Deep supervised learning algorithms typically require a large volume of labeled data to
achieve satisfactory performance. However, the process of collecting and labeling such data …

Traditional machine learning, mainly supervised learning, follows the assumptions of closed-
world learning, ie, for each testing class, a training class is available. However, such …

Learning with few labeled data has been a longstanding problem in the computer vision and
machine learning research community. In this paper, we introduced a new semi-supervised …

Molecular graph representation learning is a fundamental problem in modern drug and
material discovery. Molecular graphs are typically modeled by their 2D topological …

State-of-the-art deep learning models are often trained with a large amount of costly labeled
training data. However, requiring exhaustive manual annotations may degrade the model's …

In self-supervised representation learning, a common idea behind most of the state-of-the-
art approaches is to enforce the robustness of the representations to predefined …

Representation learning has significantly been developed with the advance of contrastive
learning methods. Most of those methods are benefited from various data augmentations …

Recently, contrastive learning-based image translation methods have been proposed, which
contrasts different spatial locations to enhance the spatial correspondence. However, the …

Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved
great success in learning visual representations without data annotations. However, most of …

Hierarchical semantic structures naturally exist in an image dataset, in which several
semantically relevant image clusters can be further integrated into a larger cluster with …