Contrastive Representation Learning: A Framework and Review
Open accessThe DOI matches its Crossref record; 147 of the 162 references it cites were found in a registry or an index, and 15 are not checked yet.
Abstract
Contrastive Learning has recently received interest due to its success in self-supervised representation learning in the computer vision domain. However, the origins of Contrastive Learning date as far back as the 1990s and its development has spanned across many fields and domains including Metric Learning and natural language processing. In this paper, we provide a comprehensive literature review and we propose a general Contrastive Representation Learning framework that simplifies and unifies many different contrastive learning methods. We also provide a taxonomy for each of the components of contrastive learning in order to summarise it and distinguish it from other forms of machine learning. We then discuss the inductive biases which are present in any contrastive learning system and we analyse our framework under different views from various sub-fields of Machine Learning. Examples of how contrastive learning has been applied in computer vision, natural language processing, audio processing, and others, as well as in Reinforcement Learning are also presented. Finally, we discuss the challenges and some of the most promising future research directions ahead.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“According to the suggestions of Le-Khac et al. [29], the main methods can be divided into the following categories: multisensory signals, data augmentation, localglobal consistency, and temporal consistency.”
From Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects (2024) · cites this paper as [29]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Contrastive learning [56-58] is in fact a training procedure used in recent artificial intelligence models as a way to efficiently learn semantic representations.”
From How Adversarial REM Dreams May Facilitate Creativity, and Why We Become Aware of Them (2024) · cites this paper as [56]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“As summarized in [29], commonly used contrastive loss functions generally include scoring functions (cosine similarity), energy-based margin functions (pair loss and triplet loss), probabilistic NCE-based functions, and mutual information based functions.”
From Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects (2024) · cites this paper as [29]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 2×
“In SimCLRv2 [17], empirical experiments show that the output of the second layer of a 3-layer MLP projection head is a better representation for transfer learning than the output of the base ResNet [42] encoder.”
BackgroundMethodVaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 3×
“Recently, the Bidirectional Encoder Representation from Transformer (BERT) [24] model learns bidirectional word representations using the Transformer architecture’s decoder [103] and demonstrated great performance for transfer learning in multiple downstream tasks.”
MethodHochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 1×
“Even though the BERT [24] text encoder and the Faster RCNN [87] object detection model are trained separately and not updated by the contrastive loss, the LSTM cells [48] and a linear project head can still map between words and object representations.”
MethodExploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173 · cited 5×
“The discretised speech representation can then be used directly as a representation for other models that expect discrete input such as BERT [24].”
MethodInfluentialFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325 · cited 5×
“The discretised speech representation can then be used directly as a representation for other models that expect discrete input such as BERT [24].”
MethodInfluentialEfficient Estimation of Word Representations in Vector Space
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1301.3781 · Cited by 26,568
Research works printed but not linked: 1
- stratos, 2019, Noise contrastive estimation
Cited by
Items 801–900 of 948
Flood Mapping Using Contrastive Learning and Semantic Segmentation
Bonalde-Marcano, E. M., & Nuñez, L. A. (2025) · IEEE Colombian Conference on Communications and Computing (COLCOM) · doi:10.1109/colcom66267.2025.11185779
“Contrastive learning, briefly said, is about learning through comparisons, where it can be done between positive pairs of similar inputs and negative pairs of different inputs [4], [5].”
Li, W., Liu, Z., & Lin, G. N. (2025) · Research Square · doi:10.21203/rs.3.rs-7469880/v1
TowerDNA: Fast and Accurate Graph Retrieval With Dividing, Contrasting and Alignment
Yang, J., Gu, Y., Qin, Y., Luo, X., Xiao, Z., Zheng, K., Ju, W., Hua, X., & Zhang, M. (2025) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2025.3621493
“…the information in unlabeled data, we can enhance the inference speed of GR models while maintaining comparable II, despite the strong performance of Info-Graph and ASGN in classification tasks in various studies [59], [92], [93], their superiority does not stand out when dealing with EGR problems.”
