Related papers: Subset-Contrastive Multi-Omics Network Embedding

Contrastive representation learning has proven to be an effective self-supervised learning method for images and videos. Most successful approaches are based on Noise Contrastive Estimation (NCE) and use different views of an instance as…

Medical image segmentation, or computing voxelwise semantic masks, is a fundamental yet challenging task to compute a voxel-level semantic mask. To increase the ability of encoder-decoder neural networks to perform this task across large…

Graph similarity learning refers to calculating the similarity score between two graphs, which is required in many realistic applications, such as visual tracking, graph classification, and collaborative filtering. As most of the existing…

While various deep learning methods have been proposed for low-dose computed tomography (CT) denoising, most of them leverage the normal-dose CT images as the ground-truth to supervise the denoising process. These methods typically ignore…

One main challenge in imbalanced graph classification is to learn expressive representations of the graphs in under-represented (minority) classes. Existing generic imbalanced learning methods, such as oversampling and imbalanced learning…

Imbalanced Data (ID) is a problem that deters Machine Learning (ML) models for achieving satisfactory results. ID is the occurrence of a situation where the quantity of the samples belonging to one class outnumbers that of the other by a…

Graph representation learning has long been an important yet challenging task for various real-world applications. However, their downstream tasks are mainly performed in the settings of supervised or semi-supervised learning. Inspired by…

While deep Embedding Learning approaches have witnessed widespread success in multiple computer vision tasks, the state-of-the-art methods for representing natural images need not necessarily perform well on images from other domains, such…

This paper presents a whitening-based contrastive learning method for sentence embedding learning (WhitenedCSE), which combines contrastive learning with a novel shuffled group whitening. Generally, contrastive learning pulls distortions of…

Contrastive learning (CL) aims to preserve relational structure between samples by learning representations that reflect a similarity graph. Yet, the geometry of the resulting embeddings remains poorly understood. Here we show that weighted…

Graph neural networks (GNNs) encounter significant computational challenges when handling large-scale graphs, which severely restricts their efficacy across diverse applications. To address this limitation, graph condensation has emerged as…

Making decent multi-lingual sentence representations is critical to achieve high performances in cross-lingual downstream tasks. In this work, we propose a novel method to align multi-lingual embeddings based on the similarity of sentences…

Semi-supervised learning has demonstrated great potential in medical image segmentation by utilizing knowledge from unlabeled data. However, most existing approaches do not explicitly capture high-level semantic relations between distant…

Large pre-trained models (LMs) and Large Language Models (LLMs) are typically effective at capturing language semantics and contextual relationships. However, these models encounter challenges in maintaining optimal performance on tasks…

We introduce Contrastive FUSE, a fast and unified framework for scalable node representation learning in graphs with partially available pairwise node labels and no available node features. Unlike existing methods, we directly optimize a…

We propose a novel architecture and method of explainable classification with Concept Bottleneck Models (CBMs). While SOTA approaches to Image Classification task work as a black box, there is a growing demand for models that would provide…

We present UNSEE: Unsupervised Non-Contrastive Sentence Embeddings, a novel approach that outperforms SimCSE in the Massive Text Embedding benchmark. Our exploration begins by addressing the challenge of representation collapse, a…

Motivated by the computational and storage challenges that dense embeddings pose, we introduce the problem of latent network summarization that aims to learn a compact, latent representation of the graph structure with dimensionality that…

Graph contrastive learning defines a contrastive task to pull similar instances close and push dissimilar instances away. It learns discriminative node embeddings without supervised labels, which has aroused increasing attention in the past…

Contrastive learning produces coherent semantic feature embeddings by encouraging positive samples to cluster closely while separating negative samples. However, existing contrastive learning methods lack principled guarantees on coverage…