Results 51 to 60 of about 120,140 (335)
Faithful Contrastive Features in Learning [PDF]
Cognitive Science, 2006 AbstractThis article pursues the idea of inferring aspects of phonological underlying forms directly from surface contrasts by looking at optimality theoretic linguistic systems (Prince & Smolensky, 1993/2004). The main result proves that linguistic systems satisfying certain conditions have the faithful contrastive feature property: Whenever 2 ...
openaire +2 more sources
Contrastive Learning for Fair Representations
CoRR, 2021 Trained classification models can unintentionally lead to biased representations and predictions, which can reinforce societal preconceptions and stereotypes. Existing debiasing methods for classification models, such as adversarial training, are often expensive to train and difficult to optimise.
Aili Shen +4 more
openaire +2 more sources
Supervised contrastive learning for recommendation
Knowledge-Based Systems, 2022 In this work, we aim to consider the application of contrastive learning in the scenario of the recommendation system adequately, making it more suitable for recommendation task. We propose a learning paradigm called supervised contrastive learning(SCL) to support the graph convolutional neural network.
Chun Yang +4 more
openaire +3 more sources
MathematicsGraph contrastive learning has demonstrated significant superiority for collaborative filtering. These methods typically use augmentation technology to generate contrastive views, and then train graph neural networks with contrastive learning as an ...
Jifeng Dong +5 more
doaj +1 more source
Robust age estimation model using group‐aware contrastive learning
IET Image Processing, 2022 Although great efforts have been devoted to developing lightweight models for age estimation in recent works, the robustness is still unsatisfactory in unconstrained environments.
Xiaoqiang Li +4 more
doaj +1 more source
CC-GNN: A Clustering Contrastive Learning Network for Graph Semi-Supervised Learning
IEEE AccessIn graph modeling, scarcity of labeled data is a challenging issue. To address this issue, state-of-the-art graph models learn the representation of graph data via contrastive learning.
Peng Qin +4 more
doaj +1 more source
Prototypical Contrastive Learning of Unsupervised Representations
, 2021 This paper presents Prototypical Contrastive Learning (PCL), an unsupervised representation learning method that addresses the fundamental limitations of instance-wise contrastive learning.
Hoi, Steven C. H. +3 more
core
Contrastive Mask Learning for Self-Supervised 3D Skeleton-Based Action Recognition
SensorsIn 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
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 +4 more
core +1 more source
Top-down neural attention by excitation backprop [PDF]
, 2016 We aim to model the top-down attention of a Convolutional Neural Network (CNN) classifier for generating task-specific attention maps. Inspired by a top-down human visual attention model, we propose a new backpropagation scheme, called Excitation ...
Bargal, Sarah Adel +5 more
core +1 more source