Results 31 to 40 of about 14,201 (266)
Contrastive Learning and Neural Oscillations [PDF]
Neural Computation, 1991 The concept of Contrastive Learning (CL) is developed as a family of possible learning algorithms for neural networks. CL is an extension of Deterministic Boltzmann Machines to more general dynamical systems. During learning, the network oscillates between two phases. One phase has a teacher signal and one phase has no teacher signal.
Baldi, Pierre, Pineda, Fernando
openaire +3 more sources
Contrastive Fairness in Machine Learning [PDF]
IEEE Letters of the Computer Society, 2020 Was it fair that Harry was hired but not Barry? Was it fair that Pam was fired instead of Sam? How can one ensure fairness when an intelligent algorithm takes these decisions instead of a human? How can one ensure that the decisions were taken based on merit and not on protected attributes like race or sex? These are the questions that must be answered
Tapabrata Chakraborti +2 more
openaire +2 more sources
Contrastive Attraction and Contrastive Repulsion for Representation Learning
Trans. Mach. Learn. Res., 2021 Contrastive learning (CL) methods effectively learn data representations in a self-supervision manner, where the encoder contrasts each positive sample over multiple negative samples via a one-vs-many softmax cross-entropy loss. By leveraging large amounts of unlabeled image data, recent CL methods have achieved promising results when pretrained on ...
Huangjie Zheng +9 more
openaire +3 more sources
Signal Contrastive Enhanced Graph Collaborative Filtering for Recommendation
Data Science and Engineering, 2023 Graph collaborative filtering methods have shown great performance improvements compared with deep neural network-based models. However, these methods suffer from data sparsity and data noise problems.
Zhi-Yuan Li +3 more
doaj +1 more source
A Framework Using Contrastive Learning for Classification with Noisy Labels
Data, 2021 We propose a framework using contrastive learning as a pre-training task to perform image classification in the presence of noisy labels. Recent strategies, such as pseudo-labeling, sample selection with Gaussian Mixture models, and weighted supervised ...
Madalina Ciortan +2 more
doaj +1 more source
IEEE Access, 2023 Self-supervised learning has been shown to be effective in various fields, proving its usefulness in contrastive learning. Recently, graph contrastive learning has shown state-of-the-art performance in the recommendation task.
Sanghun Kim, Hyeryung Jang
doaj +1 more source
Self-supervised Dynamic Graph Representation Learning Approach Based on Contrastive Prediction [PDF]
Jisuanji kexue, 2023 In recent years,graph self-supervised learning represented by graph contrastive learning has become a hot research to-pic in the field of graph learning.This learning paradigm does not depend on node labels and has good generalization ability.However ...
JIANG Linpu, CHEN Kejia
doaj +1 more source
SC-FGCL: Self-Adaptive Cluster-Based Federal Graph Contrastive Learning
IEEE Open Journal of the Computer Society, 2023 As a self-supervised learning method, the graph contrastive learning achieve admirable performance in graph pre-training tasks, and can be fine-tuned for multiple downstream tasks such as protein structure prediction, social recommendation, etc.
Tingqi Wang +4 more
doaj +1 more source
Poisoning and Backdooring Contrastive Learning
CoRR, 2021 Multimodal contrastive learning methods like CLIP train on noisy and uncurated training datasets. This is cheaper than labeling datasets manually, and even improves out-of-distribution robustness. We show that this practice makes backdoor and poisoning attacks a significant threat.
Nicholas Carlini, Andreas Terzis
openaire +3 more sources
MoCoUTRL: a momentum contrastive framework for unsupervised text representation learning
Connection Science, 2023 This paper presents MoCoUTRL: a Momentum Contrastive Framework for Unsupervised Text Representation Learning. This model improves two aspects of recently popular contrastive learning algorithms in natural language processing (NLP).
Ao Zou +4 more
doaj +1 more source