activity
20192024
most citedTowards Fast and Stable Federated Learning: Confronting Heterogeneity via Knowledge Anchor

5 citations · 13 across the 9 of their papers we have counts for

collaborators

16 papers

cs.LG2024

Towards Stable and Storage-efficient Dataset Distillation: Matching Convexified Trajectory

Wenliang Zhong, Haoyu Tang, Qinghai Zheng +3

The rapid evolution of deep learning and large language models has led to an exponential growth in the demand for training data, prompting the development of Dataset Distillation m…

cs.LG2024

Watch Your Head: Assembling Projection Heads to Save the Reliability of Federated Models

Jinqian Chen, Jihua Zhu, Qinghai Zheng +2

Federated learning encounters substantial challenges with heterogeneous data, leading to performance degradation and convergence issues. While considerable progress has been achiev…

cs.LG2023★ 5 cited

Towards Fast and Stable Federated Learning: Confronting Heterogeneity via Knowledge Anchor

Jinqian Chen, Jihua Zhu, Qinghai Zheng

Federated learning encounters a critical challenge of data heterogeneity, adversely affecting the performance and convergence of the federated model. Various approaches have been p…

cs.LG2023★ 1 cited

Label Information Bottleneck for Label Enhancement

Qinghai Zheng, Jihua Zhu, Haoyu Tang

In this work, we focus on the challenging problem of Label Enhancement (LE), which aims to exactly recover label distributions from logical labels, and present a novel Label Inform…

cs.LG2023★ 1 cited

Semantically Consistent Multi-view Representation Learning

Yiyang Zhou, Qinghai Zheng, Shunshun Bai +1

In this work, we devote ourselves to the challenging task of Unsupervised Multi-view Representation Learning (UMRL), which requires learning a unified feature representation from m…

cs.LG2023★ 2 cited

Multi-view Semantic Consistency based Information Bottleneck for Clustering

Wenbiao Yan, Jihua Zhu, Yiyang Zhou +2

Multi-view clustering can make use of multi-source information for unsupervised clustering. Most existing methods focus on learning a fused representation matrix, while ignoring th…