Contrastive Learning

Contrastive learning is a self-supervised machine learning technique that aims to learn robust data representations by contrasting similar and dissimilar data points. Current research focuses on applying contrastive learning to diverse modalities, including images, audio, text, and time-series data, often within multimodal frameworks and using architectures like MoCo and SimCLR, and exploring its application in various tasks such as object detection, speaker verification, and image dehazing. This approach is significant because it allows for effective learning from unlabeled or weakly labeled data, improving model generalization and performance across numerous applications, particularly in scenarios with limited annotated data or significant domain shifts.

Papers

December 19, 2023

DMT: Comprehensive Distillation with Multiple Self-supervised Teachers
Yuang Liu, Jing Wang, Qiang Zhou, Fan Wang, Jun Wang, Wei Zhang
Contrastive Learning Self Supervised Self Supervised Model Multi Level Distillation
Difficulty-Focused Contrastive Learning for Knowledge Tracing with a Large Language Model-Based Difficulty Prediction
Unggi Lee, Sungjun Yoon, Joon Seo Yun, Kyoungsoo Park, YoungHoon Jung, Damji Stratton, Hyeoncheol Kim
Contrastive Learning Large Language Knowledge Tracing Difficulty Level Difficulty Estimation Difficulty Prediction

December 18, 2023

Cross-Age Contrastive Learning for Age-Invariant Face Recognition
Haoyi Wang, Victor Sanchez, Chang-Tsun Li
Contrastive Learning Face Datasets Age Datasets Age Invariant Face Recognition
ContraNovo: A Contrastive Learning Approach to Enhance De Novo Peptide Sequencing
Zhi Jin, Sheng Xu, Xiang Zhang, Tianze Ling, Nanqing Dong, Wanli Ouyang, Zhiqiang Gao, Cheng Chang, Siqi Sun
Contrastive Learning Peptide Source Spectrometry Based Proteomics
Generalized Category Discovery with Large Language Models in the Loop
Wenbin An, Wenkai Shi, Feng Tian, Haonan Lin, QianYing Wang, Yaqiang Wu, Mingxiang Cai, Luyan Wang, Yan Chen, Haiping Zhu, Ping Chen
Contrastive Learning Generalized Category Discovery Active Learning Framework Clustering Friendly Representation

December 16, 2023

Debiasing Multimodal Sarcasm Detection with Contrastive Learning
Mengzhao Jia, Can Xie, Liqiang Jing
Contrastive Learning Sarcasm Detection
Rethinking Dimensional Rationale in Graph Contrastive Learning from Causal Perspective
Qirui Ji, Jiangmeng Li, Jie Hu, Rui Wang, Changwen Zheng, Fanjiang Xu
Contrastive Learning Graph Model Dimensionless Variable Graph Rationale
CONCSS: Contrastive-based Context Comprehension for Dialogue-appropriate Prosody in Conversational Speech Synthesis
Yayue Deng, Jinlong Xue, Yukang Jia, Qifei Li, Yichen Han, Fengping Wang, Yingming Gao, Dengfeng Ke, Ya Li
Contrastive Learning Synthesized Speech Prosodic Feature Contextual Understanding Conversational Speech Synthesis
Event-Based Contrastive Learning for Medical Time Series
Hyewon Jeong, Nassim Oufattole, Matthew Mcdermott, Aparna Balagopalan, Bryan Jangeesingh, Marzyeh Ghassemi, Collin Stultz
Contrastive Learning Heterogeneous Clinical Heart Failure Medical Time Series

December 15, 2023

CARAT: Contrastive Feature Reconstruction and Aggregation for Multi-Modal Multi-Label Emotion Recognition
Cheng Peng, Ke Chen, Lidan Shou, Gang Chen
Contrastive Learning Fine Grained Multimodal Information Multi Modality Data Aggregation Multi Label Emotion Multi Network Contrastive Learning
Pixel-Superpixel Contrastive Learning and Pseudo-Label Correction for Hyperspectral Image Clustering
Renxiang Guan, Zihao Li, Xianju Li, Chang Tang
Contrastive Learning Pseudo Label Hyperspectral Image Clustering Pixel Level Clustering
CLAF: Contrastive Learning with Augmented Features for Imbalanced Semi-Supervised Learning
Bowen Tao, Lan Li, Xin-Chun Li, De-Chuan Zhan
Contrastive Learning Semi Supervised Learning Contrastive Loss Pseudo Labeled Sample Imbalanced Semi Supervised Learning