Self-supervised contrastive learning for fall detection using 3D vision-based body articulation
Guendoul, O., Tabii, Y., & Thami, R. O. H. (2025) · Mathematical Modeling and Computing · doi:10.23939/mmc2025.03.1012
Human Motion Recognition Based on Videos and Radar Spectrograms in Cross-Target Scenarios
Yang, Y., Song, Y., Shang, X., Mu, Q., Li, B., & Lang, Y. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3619651
“This approach would reduce the adverse effects of identity information on motion recognition [30], [31].”
Degree-aware Progressive Contrastive Learning for Graph Combinatorial Optimization Problems
Zhao, S., Wu, Y., & Zhang, Y. (2025) · Machine Intelligence Research · doi:10.1007/s11633-024-1532-2
Speaker Inference Detection Using Only Text
Cheng, R., Ding, Y., Yuan, S., & Wang, Z. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3537-8_15 · Cited by 4
Graph Representation Learning for Game Provenance
Melo, S. A., Paes, A., & Clua, E. (2025) · Simpósio Brasileiro de Jogos e Entretenimento Digital (SBGames) · doi:10.5753/sbgames_estendido.2025.11584
“Representation learning enables automatic feature extraction from raw data and has become essential in machine learning, especially for graph-structured data, which models complex relationships across diverse domains [Bengio et al. 2013, Le-Khac et al. 2020, Myers et al. 2014].”
Leveraging Contrastive Learning and LightGBM for Classification
Sharna, N. A., & Senturk, I. F. (2025) · International Conference on Computer Science and Engineering (UBMK) · doi:10.1109/ubmk67458.2025.11206807
“By utilizing the concept of learning by comparing samples, it optimizes the model to push different data points (negatives) apart and bring comparable ones (positives) closer together in the embedding space [2].”
Guo, Z., Teng, X., & Liu, J. (2025) · Complex & Intelligent Systems · doi:10.1007/s40747-025-02102-5
“[39, 40].”
Dual-Contrastive Attribute Embedding for Generalized Zero-Shot Learning
Li, Q., Long, Y., Zhang, Z., & Jiang, K. (2025) · Electronics · doi:10.3390/electronics14214341 · Cited by 1
Valle, J. V., & Mattos, D. M. F. (2025) · International Conference on the Network of the Future (NOF) · doi:10.1109/nof66640.2025.11223333
“Contrastive methods are typically discriminative , focusing on modeling the conditional distribution p ( y x ) by first inferring latent variables p ( v x ) , followed by prediction p ( y v ) [14].”
Livne, M. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.19642
Extracting task-relevant preserved dynamics from contrastive aligned neural recordings
Jiang, Y., Sheng, K., Gao, Y., Buchanan, E. K., Shikano, Y., Kim, T. H., Zhao, Y., Woo, S. J., Dinç, F., Linderman, S. W., et al. (2025) · neural information processing systems · doi:10.52202/085713-5376 · Cited by 2
Learning phase diversity for solving ill-posed inverse problems in imaging
Birdi, J., Majumder, T., Halder, D., Kularia, M., & Khare, K. (2026) · Journal of Physics Photonics · doi:10.1088/2515-7647/ae86a1
“When coupled with contrastive learning, a powerful image representation learning framework, this strategy enables models to learn invariant representations from unlabeled or sparsely labeled data leading to improved neural network performance in various computational imaging tasks [17].”
Frequency-Aware Contrastive Loss for Self-Supervised EEG Seizure Detection
Stemikovskaya, K., Manjarrés, D., & Triguero, I. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228971
“In particular, Contrastive Representation Learning (CRL) [5], a subfield of SSL, has shown promising results when applied to images and temporal data such as EEG [6].”
