Federated Learning with Instance-Dependent Noisy Label
- URL: http://arxiv.org/abs/2312.10324v3
- Date: Wed, 10 Jan 2024 03:55:11 GMT
- Title: Federated Learning with Instance-Dependent Noisy Label
- Authors: Lei Wang, Jieming Bian, Jie Xu
- Abstract summary: FedBeat aims to build a global statistically consistent classifier using the IDN transition matrix (IDNTM)
Experiments conducted on CIFAR-10 and SVHN verify that the proposed method significantly outperforms state-of-the-art methods.
- Score: 6.093214616626228
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Federated learning (FL) with noisy labels poses a significant challenge.
Existing methods designed for handling noisy labels in centralized learning
tend to lose their effectiveness in the FL setting, mainly due to the small
dataset size and the heterogeneity of client data. While some attempts have
been made to tackle FL with noisy labels, they primarily focused on scenarios
involving class-conditional noise. In this paper, we study the more challenging
and practical issue of instance-dependent noise (IDN) in FL. We introduce a
novel algorithm called FedBeat (Federated Learning with Bayesian
Ensemble-Assisted Transition Matrix Estimation). FedBeat aims to build a global
statistically consistent classifier using the IDN transition matrix (IDNTM),
which encompasses three synergistic steps: (1) A federated data extraction step
that constructs a weak global model and extracts high-confidence data using a
Bayesian model ensemble method. (2) A federated transition matrix estimation
step in which clients collaboratively train an IDNTM estimation network based
on the extracted data. (3) A federated classifier correction step that enhances
the global model's performance by training it using a loss function tailored
for noisy labels, leveraging the IDNTM. Experiments conducted on CIFAR-10 and
SVHN verify that the proposed method significantly outperforms state-of-the-art
methods.
Related papers
- Collaboratively Learning Federated Models from Noisy Decentralized Data [21.3209961590772]
Federated learning (FL) has emerged as a prominent method for collaboratively training machine learning models using local data from edge devices.
We focus on addressing the problem of noisy data in the input space, an under-explored area compared to the label noise.
We propose a noise-aware FL aggregation method, namely Federated Noise-Sifting (FedNS), which can be used as a plug-in approach in conjunction with widely used FL strategies.
arXiv Detail & Related papers (2024-09-03T18:00:51Z) - FedAnchor: Enhancing Federated Semi-Supervised Learning with Label
Contrastive Loss for Unlabeled Clients [19.3885479917635]
Federated learning (FL) is a distributed learning paradigm that facilitates collaborative training of a shared global model across devices.
We propose FedAnchor, an innovative FSSL method that introduces a unique double-head structure, called anchor head, paired with the classification head trained exclusively on labeled anchor data on the server.
Our approach mitigates the confirmation bias and overfitting issues associated with pseudo-labeling techniques based on high-confidence model prediction samples.
arXiv Detail & Related papers (2024-02-15T18:48:21Z) - FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy
Labels [99.70895640578816]
Federated learning with noisy labels (F-LNL) aims at seeking an optimal server model via collaborative distributed learning.
We present FedDiv to tackle the challenges of F-LNL. Specifically, we propose a global noise filter called Federated Noise Filter.
arXiv Detail & Related papers (2023-12-19T15:46:47Z) - Learning Cautiously in Federated Learning with Noisy and Heterogeneous
Clients [4.782145666637457]
Federated learning (FL) is a distributed framework for collaboratively training with privacy guarantees.
In real-world scenarios, clients may have Non-IID data (local class imbalance) with poor annotation quality (label noise)
We propose FedCNI without using an additional clean proxy dataset.
It includes a noise-resilient local solver and a robust global aggregator.
arXiv Detail & Related papers (2023-04-06T06:47:14Z) - Instance-dependent Label Distribution Estimation for Learning with Label Noise [20.479674500893303]
Noise transition matrix (NTM) estimation is a promising approach for learning with label noise.
We propose an Instance-dependent Label Distribution Estimation (ILDE) method to learn from noisy labels for image classification.
Our results indicate that the proposed ILDE method outperforms all competing methods, no matter whether the noise is synthetic or real noise.
arXiv Detail & Related papers (2022-12-16T10:13:25Z) - FedNoiL: A Simple Two-Level Sampling Method for Federated Learning with
Noisy Labels [49.47228898303909]
Federated learning (FL) aims at training a global model on the server side while the training data are collected and located at the local devices.
Local training on noisy labels can easily result in overfitting to noisy labels, which is devastating to the global model through aggregation.
We develop a simple two-level sampling method "FedNoiL" that selects clients for more robust global aggregation on the server.
arXiv Detail & Related papers (2022-05-20T12:06:39Z) - Class-Aware Contrastive Semi-Supervised Learning [51.205844705156046]
We propose a general method named Class-aware Contrastive Semi-Supervised Learning (CCSSL) to improve pseudo-label quality and enhance the model's robustness in the real-world setting.
Our proposed CCSSL has significant performance improvements over the state-of-the-art SSL methods on the standard datasets CIFAR100 and STL10.
arXiv Detail & Related papers (2022-03-04T12:18:23Z) - Local Learning Matters: Rethinking Data Heterogeneity in Federated
Learning [61.488646649045215]
Federated learning (FL) is a promising strategy for performing privacy-preserving, distributed learning with a network of clients (i.e., edge devices)
arXiv Detail & Related papers (2021-11-28T19:03:39Z) - S3: Supervised Self-supervised Learning under Label Noise [53.02249460567745]
In this paper we address the problem of classification in the presence of label noise.
In the heart of our method is a sample selection mechanism that relies on the consistency between the annotated label of a sample and the distribution of the labels in its neighborhood in the feature space.
Our method significantly surpasses previous methods on both CIFARCIFAR100 with artificial noise and real-world noisy datasets such as WebVision and ANIMAL-10N.
arXiv Detail & Related papers (2021-11-22T15:49:20Z) - Tackling Instance-Dependent Label Noise via a Universal Probabilistic
Model [80.91927573604438]
This paper proposes a simple yet universal probabilistic model, which explicitly relates noisy labels to their instances.
Experiments on datasets with both synthetic and real-world label noise verify that the proposed method yields significant improvements on robustness.
arXiv Detail & Related papers (2021-01-14T05:43:51Z)
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.