paper-with-me

홈 › Papers

FedCCL: Federated Dual-Clustered Feature Contrast Under Domain Heterogeneity

2024-04-14 · Yu Qiao, Huy Q. Le, Mengchun Zhang, Apurba Adhikary, Chaoning Zhang, Choong Seon Hong

Federated learning (FL) facilitates a privacy-preserving neural network training paradigm through collaboration between edge clients and a central server. One significant challenge is that the distributed data is not independently and identically distributed (non-IID), typically including both intra-domain and inter-domain heterogeneity. However, recent research is limited to simply using averaged signals as a form of regularization and only focusing on one aspect of these non-IID challenges. Given these limitations, this paper clarifies these two non-IID challenges and attempts to introduce cluster representation to address them from both local and global perspectives. Specifically, we propose a dual-clustered feature contrast-based FL framework with dual focuses. First, we employ clustering on the local representations of each client, aiming to capture intra-class information based on these local clusters at a high level of granularity. Then, we facilitate cross-client knowledge sharing by pulling the local representation closer to clusters shared by clients with similar semantics while pushing them away from clusters with dissimilar semantics. Second, since the sizes of local clusters belonging to the same class may differ for each client, we further utilize clustering on the global side and conduct averaging to create a consistent global signal for guiding each local training in a contrastive manner. Experimental results on multiple datasets demonstrate that our proposal achieves comparable or superior performance gain under intra-domain and inter-domain heterogeneity.

📄 PDF Abstract BibTeX arXiv:2404.09259

Code (0)

등록된 구현이 없습니다.

Tasks

ClusteringFederated LearningPrivacy Preserving

Similar Papers 제목 키워드 기반

FedDAG: Clustered Federated Learning via Global Data and Gradient Integration for Heterogeneous Environments

2026-02-26 · Anik Pramanik, Murat Kantarcioglu, Vincent Oria, Shantanu Sharma arxiv

Federated Learning (FL) enables a group of clients to collaboratively train a model without sharing individual data, but its performance drops when client data are heterogeneous. Clustered FL tackles this by grouping sim…

Federated Learning

Content Popularity Prediction in Fog-RANs: A Clustered Federated Learning Based Approach

2022-06-13 · Zhiheng Wang, Yanxiang Jiang, Fu-Chun Zheng, Mehdi Bennis 외

In this paper, the content popularity prediction problem in fog radio access networks (F-RANs) is investigated. Based on clustered federated learning, we propose a novel mobility-aware popularity prediction policy, which…

Federated Learning

Contrastive encoder pre-training-based clustered federated learning for heterogeneous data

2023-11-28 · Ye Lin Tun, Minh N. H. Nguyen, Chu Myaet Thwal, Jinwoo Choi 외

Federated learning (FL) is a promising approach that enables distributed clients to collaboratively train a global model while preserving their data privacy. However, FL often suffers from data heterogeneity problems, wh…

ClusteringContrastive LearningFederated Learning

Interaction-Aware Gaussian Weighting for Clustered Federated Learning

2025-02-05 · Alessandro Licciardi, Davide Leo, Eros Faní, Barbara Caputo 외

Federated Learning (FL) emerged as a decentralized paradigm to train models while preserving privacy. However, conventional FL struggles with data heterogeneity and class imbalance, which degrade model performance. Clust…

ClusteringFederated Learning

Federated Contrastive Representation Learning with Feature Fusion and Neighborhood Matching

2021-09-29 · Yawen Wu, Zhepeng Wang, Dewen Zeng, Meng Li 외

Federated learning (FL) enables distributed clients to learn a shared model for prediction while keeping the training data local on each client. However, existing FL requires fully-labeled data for training, which is inc…

Contrastive LearningFederated LearningRepresentation LearningSelf-Supervised Learning