2 papers
cs.LG2026
Leveraging Data Symmetries to Select an Optimal Subset of Training Data under Label Noise
Kumar Shubham, Pavan Karjol, Kiran M K +1
The performance of machine learning models often relies on large labeled datasets; however, data collected from diverse sources can contain label noise. Recent work has shown that,…
cs.LG2024
Unsupervised Learning of Group Invariant and Equivariant Representations
Robin Winter, Marco Bertolini, Tuan Le +2
Equivariant neural networks, whose hidden features transform according to representations of a group G acting on the data, exhibit training efficiency and an improved generalisatio…