DRA: A Dual Retrieval Architecture for Domain Chinese Spelling Check
Wu, H., Nie, Z., Ji, S., & Song, D. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3346-6_19
An Adaptive Semantic-Aware Fusion Method for Multimodal Entity Linking
Xu, H., Xu, Y., Lin, X., Xu, H., Wang, Y., & Gou, G. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3343-5_12
CeTAD: Towards Certified Toxicity-Aware Distance in Vision Language ModelsPreprint
Yin, X., Liu, J., Chen, Z., Hu, J., Dong, Y., Huang, X., & Ruan, W. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.10661
“Specifically, the cosine similarity between encoded features of two sentences is extensively used to evaluate their physical distance in contrastive learning (Jaiswal et al., 2020; Le-Khac et al., 2020; Liu et al., 2021).”
SMENET: A Multi-View Semantic Model for Multi-Level Enzyme Function Prediction
Zhou, H., Zhang, W., Deng, Z., Wang, G., Wei, Z., Wang, L., Pan, X., Shen, H., Yu, D., & Wu, J. (2025) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbbio.2025.3644035
“To address this issue, one can construct enzyme function prediction models using contrastive learning models [47], [48] or adversarial generative networks [49], [50].”
Entropy-guided partial annotation for cross-domain rib segmentation
Yang, Y., You, K., He, H., Zhang, Y., Feng, X., Lu, F., Fang, L., Wang, Y., & Pan, Q. (2025) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2025.102689
Additive Logistic Mechanism for Privacy-Preserving Self-Supervised LearningPreprint
Yang, Y., Gohari, P., & Topcu, U. (2022) · arXiv (Cornell University) · doi:10.26153/tsw/52361
Alif, A. K., Hossain, S. J., Hossain, M. I., Antor, S. S., & Roy, A. P. (2024) · BRAC University Institutional Repository (BRAC University)
El Oakley, O. (2023) · UCL Discovery (University College London)
Synergier mellan policyinlärning och sampling-baserad planering
Gieselmann, R. (2024) · KTH Publication Database DiVA (KTH Royal Institute of Technology)
Validating Machine Learning-based Highly Automated Driving Functions by Diversity
De Candido, O. T., Utschick, W., & München, T. U. (2023)
Abstract Image Similarity with Pre-Trained Image Embeddings
Kosova, R. (2025) · Theseus (Ammattikorkeakoulujen)
Self-supervised learning for drug discovery
Li, Z., Niu, D., & Deng, Z. (2025) · Elsevier eBooks · doi:10.1016/b978-0-44-332908-1.00017-9
Yuan, H., Yan, Y., Jing, X., & Luo, W. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11229326
“Contrastive learning [22] aims to learn effective representations by defining a contrastive loss function that brings similar samples closer and pushes dissimilar ones apart, yielding enhanced performance in tasks like image classification [9] and natural language processing [23].”
Kusumaningrum, R., Herlambang, A. A., Afifah, W., Wibowo, A., -, S., & Sasongko, P. S. (2025) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2025.0161168
“Contrastive learning is learning by comparison, in which the learning process is performed by comparing different input samples, namely comparisons between positive pairs of similar input and negative pairs of dissimilar input [24].”
Dahal, A. (2023) · Doria (University of Helsinki)
Uncertainty-Decoupled Active Learning for Annotation-Efficient Deep Face Recognition
Huang, Q., Su, J., Huang, W., Chen, Z., Huang, Y., Yang, L., Li, J., & Chen, J. (2025) · International Conference on Advanced Robotics and Mechatronics (ICARM) · doi:10.1109/icarm65671.2025.11293547
“Representation learning aims to extract low-dimensional, high-semantic feature representations from raw data through parameterized mappings, thereby enhancing the performance of downstream tasks such as face recognition and attribute classification [13], [14], [15], [16].”
