In recent years, neural architecture-based recommender systems have achieved
tremendous success, but they still fall short of expectation when dealing with highly sparse …

Deep models trained in supervised mode have achieved remarkable success on a variety of
tasks. When labeled samples are limited, self-supervised learning (SSL) is emerging as a …

Mainstream 3D representation learning approaches are built upon contrastive or generative
modeling pretext tasks, where great improvements in performance on various downstream …

Human skeleton-based action recognition offers a valuable means to understand the
intricacies of human behavior because it can handle the complex relationships between …

The field of graph neural networks (GNNs) has seen rapid and incredible strides over the
recent years. Graph neural networks, also known as deep learning on graphs, graph …

Vision-language representation learning largely benefits from image-text alignment through
contrastive losses (eg, InfoNCE loss). The success of this alignment strategy is attributed to …

Few-shot classification is a challenging problem as only very few training examples are
given for each new task. One of the effective research lines to address this challenge …

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

In multimodal sentiment analysis (MSA), the performance of a model highly depends on the
quality of synthesized embeddings. These embeddings are generated from the upstream …

Molecular property prediction is one of the fastest-growing applications of deep learning with
critical real-world impacts. Although the 3D molecular graph structure is necessary for …