No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier

• URL: http://arxiv.org/abs/2303.10058v2
• Date: Mon, 28 Aug 2023 10:46:22 GMT
• Title: No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier
• Authors: Zexi Li, Xinyi Shang, Rui He, Tao Lin, Chao Wu
• Abstract summary: We propose a solution to the FL's classifier bias problem by utilizing a synthetic and fixed ETF classifier during training. We devise several effective modules to better adapt the ETF structure in FL, achieving both high generalization and personalization. Our method achieves state-of-the-art performances on CIFAR-10, CIFAR-100, and Tiny-ImageNet.
• Score: 10.491645205483051
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Data heterogeneity is an inherent challenge that hinders the performance of federated learning (FL). Recent studies have identified the biased classifiers of local models as the key bottleneck. Previous attempts have used classifier calibration after FL training, but this approach falls short in improving the poor feature representations caused by training-time classifier biases. Resolving the classifier bias dilemma in FL requires a full understanding of the mechanisms behind the classifier. Recent advances in neural collapse have shown that the classifiers and feature prototypes under perfect training scenarios collapse into an optimal structure called simplex equiangular tight frame (ETF). Building on this neural collapse insight, we propose a solution to the FL's classifier bias problem by utilizing a synthetic and fixed ETF classifier during training. The optimal classifier structure enables all clients to learn unified and optimal feature representations even under extremely heterogeneous data. We devise several effective modules to better adapt the ETF structure in FL, achieving both high generalization and personalization. Extensive experiments demonstrate that our method achieves state-of-the-art performances on CIFAR-10, CIFAR-100, and Tiny-ImageNet.

Related papers

• FedDr+: Stabilizing Dot-regression with Global Feature Distillation for Federated Learning [27.782676760198697]
  Federated Learning (FL) has emerged as a pivotal framework for the development of effective global models. A key challenge in FL is client drift, where data heterogeneity impedes the aggregation of scattered knowledge. We introduce a novel algorithm named FedDr+, which empowers local model alignment using dot-regression loss.
  arXiv  Detail & Related papers  (2024-06-04T14:34:13Z)
• Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning [120.53458753007851]
  Few-shot class-incremental learning (FSCIL) has been a challenging problem as only a few training samples are accessible for each novel class in the new sessions. We deal with this misalignment dilemma in FSCIL inspired by the recently discovered phenomenon named neural collapse. We propose a neural collapse inspired framework for FSCIL. Experiments on the miniImageNet, CUB-200, and CIFAR-100 datasets demonstrate that our proposed framework outperforms the state-of-the-art performances.
  arXiv  Detail & Related papers  (2023-02-06T18:39:40Z)
• 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)
• Federated Learning on Heterogeneous and Long-Tailed Data via Classifier Re-Training with Federated Features [24.679535905451758]
  Federated learning (FL) provides a privacy-preserving solution for distributed machine learning tasks. One challenging problem that severely damages the performance of FL models is the co-occurrence of data heterogeneity and long-tail distribution. We propose a novel privacy-preserving FL method for heterogeneous and long-tailed data via Federated Re-training with Federated Features (CReFF)
  arXiv  Detail & Related papers  (2022-04-28T10:35:11Z)
• Do We Really Need a Learnable Classifier at the End of Deep Neural Network? [118.18554882199676]
  We study the potential of learning a neural network for classification with the classifier randomly as an ETF and fixed during training. Our experimental results show that our method is able to achieve similar performances on image classification for balanced datasets.
  arXiv  Detail & Related papers  (2022-03-17T04:34:28Z)
• 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)
• No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data [78.69828864672978]
  A central challenge in training classification models in the real-world federated system is learning with non-IID data. We propose a novel and simple algorithm called Virtual Representations (CCVR), which adjusts the classifier using virtual representations sampled from an approximated ssian mixture model. Experimental results demonstrate that CCVR state-of-the-art performance on popular federated learning benchmarks including CIFAR-10, CIFAR-100, and CINIC-10.
  arXiv  Detail & Related papers  (2021-06-09T12:02:29Z)
• Solving Long-tailed Recognition with Deep Realistic Taxonomic Classifier [68.38233199030908]
  Long-tail recognition tackles the natural non-uniformly distributed data in realworld scenarios. While moderns perform well on populated classes, its performance degrades significantly on tail classes. Deep-RTC is proposed as a new solution to the long-tail problem, combining realism with hierarchical predictions.
  arXiv  Detail & Related papers  (2020-07-20T05:57:42Z)

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.