Contrastive Self-Supervised Domain Adaptive Framework for Cross-Domain Hurricane Damage Assessment
Talreja, P. V., Durbha, S. S., Shreelakshmi, C. R., Mahajan, C., & Singh, G. (2025) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss55030.2025.11313890
Double masked sub-representations for contrastive learning withsmall-batch trainingPreprint
Leng, Q., Yuan, G., Yi, G., Fan, X., & Wang, C. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5987338
A Contrastive Learning-Based Multi-scale Attention Model for Text Recognition
Li, Z., Wan, L., Meng, X., Zhang, Y., Ni, W., & Luo, H. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-3483-8_20
AI Approaches for Constructing Digital Transcriptomics
Das, S., & Maity, S. (2026) · IGI Global eBooks · doi:10.4018/979-8-3373-4849-0.ch011
Yao, H. (2025) · IEEE International Conference on Advances in Electrical Engineering and Computer Applications (AEECA) · doi:10.1109/aeeca65693.2025.00133
“Recent studies reveal that 68% of users attempt to issue such context-rich commands, exposing the inability of traditional rule-based systems to handle linguistic diversity and ambiguity effectively [3].”
Self-supervised Representation Learning for Anomaly Detection in Brain MRI
Safdar, S., Jamıl, A., Hameed, A. A., & Ahmed, S. B. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-13921-4_49
COS-META: Enhancing Few-Shot Node Classification with Contrastive Meta-Learning
Prince, M. S. M., & Dividino, R. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-13513-1_2
Adaptive Weighting Contrastive Learning for Spatial Domain Identification in Spatial Transcriptomics
Li, X., Dai, L.-Y., Shang, J., Zhu, R., & Li, F. (2025) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm66473.2025.11356799
Zhang, S., Wang, Z., & Kharrazi, H. H. K. (2025) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm66473.2025.11356803
“In particular, contrastive learning principles [17] have been introduced to encourage the student to learn embedding spaces that are close to the teacher for corresponding inputs while remaining separated from unrelated ones [18].”
Simulation Method for Considering the Lag of Turbulent Evapotranspiration
Shu, Y., Zhang, K., Duan, H., & Wu, L. (2026) · Ecohydrology · doi:10.1002/eco.70184 · Cited by 1
Kruse, M., Böhnke, D., & Neustock, J. (2026) · Procedia CIRP · doi:10.1016/j.procir.2025.09.047
Wang, J., Jin, X., Tang, R., Zeng, Z., Lin, Z., Li, Y., & Chen, Y. (2026) · Scientific Reports · doi:10.1038/s41598-026-39857-x
Li, Z., Zhang, S., & Stamos, I. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00254
“Contrastive Learning Contrastive learning [22] has played an important role in representation learning, aiming to bring similar data points closer in feature space while pushing dissimilar ones apart.”
Generation and Generalized Detection of Fully Synthetic Photorealistic Images
Olán, T. (2023) · Tampere University Institutional Repository (Tampere University) · Cited by 1
Augmentation-Free Contrastive Learning for Few-Shot Hindi Fake News Detection
Rajee, S. M., & Praseed, A. (2025) · International Conference on Smart and Intelligent Systems (SISCON) · doi:10.1109/siscon66686.2025.11409014
Learning for Robust EEG-Based Person Identification
Tabatabaei, M., & Shamsollahi, M. B. (2025) · National and International Iranian Conference on Biomedical Engineering (ICBME) · doi:10.1109/icbme68496.2025.11392419
“In simple terms, contrastive learning trains the model to pull together EEG signal representations from the same person and push apart those from different people [26], [27].”
Pombero, B. L. (2025) · UNED repository · Cited by 1
Representation learning and deep neural approaches for international trade product classification
Anggoro, A. W. (2025) · ORCA Online Research @Cardiff (Cardiff University)
Xu, S., Ding, S., Shao, B., & Lu, X. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133292
A Review of Image Inpainting and Restoration Based on Few-Shot Learning
王, 永. (2026) · Artificial Intelligence and Robotics Research · doi:10.12677/airr.2026.152048
Text-Aware Contrastive Learning for Bridging Graph Components in a Joint Embedding SpacePreprint
Farhan, A., Rahman, M., Akbar, M., & Hossain, M. S. (2026) · Research Square · doi:10.21203/rs.3.rs-8896676/v1
Li, Y., Shen, C., Zhan, W., Xu, B., Yang, Y., Zhang, X., Wang, H., Zhao, C., & Jian, H. (2026) · Journal of Semiconductors · doi:10.1088/1674-4926/25070029
Prawira, N. A., Firmansyah, M. E., Marutho, D., Ouhab, A., & Ilham, A. (2026) · Journal of Intelligent Computing & Health Informatics · doi:10.26714/jichi.v7i1.20179
Abid, M., Benkaddour, M. K., Benouis, M., & Can, Y. S. (2026) · Cluster Computing · doi:10.1007/s10586-026-06047-3
“That will involve minimizing the loss function concerning distance between positive pairs while maximizing regarding negative pairings [ 35 ].”
