Related papers: Triangular Contrastive Learning on Molecular Graph…
Contrastive Self-supervised Learning (CSL) is a practical solution that learns meaningful visual representations from massive data in an unsupervised approach. The ordinary CSL embeds the features extracted from neural networks onto…
Multi-modal contrastive learning as a self-supervised representation learning technique has achieved great success in foundation model training, such as CLIP~\citep{radford2021learning}. In this paper, we study the theoretical properties of…
Multimodal learning seeks to integrate information from heterogeneous sources, where signals may be shared across modalities, specific to individual modalities, or emerge only through their interaction. While self-supervised multimodal…
Multi-modal contrastive representation (MCR) of more than three modalities is critical in multi-modal learning. Although recent methods showcase impressive achievements, the high dependence on large-scale, high-quality paired data and the…
Contrastive loss and triplet loss are widely used objectives in deep metric learning, yet their effects on representation quality remain insufficiently understood. We present a theoretical and empirical comparison of these losses, focusing…
Self-supervised learning (SSL) has gained remarkable success, for which contrastive learning (CL) plays a key role. However, the recent development of new non-CL frameworks has achieved comparable or better performance with high improvement…
Graph Contrastive Learning (GCL) has recently drawn much research interest for learning generalizable node representations in a self-supervised manner. In general, the contrastive learning process in GCL is performed on top of the…
Recent years have seen a rapid growth of utilizing graph neural networks (GNNs) in the biomedical domain for tackling drug-related problems. However, like any other deep architectures, GNNs are data hungry. While requiring labels in real…
This paper proposes to perform online clustering by conducting twin contrastive learning (TCL) at the instance and cluster level. Specifically, we find that when the data is projected into a feature space with a dimensionality of the target…
Contrastive learning has achieved remarkable success on various high-level tasks, but there are fewer contrastive learning-based methods proposed for low-level tasks. It is challenging to adopt vanilla contrastive learning technologies…
The effectiveness of contrastive learning technology in natural language processing tasks is yet to be explored and analyzed. How to construct positive and negative samples correctly and reasonably is the core challenge of contrastive…
Pursuing realistic results according to human visual perception is the central concern in the image transformation tasks. Perceptual learning approaches like perceptual loss are empirically powerful for such tasks but they usually rely on…
Attempt to fully discover the temporal diversity and chronological characteristics for self-supervised video representation learning, this work takes advantage of the temporal dependencies within videos and further proposes a novel…
The versatility of multimodal deep learning holds tremendous promise for advancing scientific research and practical applications. As this field continues to evolve, the collective power of cross-modal analysis promises to drive…
Recently, hyperbolic space has risen as a promising alternative for semi-supervised graph representation learning. Many efforts have been made to design hyperbolic versions of neural network operations. However, the inspiring geometric…
Graph Contrastive Learning (GCL) is a widely adopted approach in self-supervised graph representation learning, applying contrastive objectives to produce effective representations. However, current GCL methods primarily focus on capturing…
Graph contrastive learning (GCL) has recently emerged as a promising approach for graph representation learning. Some existing methods adopt the 1-vs-K scheme to construct one positive and K negative samples for each graph, but it is…
Graph contrastive learning (GCL) is a popular method for leaning graph representations by maximizing the consistency of features across augmented views. Traditional GCL methods utilize single-perspective i.e. data or model-perspective)…
Cross-modal contrastive learning has led the recent advances in multimodal retrieval with its simplicity and effectiveness. In this work, however, we reveal that cross-modal contrastive learning suffers from incorrect normalization of the…
Graph Contrastive Learning (GCL) has emerged as a powerful paradigm for training Graph Neural Networks (GNNs) in the absence of task-specific labels. However, its scalability on large-scale graphs is hindered by the intensive message…