中文
相关论文

相关论文: Exploring Galaxy Properties of eCALIFA with Contra…

200 篇论文

We characterize in detail the radial structure of the stellar population properties of 300 galaxies in the nearby universe, observed with integral field spectroscopy in the CALIFA survey. The sample covers a wide range of Hubble types, from…

We propose Graph Contrastive Learning (GraphCL), a general framework for learning node representations in a self supervised manner. GraphCL learns node embeddings by maximizing the similarity between the representations of two randomly…

机器学习 · 计算机科学 2020-07-17 Hakim Hafidi , Mounir Ghogho , Philippe Ciblat , Ananthram Swami

Contrastive analysis (CA) refers to the exploration of variations uniquely enriched in a target dataset as compared to a corresponding background dataset generated from sources of variation that are irrelevant to a given task. For example,…

机器学习 · 计算机科学 2023-10-31 Ethan Weinberger , Ian Covert , Su-In Lee

Self-Supervised Contrastive Learning has proven effective in deriving high-quality representations from unlabeled data. However, a major challenge that hinders both unimodal and multimodal contrastive learning is feature suppression, a…

计算机视觉与模式识别 · 计算机科学 2024-07-16 Jihai Zhang , Xiang Lan , Xiaoye Qu , Yu Cheng , Mengling Feng , Bryan Hooi

We present a study of the integrated properties of the 835 galaxies in the CALIFA survey. To derive the main physical parameters of the galaxies we have fitted their UV-to-IR spectral energy distributions (SED) with sets of theoretical…

Contrastive learning -- a modern approach to extract useful representations from unlabeled data by training models to distinguish similar samples from dissimilar ones -- has driven significant progress in foundation models. In this work, we…

机器学习 · 统计学 2025-10-15 Licong Lin , Song Mei

Unsupervised graph representation learning is a non-trivial topic. The success of contrastive methods in the unsupervised representation learning on structured data inspires similar attempts on the graph. Existing graph contrastive learning…

机器学习 · 计算机科学 2024-04-02 Tianyu Zhang , Yuxiang Ren , Wenzheng Feng , Weitao Du , Xuecang Zhang

Studying galaxy evolution requires knowledge not only of the stellar properties, but also of the interstellar medium (in particular the molecular phase) out of which stars form, using a statistically significant and unbiased sample of…

Continual learning (CL) involves acquiring and accumulating knowledge from evolving tasks while alleviating catastrophic forgetting. Recently, leveraging contrastive loss to construct more transferable and less forgetful representations has…

机器学习 · 计算机科学 2025-09-22 Jia Tang , Xinrui Wang , Songcan Chen

Contrastive Learning (CL) has emerged as a powerful method for training feature extraction models using unlabeled data. Recent studies suggest that incorporating a linear projection head post-backbone significantly enhances model…

机器学习 · 计算机科学 2024-10-08 Huanran Li , Daniel Pimentel-Alarcón

A galaxy's morphological features encode details about its gas content, star formation history, and feedback processes, which play important roles in regulating its growth and evolution. We use deep convolutional neural networks (CNNs) to…

星系天体物理 · 物理学 2020-09-15 John F. Wu

Contrastive learning is one of the fastest growing research areas in machine learning due to its ability to learn useful representations without labeled data. However, contrastive learning is susceptible to feature suppression, i.e., it may…

机器学习 · 计算机科学 2021-11-30 Tianhong Li , Lijie Fan , Yuan Yuan , Hao He , Yonglong Tian , Rogerio Feris , Piotr Indyk , Dina Katabi

Graph contrastive learning (CL) methods learn node representations in a self-supervised manner by maximizing the similarity between the augmented node representations obtained via a GNN-based encoder. However, CL methods perform poorly on…

机器学习 · 计算机科学 2024-06-12 Wenhan Yang , Baharan Mirzasoleiman

Graph-level representations (and clustering/classification based on these representations) are required in a variety of applications. Examples include identifying malicious network traffic, prediction of protein properties, and many others.…

机器学习 · 计算机科学 2024-11-20 Xiang Li , Gagan Agrawal , Rajiv Ramnath , Ruoming Jin

In the domain of recommendation and collaborative filtering, Graph Contrastive Learning (GCL) has become an influential approach. Nevertheless, the reasons for the effectiveness of contrastive learning are still not well understood. In this…

信息检索 · 计算机科学 2024-10-01 Chengkai Liu , Jianling Wang , James Caverlee

Understanding structure-property relationships is an essential yet challenging aspect of materials discovery and development. To facilitate this process, recent studies in materials informatics have sought latent embedding spaces of crystal…

机器学习 · 计算机科学 2025-06-23 Yuta Suzuki , Tatsunori Taniai , Ryo Igarashi , Kotaro Saito , Naoya Chiba , Yoshitaka Ushiku , Kanta Ono

Learning from vertical partitioned data silos is challenging due to the segmented nature of data, sample misalignment, and strict privacy concerns. Federated learning has been proposed as a solution. However, sample misalignment across…

机器学习 · 计算机科学 2025-02-17 Achmad Ginanjar , Xue Li , Wen Hua , Jiaming Pei

We present a multilinear analysis to determine the significant predictors of star formation in galaxies using the combined EDGE-CALIFA sample of galaxies. We analyze 1845 kpc-scale lines of sight across 39 galaxies with molecular line…

Contrastive Learning (CL) performances as a rising approach to address the challenge of sparse and noisy recommendation data. Although having achieved promising results, most existing CL methods only perform either hand-crafted data or…

信息检索 · 计算机科学 2023-11-22 Xiuyuan Qin , Huanhuan Yuan , Pengpeng Zhao , Junhua Fang , Fuzhen Zhuang , Guanfeng Liu , Victor Sheng

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…

计算机视觉与模式识别 · 计算机科学 2024-04-09 Qingshan Hou , Shuai Cheng , Peng Cao , Jinzhu Yang , Xiaoli Liu , Osmar R. Zaiane , Yih Chung Tham