An Experimental Study of Class Imbalance in Federated Learning
- URL: http://arxiv.org/abs/2109.04094v1
- Date: Thu, 9 Sep 2021 08:26:16 GMT
- Title: An Experimental Study of Class Imbalance in Federated Learning
- Authors: C. Xiao, S. Wang
- Abstract summary: We propose two new metrics to define class imbalance -- the global class imbalance degree (MID) and the local difference of class imbalance among clients (WCS)
Our results show that a higher MID and a larger WCS degrade more the performance of the global model.
- Score: 0.8122270502556371
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Federated learning is a distributed machine learning paradigm that trains a
global model for prediction based on a number of local models at clients while
local data privacy is preserved. Class imbalance is believed to be one of the
factors that degrades the global model performance. However, there has been
very little research on if and how class imbalance can affect the global
performance. class imbalance in federated learning is much more complex than
that in traditional non-distributed machine learning, due to different class
imbalance situations at local clients. Class imbalance needs to be re-defined
in distributed learning environments. In this paper, first, we propose two new
metrics to define class imbalance -- the global class imbalance degree (MID)
and the local difference of class imbalance among clients (WCS). Then, we
conduct extensive experiments to analyze the impact of class imbalance on the
global performance in various scenarios based on our definition. Our results
show that a higher MID and a larger WCS degrade more the performance of the
global model. Besides, WCS is shown to slow down the convergence of the global
model by misdirecting the optimization.
Related papers
- Uncertainty-guided Boundary Learning for Imbalanced Social Event
Detection [64.4350027428928]
We propose a novel uncertainty-guided class imbalance learning framework for imbalanced social event detection tasks.
Our model significantly improves social event representation and classification tasks in almost all classes, especially those uncertain ones.
arXiv Detail & Related papers (2023-10-30T03:32:04Z) - Class-Imbalanced Graph Learning without Class Rebalancing [62.1368829847041]
Class imbalance is prevalent in real-world node classification tasks and poses great challenges for graph learning models.
In this work, we approach the root cause of class-imbalance bias from an topological paradigm.
We devise a lightweight topological augmentation framework BAT to mitigate the class-imbalance bias without class rebalancing.
arXiv Detail & Related papers (2023-08-27T19:01:29Z) - 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) - Federated Learning with Classifier Shift for Class Imbalance [6.097542448692326]
Federated learning aims to learn a global model collaboratively while the training data belongs to different clients and is not allowed to be exchanged.
This paper proposes a simple and effective approach named FedShift which adds the shift on the classifier output during the local training phase to alleviate the negative impact of class imbalance.
arXiv Detail & Related papers (2023-04-11T04:38:39Z) - Addressing Class Variable Imbalance in Federated Semi-supervised
Learning [10.542178602467885]
We propose Federated Semi-supervised Learning for Class Variable Imbalance (FCVI) to solve class variable imbalance.
FCVI is used to mitigate the data imbalance due to changes of the number of classes.
Our scheme is proved to be significantly better than baseline methods, while maintaining client privacy.
arXiv Detail & Related papers (2023-03-21T12:50:17Z) - 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 Class-Incremental Learning [32.676616274338734]
Federated learning (FL) has attracted growing attention via data-private collaborative training on decentralized clients.
Most existing methods unrealistically assume object classes of the overall framework are fixed over time.
We develop a novel Global-Local Forgetting Compensation (GLFC) model to learn a global class incremental model.
arXiv Detail & Related papers (2022-03-22T05:58:44Z) - CoSSL: Co-Learning of Representation and Classifier for Imbalanced
Semi-Supervised Learning [98.89092930354273]
We propose a novel co-learning framework (CoSSL) with decoupled representation learning and classifier learning for imbalanced SSL.
To handle the data imbalance, we devise Tail-class Feature Enhancement (TFE) for classifier learning.
In experiments, we show that our approach outperforms other methods over a large range of shifted distributions.
arXiv Detail & Related papers (2021-12-08T20:13:13Z) - Long-Tailed Recognition Using Class-Balanced Experts [128.73438243408393]
We propose an ensemble of class-balanced experts that combines the strength of diverse classifiers.
Our ensemble of class-balanced experts reaches results close to state-of-the-art and an extended ensemble establishes a new state-of-the-art on two benchmarks for long-tailed recognition.
arXiv Detail & Related papers (2020-04-07T20:57:44Z)
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.