Thi, Q.-T. P., Pham, A. D. V., Nguyen, T.-T., & Dang, T.-H. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-18159-6_40
Enhancing Zero-Shot Learning with Non-linear Visual-Semantic Mapping and Dual Loss
Le, T. T., Tran, H. C., & Nguyen, D. C. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-18159-6_29
Agrawal, D. V., Gupta, V., & Krishna, C. R. (2026) · Journal of Transportation Engineering Part B Pavements · doi:10.1061/jpeodx.pveng-1768
Unsupervised pretraining of state representations in a rewardless environment
Merckling, A. (2021) · theses.fr (ABES) · doi:10.70675/e5589029zb8c4z4364zb923zbb4c70deaaf9
Passage Retrieval in Standardization Documents
Albarede, L. (2023) · theses.fr (ABES) · doi:10.70675/00952a66z742az4995zb6c4z4e58ac198642
Self-supervised learning in the presence of limited labelled data for digital histopathology
Nisar, Z. (2024) · theses.fr (ABES) · doi:10.70675/a7943d75z63f1z4364z833fz8f3c70b639a5
Low Bitrate Face Video Compression with Generative Animation Models
Konuko, G. (2025) · theses.fr (ABES) · doi:10.70675/478ecc9az4adez4d1dzb4c7z37d2f6f05ac5
Feasibility of Interactions and Network Inference of Online Social Networks
Papanastasiou, E. (2024) · theses.fr (ABES) · doi:10.70675/dca5b034z74b1z47b5z80e7z67e704a701d5
Modèles de comportement et loi de défaillance de systèmes enrichis par les données
Suhas, M. (2024) · theses.fr (ABES) · doi:10.70675/798980bfz6736z4376z97a4z8533e0af90c1
Répondre aux questions visuelles à propos d'entités nommées
Lerner, P. J. (2023) · theses.fr (ABES) · doi:10.70675/78c96766zfc95z4da8zb67aze67555da6c75 · Cited by 1
Transcription de documents historiques avec des algorithmes de Deep Learning
Fizaine, F. C. (2024) · theses.fr (ABES) · doi:10.70675/5157ea2fz46c2z4525za138z22cc7ca1b63c
Advancements in Multimodal and Unsupervised Learning with Application to Recommender Systems
Khalafaoui, Y. (2024) · theses.fr (ABES) · doi:10.70675/dd7b8948z0036z499dz99dez131402d47938
Apprentissage auto-supervisé pour la détection d'anomalies dans des séries temporelles
Bailly, R. (2023) · theses.fr (ABES) · doi:10.70675/6677e929z05a9z4321zbbebz1f050c4b0abf
Deep generative models for the detection of subtle phenotypes in microscopy images
Bourou, A. (2025) · theses.fr (ABES) · doi:10.70675/f16ad5c8z12b4z4b25z901ezacfc784cd32e
Enhancing surrogate regression methods for structured prediction : An odyssey with loss functions
Junjie, Y. A. N. G. (2025) · theses.fr (ABES) · doi:10.70675/8a087025za007z4013zaa7dz6fde23f91948
Manouvriez, D. (2025) · theses.fr (ABES) · doi:10.70675/bc259a39zb9faz4c92z95cbz9326a9391af3
Volting ˸ a wheelchair and human-machine interface for physical activity
Rocha, J. M. (2025) · theses.fr (ABES) · doi:10.70675/443e5d48z16bdz43f4z9d66z2689dc3732e8
Contrastive multimodal deep learning for survival prediction in grade 2/3 gliomas
Hua, P., Lin, C.-C., Fenlon, T., Liu, X., & Hassanpour, S. (2026) · JNCI Cancer Spectrum · doi:10.1093/jncics/pkag039
“24,25 It is a representation learning approach that trains models to bring related samples closer together in the embedding space while pushing unrelated samples farther apart, therefore producing more informative, generalizable representations.”
