Modeling Global Distribution for Federated Learning with Label Distribution Skew

• URL: http://arxiv.org/abs/2212.08883v1
• Date: Sat, 17 Dec 2022 14:46:01 GMT
• Title: Modeling Global Distribution for Federated Learning with Label Distribution Skew
• Authors: Tao Sheng, Chengchao Shen, Yuan Liu, Yeyu Ou, Zhe Qu, Jianxin Wang
• Abstract summary: Federated learning achieves joint training of deep models by connecting decentralized data sources. In a more general case, the distributions of labels among clients are different, called label distribution skew'' We propose a novel federated learning method, named FedMGD, to alleviate the performance degradation caused by the label distribution skew issue.
• Score: 15.417187554408104
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Federated learning achieves joint training of deep models by connecting decentralized data sources, which can significantly mitigate the risk of privacy leakage. However, in a more general case, the distributions of labels among clients are different, called ``label distribution skew''. Directly applying conventional federated learning without consideration of label distribution skew issue significantly hurts the performance of the global model. To this end, we propose a novel federated learning method, named FedMGD, to alleviate the performance degradation caused by the label distribution skew issue. It introduces a global Generative Adversarial Network to model the global data distribution without access to local datasets, so the global model can be trained using the global information of data distribution without privacy leakage. The experimental results demonstrate that our proposed method significantly outperforms the state-of-the-art on several public benchmarks. Code is available at \url{https://github.com/Sheng-T/FedMGD}.

Related papers

• Disentangling data distribution for Federated Learning [20.524108508314107]
  Federated Learning (FL) facilitates collaborative training of a global model whose performance is boosted by private data owned by distributed clients. Yet the wide applicability of FL is hindered by entanglement of data distributions across different clients. This paper demonstrates for the first time that by disentangling data distributions FL can in principle achieve efficiencies comparable to those of distributed systems.
  arXiv  Detail & Related papers  (2024-10-16T13:10:04Z)
• Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition [50.61991746981703]
  Current state-of-the-art LTSSL approaches rely on high-quality pseudo-labels for large-scale unlabeled data. This paper introduces a novel probabilistic framework that unifies various recent proposals in long-tail learning. We introduce a continuous contrastive learning method, CCL, extending our framework to unlabeled data using reliable and smoothed pseudo-labels.
  arXiv  Detail & Related papers  (2024-10-08T15:06:10Z)
• Recovering Global Data Distribution Locally in Federated Learning [7.885010255812708]
  Federated Learning (FL) is a distributed machine learning paradigm that enables collaboration among multiple clients. A major challenge in FL is the label imbalance, where clients may exclusively possess certain classes while having numerous minority and missing classes. We propose a novel approach ReGL to address this challenge, whose key idea is to Recover the Global data distribution Locally.
  arXiv  Detail & Related papers  (2024-09-21T08:35:04Z)
• Tunable Soft Prompts are Messengers in Federated Learning [55.924749085481544]
  Federated learning (FL) enables multiple participants to collaboratively train machine learning models using decentralized data sources. The lack of model privacy protection in FL becomes an unneglectable challenge. We propose a novel FL training approach that accomplishes information exchange among participants via tunable soft prompts.
  arXiv  Detail & Related papers  (2023-11-12T11:01:10Z)
• Rethinking Client Drift in Federated Learning: A Logit Perspective [125.35844582366441]
  Federated Learning (FL) enables multiple clients to collaboratively learn in a distributed way, allowing for privacy protection. We find that the difference in logits between the local and global models increases as the model is continuously updated. We propose a new algorithm, named FedCSD, a Class prototype Similarity Distillation in a federated framework to align the local and global models.
  arXiv  Detail & Related papers  (2023-08-20T04:41:01Z)
• Towards Unbiased Training in Federated Open-world Semi-supervised Learning [15.08153616709326]
  We propose a novel Federatedopen-world Semi-Supervised Learning (FedoSSL) framework, which can solve the key challenge in distributed and open-world settings. We adopt an uncertainty-aware suppressed loss to alleviate the biased training between locally unseen and globally unseen classes. The proposed FedoSSL can be easily adapted to state-of-the-art FL methods, which is also validated via extensive experiments on benchmarks and real-world datasets.
  arXiv  Detail & Related papers  (2023-05-01T11:12:37Z)
• Integrating Local Real Data with Global Gradient Prototypes for Classifier Re-Balancing in Federated Long-Tailed Learning [60.41501515192088]
  Federated Learning (FL) has become a popular distributed learning paradigm that involves multiple clients training a global model collaboratively. The data samples usually follow a long-tailed distribution in the real world, and FL on the decentralized and long-tailed data yields a poorly-behaved global model. In this work, we integrate the local real data with the global gradient prototypes to form the local balanced datasets.
  arXiv  Detail & Related papers  (2023-01-25T03:18:10Z)
• 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)
• Preservation of the Global Knowledge by Not-True Self Knowledge Distillation in Federated Learning [8.474470736998136]
  In Federated Learning (FL), a strong global model is collaboratively learned by aggregating the clients' locally trained models. We observe that fitting on biased local distribution shifts the feature on global distribution and results in forgetting of global knowledge. We propose a simple yet effective framework Federated Local Self-Distillation (FedLSD), which utilizes the global knowledge on locally available data.
  arXiv  Detail & Related papers  (2021-06-06T11:51:47Z)
• Multi-Center Federated Learning [62.57229809407692]
  This paper proposes a novel multi-center aggregation mechanism for federated learning. It learns multiple global models from the non-IID user data and simultaneously derives the optimal matching between users and centers. Our experimental results on benchmark datasets show that our method outperforms several popular federated learning methods.
  arXiv  Detail & Related papers  (2020-05-03T09:14:31Z)

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.