Related papers: scI2CL: Effectively Integrating Single-cell Multi-…

Multimodal representation learning is commonly built on a shared-private decomposition, treating latent information as either common to all modalities or specific to one. This binary view is often inadequate: many factors are shared by only…

Through minimization of an appropriate loss function such as the InfoNCE loss, contrastive learning (CL) learns a useful representation function by pulling positive samples close to each other while pushing negative samples far apart in the…

In a wide range of multimodal tasks, contrastive learning has become a particularly appealing approach since it can successfully learn representations from abundant unlabeled data with only pairing information (e.g., image-caption or…

Single-cell analysis is currently one of the most high-resolution techniques to study biology. The large complex datasets that have been generated have spurred numerous developments in computational biology, in particular the use of…

Brain-computer interfaces (BCIs), is ways for electronic devices to communicate directly with the brain. For most medical-type brain-computer interface tasks, the activity of multiple units of neurons or local field potentials is sufficient…

Multi-modal contrastive learning (MMCL) has recently garnered considerable interest due to its superior performance in visual tasks, achieved by embedding multi-modal data, such as visual-language pairs. However, there still lack…

Learning semantic-rich representations from raw unlabeled time series data is critical for downstream tasks such as classification and forecasting. Contrastive learning has recently shown its promising representation learning capability in…

Live-cell imaging (LCI) technology enables the detailed spatio-temporal characterization of living cells at the single-cell level, which is critical for advancing research in the life sciences, from biomedical applications to bioprocessing.…

Metacells are disjoint and homogeneous groups of single-cell profiles, representing discrete and highly granular cell states. Existing metacell algorithms tend to use only one modality to infer metacells, even though single-cell multi-omics…

In recent years, a variety of contrastive learning based unsupervised visual representation learning methods have been designed and achieved great success in many visual tasks. Generally, these methods can be roughly classified into four…

The plethora of single-cell multi-omics data is getting treatment with deep learning, a revolutionary method in artificial intelligence, which has been increasingly expanding its reign over the bioscience frontiers.

Label-free cell classification is advantageous for supplying pristine cells for further use or examination, yet existing techniques frequently fall short in terms of specificity and speed. In this study, we address these limitations through…

Deep learning has been a prevalence in computational chemistry and widely implemented in molecule property predictions. Recently, self-supervised learning (SSL), especially contrastive learning (CL), gathers growing attention for the…

Graph neural networks (GNNs) have recently emerged as an effective approach to model neighborhood signals in collaborative filtering. Towards this research line, graph contrastive learning (GCL) demonstrates robust capabilities to address…

Cross-modal retrieval has become a highlighted research topic for retrieval across multimedia data such as image and text. A two-stage learning framework is widely adopted by most existing methods based on Deep Neural Network (DNN): The…

The distinct characteristics of multiomics data, including complex interactions within and across biological layers and disease heterogeneity (e.g., heterogeneity in etiology and clinical symptoms), drive us to develop novel designs to…

Inspired by the success of Self-supervised learning (SSL) in learning visual representations from unlabeled data, a few recent works have studied SSL in the context of continual learning (CL), where multiple tasks are learned sequentially,…

Representation learning offers a conduit to elucidate distinctive features within the latent space and interpret the deep models. However, the randomness of lesion distribution and the complexity of low-quality factors in medical images…

Continual learning aims to learn continuously from a stream of tasks and data in an online-learning fashion, being capable of exploiting what was learned previously to improve current and future tasks while still being able to perform well…

Visual recognition is recently learned via either supervised learning on human-annotated image-label data or language-image contrastive learning with webly-crawled image-text pairs. While supervised learning may result in a more…