Jiang, Y., Guo, Y., & Hu, A. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3685438
“Alternatively, other assumptions and architectural constraints can be applied to prevent the trivial minimization of pairwise distances [30].”
Martino, L. (2026) · Research Square · doi:10.21203/rs.3.rs-9368004/v1
Complex-Scene-Oriented Autonomous Decision-Making Method for UAVs
Qu, H., & Zou, J. (2026) · Electronics · doi:10.3390/electronics15081757
Contrastive learning for the classification of herbarium specimens of the Piperaceae family
Vieira, A. D. S. (2025) · Institutional Repository of the Federal Technological University of Paraná (RIUT) (Federal University of Technology – Paraná)
Boosting commit classification with contrastive learning
Tong, J., Wang, Z., & Rui, X. (2026) · Journal of Systems and Software · doi:10.1016/j.jss.2026.112924
Sousa, J., Darabi, R., Sousa, A. J., Brueckner, F. P., Reis, L. P., & Reis, A. (2026) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2026.104771
Self-supervised learning model leveraging structural similarity index for glaucoma recognition
Frasca, M., Lin, J., & Torre, D. L. (2025) · International Conference on Decision Aid Sciences and Applications (DASA) · doi:10.1109/dasa68193.2025.11498861
“Similarity is measured using cosine similarity, and the model is trained with the NT-Xent Loss (Normalized Temperature-scaled Cross-Entropy Loss) [32].”
Sun, Y., Pang, S., Li, H., Wang, W., & Qiao, S. (2026) · Journal of Applied Geophysics · doi:10.1016/j.jappgeo.2026.106310
Huang, X., Liu, D. Y., Liang, Q., Guo, Z., Wang, F., & Yang, C. (2026) · Smart Agricultural Technology · doi:10.1016/j.atech.2026.102195
Ali, A., Yu, Q., Ren, Z., Li, H., Zhang, Y., Chengfu, L., Ullah, N., Yuan, R., Wang, T., Lv, Y., et al. (2026) · Geological Journal · doi:10.1002/gj.70318
Data-driven AI system for learning how to run transcript assemblers
Shen, Y., Yan, Z., & Kingsford, C. (2026) · Genome biology · doi:10.1186/s13059-026-04085-z · Cited by 1
An exploration of contrastive self-supervised learning for reconstructed atom probe tomography data
Sälker, J. A., Hans, M., Schneider, J. M., & Hadian, R. (2026) · Machine Learning Science and Technology · doi:10.1088/2632-2153/ae5c57
Variational views for self-supervised learning in radio astronomy
Alphonse, J. J., & Scaife, A. M. M. (2026) · RAS Techniques and Instruments · doi:10.1093/rasti/rzag037
Large models for battery prognostics and health management: A review and future roadmap
Liu, J., Wang, H., Wang, W., Zhu, R., Wang, Q., & Xie, M. (2026) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2026.117120 · Cited by 1
Rosa, D. D. L., del Jesús, M. J., & Charte, F. (2026) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai68641.2026.11536561
When Softmax Fails at the Top: Extreme Value Corrections for InfoNCEPreprint
Erol, M., Evren, S., Ozel, O., Morgan, A., Ryu, J. J., & Zheng, L. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.00262
“…and InfoNCE or closely related softmax-based objectives sit at the core of many influential methods in vision, language, and multimodal learning (Jaiswal et al., 2021; Le-Khac et al., 2020; van den Oord et al., 2018; Chen et al., 2020; He et al., 2020; Gao et al., 2022; Radford et al., 2021).”
