3 papers
cs.LG2025
Graph Probability Aggregation Clustering
Yuxuan Yan, Na Lu, Difei Mei +2
Traditional clustering methods typically focus on either cluster-wise global clustering or point-wise local clustering to reveal the intrinsic structures in unlabeled data. Global…
cs.LG2025
Set a Thief to Catch a Thief: Combating Label Noise through Noisy Meta Learning
Hanxuan Wang, Na Lu, Xueying Zhao +4
Learning from noisy labels (LNL) aims to train high-performance deep models using noisy datasets. Meta learning based label correction methods have demonstrated remarkable performa…
cs.LG2024
Deep Online Probability Aggregation Clustering
Yuxuan Yan, Na Lu, Ruofan Yan
Combining machine clustering with deep models has shown remarkable superiority in deep clustering. It modifies the data processing pipeline into two alternating phases: feature clu…