Graph contrastive learning (GCL) has emerged as a dominant technique for graph
representation learning which maximizes the mutual information between paired graph …

Deep Learning has achieved remarkable successes in many industry applications and
scientific research fields. One essential reason is that deep models can learn rich …

Existing studies indicate that deep neural networks (DNNs) can eventually memorize the
label noise. We observe that the memorization strength of DNNs towards each instance is …

Sign language recognition (SLR) is a weakly supervised task that annotates sign videos as
textual glosses. Recent studies show that insufficient training caused by the lack of large …

The sample selection approach is popular in learning with noisy labels. The state-of-the-art
methods train two deep networks simultaneously for sample selection, which aims to employ …

Spatiotemporal predictive learning aims to generate future frames by learning from historical
frames. In this paper, we investigate existing methods and present a general framework of …

Recent studies demonstrated that deep neural networks (DNNs) are vulnerable to backdoor
attacks. The attacked model behaves normally on benign samples, while its predictions are …

Recent years have witnessed the prosperity of pre-training graph neural networks (GNNs)
for molecules. Typically, atom types as node attributes are randomly masked and GNNs are …

Benefiting from the strong view-consistent information mining capacity, multi-view
contrastive clustering has attracted plenty of attention in recent years. However, we observe …

Label noise widely exists in large-scale image datasets. To mitigate the side effects of label
noise, state-of-the-art methods focus on selecting confident examples by leveraging semi …