Zewail, R., & Mokhtar, B. M. (2026) · Advanced Intelligent Systems · doi:10.1002/aisy.202501454
“We utilize the conventional Euclidean-based contrastive loss [50], which encourages similar pairs to be closer in the embedding space while pushing dissimilar pairs apart by a margin m .”
CaRgo: contrastive representation learning for anomaly detection in multi-relational graphs
Aktaş, M. Y., Coşkun, M., & Lu, C. (2026) · Social Network Analysis and Mining · doi:10.1007/s13278-026-01612-5
Patient-Aware Contrastive Learning Preserves Per-Patient Structure in RR-Interval RepresentationsPreprint
Niroshana, Y., Wimalasiri, W. M., & Hettiarachchi, C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.23570
“Contrastive representation learning is now the default for unlabeled and weakly-labeled time-series and physiological signals (Chen et al., 2020; Le-Khac et al., 2020; Wang & Isola, 2020; Khosla et al., 2021).”
Self-supervised Learning for Audio Signal
Sun, Y., Xu, Q., Zhu, B., Chen, W., Sun, Y., & Xu, K. (2026) · Springer eBooks · doi:10.1007/978-981-95-0836-5_4
Visual Analytics Pathway III: Data Engineering
Yousef, I., Shah, S. L., & Gopaluni, R. B. (2026) · Synthesis lectures on emerging engineering technologies · doi:10.1007/978-3-032-22126-1_5
Degradation of Feature Space in Continual Learning
Lanza, C., Pereira, R., Miozzo, M., Angelats, E., & Dini, P. (2026) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomworkshops68308.2026.11585332
“Contrastive learning [2] has emerged as an effective framework for learning structured feature spaces.”
Brain-to-Language Model: Decoding Semantic Speech Representations from EEG via Cross-Modal Alignment
Engström, J., & O'Brien, E. (2026) · Lund University Publications Student Papers (Lund University)
An Initial Exploration of Contrastive Prompt Tuning to Generate Energy-Efficient Code
Weidmann, S., & Castor, F. (2026) · International Workshop on Large Language Models for Code (LLM4Code) · doi:10.1145/3786181.3788718
“IthasbeenusedinvariousMLtasks,especially representation learning for vision and NLP tasks [12].”
Rifqi, R. M., & Muhamad, A. H. (2026) · Journal of Informatics and Electronics Engineering · doi:10.70428/jiee.v6i01.1599
“…merupakan efek yang lazim sesuai pada penelitian Zhang (2024) dimana fungsi objektif Contrastive Learning adalah untuk memaksakan penyebaran representasi secara merata [15], [18], sehingga model mengorbankan ketajaman prediksi pada item-item berinteraksi tinggi demi mengeksplorasi item long tail .”
Metadata
- Authors
- Le-Khac, P. H., Healy, G., & Smeaton, A. F.
- Affiliations
- Dublin City University (IE)
- Venue
- IEEE Access
- Published
- 2020
- Volume
- 8
- Pages
- 193907-193934
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W3096655658
- Cited by
- 862
- References
- 144
- Citations by year
- 2026: 111 · 2025: 197 · 2024: 212 · 2023: 157 · 2022: 113 · 2021: 71 · 2020: 1
- FWCI
- 33.61
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- IEEE Access (publishedVersion, cc-by)
- arXiv (Cornell University) (acceptedVersion)
- Dublin City University Open Access Institutional Repository (Dublin City University) (submittedVersion, cc-by)
- Arrow@dit (Dublin Institute of Technology) (submittedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- arXiv (Cornell University) (cc-by)
- Funders
- Science Foundation Ireland through the Science Foundation Ireland (SFI) Centre for Research Training in Machine Learning (18/CRT/6183)
- Insight Centre for Data Analytics (SFI/12/RC/2289_P2)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Algorithms
- Keywords
- contrastive learning, representation learning, self-supervised learning, metric learning, inductive bias, computer vision, natural language processing, audio signal processing, reinforcement learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.