Exploring Vacant Classes in Label-Skewed Federated Learning

• URL: http://arxiv.org/abs/2401.02329v2
• Date: Mon, 19 Aug 2024 13:27:59 GMT
• Title: Exploring Vacant Classes in Label-Skewed Federated Learning
• Authors: Kuangpu Guo, Yuhe Ding, Jian Liang, Ran He, Zilei Wang, Tieniu Tan,
• Abstract summary: Label skews, characterized by disparities in local label distribution across clients, pose a significant challenge in federated learning. This paper introduces FedVLS, a novel approach to label-skewed federated learning that integrates vacant-class distillation and logit suppression simultaneously.
• Score: 113.65301899666645
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Label skews, characterized by disparities in local label distribution across clients, pose a significant challenge in federated learning. As minority classes suffer from worse accuracy due to overfitting on local imbalanced data, prior methods often incorporate class-balanced learning techniques during local training. Although these methods improve the mean accuracy across all classes, we observe that vacant classes-referring to categories absent from a client's data distribution-remain poorly recognized. Besides, there is still a gap in the accuracy of local models on minority classes compared to the global model. This paper introduces FedVLS, a novel approach to label-skewed federated learning that integrates both vacant-class distillation and logit suppression simultaneously. Specifically, vacant-class distillation leverages knowledge distillation during local training on each client to retain essential information related to vacant classes from the global model. Moreover, logit suppression directly penalizes network logits for non-label classes, effectively addressing misclassifications in minority classes that may be biased toward majority classes. Extensive experiments validate the efficacy of FedVLS, demonstrating superior performance compared to previous state-of-the-art (SOTA) methods across diverse datasets with varying degrees of label skews. Code is available in the supplementary material.

Related papers

• FedDistill: Global Model Distillation for Local Model De-Biasing in Non-IID Federated Learning [10.641875933652647]
  Federated Learning (FL) is a novel approach that allows for collaborative machine learning. FL faces challenges due to non-uniformly distributed (non-iid) data across clients. This paper introduces FedDistill, a framework enhancing the knowledge transfer from the global model to local models.
  arXiv  Detail & Related papers  (2024-04-14T10:23:30Z)
• Federated Skewed Label Learning with Logits Fusion [23.062650578266837]
  Federated learning (FL) aims to collaboratively train a shared model across multiple clients without transmitting their local data. We propose FedBalance, which corrects the optimization bias among local models by calibrating their logits. Our method can gain 13% higher average accuracy compared with state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-11-14T14:37:33Z)
• 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)
• On Non-Random Missing Labels in Semi-Supervised Learning [114.62655062520425]
  Semi-Supervised Learning (SSL) is fundamentally a missing label problem. We explicitly incorporate "class" into SSL. Our method not only significantly outperforms existing baselines but also surpasses other label bias removal SSL methods.
  arXiv  Detail & Related papers  (2022-06-29T22:01:29Z)
• Towards Unbiased Multi-label Zero-Shot Learning with Pyramid and Semantic Attention [14.855116554722489]
  Multi-label zero-shot learning aims at recognizing multiple unseen labels of classes for each input sample. We propose a novel framework of unbiased multi-label zero-shot learning, by considering various class-specific regions.
  arXiv  Detail & Related papers  (2022-03-07T15:52:46Z)
• Prototypical Classifier for Robust Class-Imbalanced Learning [64.96088324684683]
  We propose textitPrototypical, which does not require fitting additional parameters given the embedding network. Prototypical produces balanced and comparable predictions for all classes even though the training set is class-imbalanced. We test our method on CIFAR-10LT, CIFAR-100LT and Webvision datasets, observing that Prototypical obtains substaintial improvements compared with state of the arts.
  arXiv  Detail & Related papers  (2021-10-22T01:55:01Z)
• PLM: Partial Label Masking for Imbalanced Multi-label Classification [59.68444804243782]
  Neural networks trained on real-world datasets with long-tailed label distributions are biased towards frequent classes and perform poorly on infrequent classes. We propose a method, Partial Label Masking (PLM), which utilizes this ratio during training. Our method achieves strong performance when compared to existing methods on both multi-label (MultiMNIST and MSCOCO) and single-label (imbalanced CIFAR-10 and CIFAR-100) image classification datasets.
  arXiv  Detail & Related papers  (2021-05-22T18:07:56Z)
• Federated Learning with Only Positive Labels [71.63836379169315]
  We propose a generic framework for training with only positive labels, namely Federated Averaging with Spreadout (FedAwS) We show, both theoretically and empirically, that FedAwS can almost match the performance of conventional learning where users have access to negative labels.
  arXiv  Detail & Related papers  (2020-04-21T23:35:02Z)
• M2m: Imbalanced Classification via Major-to-minor Translation [79.09018382489506]
  In most real-world scenarios, labeled training datasets are highly class-imbalanced, where deep neural networks suffer from generalizing to a balanced testing criterion. In this paper, we explore a novel yet simple way to alleviate this issue by augmenting less-frequent classes via translating samples from more-frequent classes. Our experimental results on a variety of class-imbalanced datasets show that the proposed method improves the generalization on minority classes significantly compared to other existing re-sampling or re-weighting methods.
  arXiv  Detail & Related papers  (2020-04-01T13:21:17Z)

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.