prompt-Tuning in Bridging Generalized and Personalized Federated Learning [49.72857433721424]
  Vision Transformers (ViT) and Visual Prompt Tuning (VPT) achieve state-of-the-art performance with improved efficiency in various computer vision tasks. We present a novel algorithm, SGPT, that integrates Generalized FL (GFL) and Personalized FL (PFL) approaches by employing a unique combination of both shared and group-specific prompts.
  arXiv  Detail & Related papers  (2023-10-27T17:22:09Z)
• Enhancing Clustered Federated Learning: Integration of Strategies and Improved Methodologies [4.489171618387544]
  Federated Learning (FL) is an evolving distributed machine learning approach.<n> variation in data among clients poses challenges in training models that excel across all local distributions.<n>Recent studies suggest clustering as a solution to address client heterogeneity in FL by grouping clients with distribution shifts into distinct clusters.
  arXiv  Detail & Related papers  (2023-10-09T04:23:11Z)
• Unified Multi-View Orthonormal Non-Negative Graph Based Clustering Framework [74.25493157757943]
  We formulate a novel clustering model, which exploits the non-negative feature property and incorporates the multi-view information into a unified joint learning framework. We also explore, for the first time, the multi-model non-negative graph-based approach to clustering data based on deep features.
  arXiv  Detail & Related papers  (2022-11-03T08:18:27Z)
• Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning [86.59588262014456]
  Federated Learning (FL) is an emerging distributed learning paradigm under privacy constraint. We propose a data-free knowledge distillation method to fine-tune the global model in the server (FedFTG) Our FedFTG significantly outperforms the state-of-the-art (SOTA) FL algorithms and can serve as a strong plugin for enhancing FedAvg, FedProx, FedDyn, and SCAFFOLD.
  arXiv  Detail & Related papers  (2022-03-17T11:18:17Z)
• On the Convergence of Clustered Federated Learning [57.934295064030636]
  In a federated learning system, the clients, e.g. mobile devices and organization participants, usually have different personal preferences or behavior patterns. This paper proposes a novel weighted client-based clustered FL algorithm to leverage the client's group and each client in a unified optimization framework.
  arXiv  Detail & Related papers  (2022-02-13T02:39:19Z)
• Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification [106.08067870620218]
  We propose a self-paced knowledge distillation framework, termed Learning From Multiple Experts (LFME) We refer to these models as 'Experts', and the proposed LFME framework aggregates the knowledge from multiple 'Experts' to learn a unified student model. We conduct extensive experiments and demonstrate that our method is able to achieve superior performances compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-01-06T12:57:36Z)

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.