Yuxia Liu

Yuxia Liu

Auto-generated profile, based on publicly available information

Yuxia Liu

National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, Hubei Key Laboratory of Multimedia and Network Communication Engineering, the School of Computer Science, and Hubei Luojia Laboratory, Wuhan University, Wuhan, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 May 2024 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
WHWenke Huang
Wenke Huang
YLYuxia Liu
Yuxia Liu
Mang YeMang Ye
Mang Ye
军陈军 陈
军 陈
BDBo Du
Bo Du
Prevalent federated learning commonly develops under the assumption that the ideal global class distributions are balanced. In contrast, real-world data typically follows the long-tailed class distribution, where models struggle to classify samples from tail classes. In this paper, we alleviate the issue under the long-tailed data, dissecting the into two aspects: the distorted feature space and the biased classifier. Specifically, we propose the Representation Unification and Classifier Rectification (RUCR), which leverages global unified prototypes to shape the feature space and calibrate the classifier. RUCR aggregates local prototypes (class-wise mean features) extracted by the global model to obtain global unified prototypes. It calibrates the feature space by pulling features within the same class towards corresponding global unified prototypes and pushing the other classes away. Moreover, RUCR utilizes global prototypes to reduce the classifier bias via prototypical mix-up. It generates a balanced virtual feature set by arbitrarily fusing global unified prototypes and local features. The classifier re-training is then conducted on the balanced virtual feature set to rectify the decision boundary and thus alleviate the shifts. Empirical results on CIFAR-10-LT, CIFAR-100-LT, and Tiny-Imagenet-LT datasets validate the superior performance of our proposed method.