Graph representation learning seeks to encode the structure and attributes of nodes and edges into low-dimensional vectors, enabling effective analysis of complex relational data. Early methods relied ...

Molecular graph representation learning has shown considerable strength in molecular analysis and drug discovery. Due to the difficulty of obtaining molecular property labels, pre-training models ...

With the emergence of huge amounts of heterogeneous multi-modal data, including images, videos, texts/languages, audios, and multi-sensor data, deep learning-based methods have shown promising ...

Graphs, visual representations outlining the relationships between different entities, concepts or variables, can be very effective in summarizing complex patterns and information. Past psychology ...