December 14, 2023

On the Difficulty of Defending Contrastive Learning against Backdoor Attacks
Changjiang Li, Ren Pang, Bochuan Cao, Zhaohan Xi, Jinghui Chen, Shouling Ji, Ting Wang
Contrastive Learning Backdoor Attack Difficulty Level Unsupervised Anomaly
TiMix: Text-aware Image Mixing for Effective Vision-Language Pre-training
Chaoya Jiang, Wei ye, Haiyang Xu, Qinghao Ye, Ming Yan, Ji Zhang, Shikun Zhang
Contrastive Learning Data Augmentation Vision Language Contrastive Loss Cross Modal Contrastive Learning Image Blending
CLIP-guided Federated Learning on Heterogeneous and Long-Tailed Data
Jiangming Shi, Shanshan Zheng, Xiangbo Yin, Yang Lu, Yuan Xie, Yanyun Qu
Contrastive Learning Long Tailed Data Heterogeneous Setting Federated Contrastive Learning

December 13, 2023

Revisiting Recommendation Loss Functions through Contrastive Learning (Technical Report)
Dong Li, Ruoming Jin, Bin Ren
Contrastive Learning Contrastive Loss Technical Report
(Debiased) Contrastive Learning Loss for Recommendation (Technical Report)
Ruoming Jin, Dong Li
Contrastive Learning Contrastive Loss Effective Recommendation Technical Report Mutual Information Loss
Partial Symmetry Detection for 3D Geometry using Contrastive Learning with Geodesic Point Cloud Patches
Gregor Kobsik, Isaak Lim, Leif Kobbelt
Contrastive Learning Point Cloud Shape Completion Symmetry Detection 3D Geometry
Patch-wise Graph Contrastive Learning for Image Translation
Chanyong Jung, Gihyun Kwon, Jong Chul Ye
Contrastive Learning Contrastive Loss Image Translation Graph Contrastive Learning Semantic Correspondence Semantic Encoding
CoRTEx: Contrastive Learning for Representing Terms via Explanations with Applications on Constructing Biomedical Knowledge Graphs
Huaiyuan Ying, Zhengyun Zhao, Yang Zhao, Sihang Zeng, Sheng Yu
Contrastive Learning Knowledge Graph Financial Application Line by Line Explanation BiOmedical Ontology Biomedical Knowledge Graph Unified Medical Language System

Contrastive Learning

Papers

DMT: Comprehensive Distillation with Multiple Self-supervised Teachers

Difficulty-Focused Contrastive Learning for Knowledge Tracing with a Large Language Model-Based Difficulty Prediction

Cross-Age Contrastive Learning for Age-Invariant Face Recognition

ContraNovo: A Contrastive Learning Approach to Enhance De Novo Peptide Sequencing

Generalized Category Discovery with Large Language Models in the Loop

Debiasing Multimodal Sarcasm Detection with Contrastive Learning

Rethinking Dimensional Rationale in Graph Contrastive Learning from Causal Perspective

CONCSS: Contrastive-based Context Comprehension for Dialogue-appropriate Prosody in Conversational Speech Synthesis

Event-Based Contrastive Learning for Medical Time Series

CARAT: Contrastive Feature Reconstruction and Aggregation for Multi-Modal Multi-Label Emotion Recognition

Pixel-Superpixel Contrastive Learning and Pseudo-Label Correction for Hyperspectral Image Clustering

CLAF: Contrastive Learning with Augmented Features for Imbalanced Semi-Supervised Learning

On the Difficulty of Defending Contrastive Learning against Backdoor Attacks

TiMix: Text-aware Image Mixing for Effective Vision-Language Pre-training

CLIP-guided Federated Learning on Heterogeneous and Long-Tailed Data

Revisiting Recommendation Loss Functions through Contrastive Learning (Technical Report)

(Debiased) Contrastive Learning Loss for Recommendation (Technical Report)

Partial Symmetry Detection for 3D Geometry using Contrastive Learning with Geodesic Point Cloud Patches

Patch-wise Graph Contrastive Learning for Image Translation

CoRTEx: Contrastive Learning for Representing Terms via Explanations with Applications on Constructing Biomedical Knowledge Graphs