294 citations · 567 across the 32 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.AI2021★ 47 cited
ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning
Jun Xia, Lirong Wu, Ge Wang +2
Contrastive Learning (CL) has emerged as a dominant technique for unsupervised representation learning which embeds augmented versions of the anchor close to each other (positive s…
cs.LG2021★ 122 cited
Co-learning: Learning from Noisy Labels with Self-supervision
Cheng Tan, Jun Xia, Lirong Wu +1
Noisy labels, resulting from mistakes in manual labeling or webly data collecting for supervised learning, can cause neural networks to overfit the misleading information and degra…