Abstract: Graph contrastive learning is usually performed by first conducting Graph Data Augmentation (GDA) and then employing a contrastive learning pipeline to train GNNs. As we know that GDA is an ...

This repository provides a comprehensive implementation of contrastive learning approaches for multi-label classification tasks. Our work explores the effectiveness of contrastive learning across ...

Abstract: Contrastive learning has gained popularity and pushes state-of-the-art performance across numerous large-scale benchmarks. In contrastive learning, the contrastive loss function plays a ...

Morphological profiling has recently demonstrated remarkable potential for identifying the biological activities of small molecules. Alongside the fully supervised and self-supervised machine learning ...

Recommender systems are essential for modern content platforms. Yet, traditional behavior-based recommendation models often struggle with cold users, who have limited interaction data. Despite this, ...

1 German Center for Neurodegenerative Diseases (DZNE), Rostock, Germany 2 Department of Psychosomatic Medicine, Rostock University Medical Center, Rostock, Germany Introduction: Neurodegenerative ...

1 Big Data Research Center, University of Electronic Science and Technology of China, Chengdu, China 2 i-Large Model Innovation Lab of Ideological and Political Science, University of Electronic ...