Results 41 to 50 of about 115,093 (312)

Prototypical Graph Contrastive Learning

IEEE Transactions on Neural Networks and Learning Systems
Graph-level representations are critical in various real-world applications, such as predicting the properties of molecules. However, in practice, precise graph annotations are generally very expensive and time-consuming. To address this issue, graph contrastive learning constructs an instance discrimination task, which pulls together positive pairs ...
Shuai Lin, Chen Liu, Pan Zhou, Zi-Yuan Hu, Shuojia Wang, Ruihui Zhao, Yefeng Zheng, Liang Lin, Eric Xing, Xiaodan Liang   +9 more
openaire   +3 more sources

Supervised Contrastive Learning

, 2020
Contrastive learning applied to self-supervised representation learning has seen a resurgence in recent years, leading to state of the art performance in the unsupervised training of deep image models. Modern batch contrastive approaches subsume or significantly outperform traditional contrastive losses such as triplet, max-margin and the N-pairs loss.
Khosla, Prannay, Teterwak, Piotr, Wang, Chen, Sarna, Aaron, Tian, Yonglong, Isola, Phillip, Maschinot, Aaron, Liu, Ce, Krishnan, Dilip   +8 more
openaire   +2 more sources

Unsupervised learning with contrastive latent variable models

, 2018
In unsupervised learning, dimensionality reduction is an important tool for data exploration and visualization. Because these aims are typically open-ended, it can be useful to frame the problem as looking for patterns that are enriched in one dataset ...
Ghosh, Soumya, Ng, Kenney, Severson, Kristen   +2 more
core   +1 more source

Contrastive Mask Learning for Self-Supervised 3D Skeleton-Based Action Recognition

Sensors
In this paper, we propose a contrastive mask learning (CML) method for self-supervised 3D skeleton-based action recognition. Specifically, the mask modeling mechanism is integrated into multi-level contrastive learning with the aim of forming a mutually ...
Haoyuan Zhang
doaj   +1 more source

Graph Clustering with High-Order Contrastive Learning

Entropy, 2023
Graph clustering is a fundamental and challenging task in unsupervised learning. It has achieved great progress due to contrastive learning. However, we find that there are two problems that need to be addressed: (1) The augmentations in most graph ...
Wang Li, En Zhu, Siwei Wang, Xifeng Guo
doaj   +1 more source

Psychological Safety Among Interprofessional Pediatric Oncology Teams in Germany: A Nationwide Survey

Pediatric Blood &Cancer, EarlyView.
ABSTRACT Background Psychological safety (PS) is essential for teamwork, communication, and patient safety in complex healthcare environments. In pediatric oncology, interprofessional collaboration occurs under high emotional and organizational demands. Low PS may increase stress, burnout, and adverse events.
Alexandros Rahn, Anna‐Lena Herbach, Christian Bock, Katharina Fleig, Urs Mücke   +4 more
wiley   +1 more source

Deep Metric Learning with Angular Loss

, 2017
The modern image search system requires semantic understanding of image, and a key yet under-addressed problem is to learn a good metric for measuring the similarity between images.
Lin, Yuanqing, Liu, Xiao, Wang, Jian, Wen, Shilei, Zhou, Feng   +4 more
core   +1 more source

Predicting the Future Burden of Renal Replacement Therapy in Türkiye Using National Registry Data and Comparative Modeling Approaches

Therapeutic Apheresis and Dialysis, EarlyView.
ABSTRACT Background Chronic kidney disease is a growing public health problem worldwide, and the number of patients requiring renal replacement therapy is steadily increasing. Türkiye has experienced a similar rise in both the incidence and prevalence of renal replacement therapy over the past decades; however, national‐level projections of future ...
Arzu Akgül, Neriman Sıla Koç, Berrak Itır Aylı   +2 more
wiley   +1 more source

Study on Graph Collaborative Filtering Model Based on FeatureNet Contrastive Learning [PDF]

Jisuanji kexue
Graph-based collaborative filtering recommendation techniques have gained significant attention for their ability to efficiently process large-scale interaction data.However,the effectiveness of these techniques is limited by the sparsity of data in real-
WU Pengyuan, FANG Wei
doaj   +1 more source

An Unsupervised Band Selection Method via Contrastive Learning for Hyperspectral Images

Remote Sensing, 2023
Band selection (BS) is an efficacious approach to reduce hyperspectral information redundancy while preserving the physical meaning of hyperspectral images (HSIs).
Xiaorun Li, Yufei Liu, Ziqiang Hua, Shuhan Chen   +3 more
doaj   +1 more source