{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T00:55:48Z","timestamp":1781312148577,"version":"3.54.1"},"reference-count":64,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100007930","name":"Xiangtan University","doi-asserted-by":"publisher","award":["XDCX2024Y278"],"award-info":[{"award-number":["XDCX2024Y278"]}],"id":[{"id":"10.13039\/501100007930","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019091","name":"Key Research and Development Program of Hunan Province of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100019091","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016104","name":"Key Project of Research and Development Plan of Hunan Province","doi-asserted-by":"publisher","award":["2024JK2004"],"award-info":[{"award-number":["2024JK2004"]}],"id":[{"id":"10.13039\/100016104","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.eswa.2026.132355","type":"journal-article","created":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T23:14:29Z","timestamp":1775517269000},"page":"132355","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Understanding InfoNCE: Transition probability matrix induced feature clustering"],"prefix":"10.1016","volume":"322","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4342-8029","authenticated-orcid":false,"given":"Ge","family":"Cheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7119-1084","authenticated-orcid":false,"given":"Shuo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"7","key":"10.1016\/j.eswa.2026.132355_bib0001","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3544558","article-title":"A survey on data augmentation for text classification","volume":"55","author":"Bayer","year":"2022","journal-title":"ACM Computing Surveys"},{"issue":"6356","key":"10.1016\/j.eswa.2026.132355_bib0002","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1038\/355161a0","article-title":"Self-organizing neural network that discovers surfaces in random-dot stereograms","volume":"355","author":"Becker","year":"1992","journal-title":"Nature"},{"issue":"suppl_1","key":"10.1016\/j.eswa.2026.132355_bib0003","doi-asserted-by":"crossref","first-page":"i47","DOI":"10.1093\/bioinformatics\/bti1007","article-title":"Protein function prediction via graph kernels","volume":"21","author":"Borgwardt","year":"2005","journal-title":"Bioinformatics (Oxford, England)"},{"key":"10.1016\/j.eswa.2026.132355_bib0004","doi-asserted-by":"crossref","unstructured":"Cer, D., Diab, M., Agirre, E., Lopez-Gazpio, I., & Specia, L. (2017). Semeval-2017 task 1: Semantic textual similarity-multilingual and cross-lingual focused evaluation. arXiv: 1708.00055.","DOI":"10.18653\/v1\/S17-2001"},{"key":"10.1016\/j.eswa.2026.132355_bib0005","series-title":"International conference on machine learning","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"10.1016\/j.eswa.2026.132355_bib0006","unstructured":"Chen, X., Fan, H., Girshick, R., & He, K. (2020b). Improved baselines with momentum contrastive learning.arXiv: 2003.04297."},{"key":"10.1016\/j.eswa.2026.132355_bib0007","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"15750","article-title":"Exploring simple siamese representation learning","author":"Chen","year":"2021"},{"key":"10.1016\/j.eswa.2026.132355_bib0008","doi-asserted-by":"crossref","unstructured":"Chen*, X., Xie*, S., & He, K. (2021). An empirical study of training self-supervised vision transformers. arXiv: 2104.02057.","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"10.1016\/j.eswa.2026.132355_bib0009","series-title":"2005\u202fIEEE computer society conference on computer vision and pattern recognition (CVPR\u201905)","first-page":"539","article-title":"Learning a similarity metric discriminatively, with application to face verification","volume":"vol. 1","author":"Chopra","year":"2005"},{"key":"10.1016\/j.eswa.2026.132355_bib0010","series-title":"European conference on computer vision","first-page":"290","article-title":"Fast-moco: Boost momentum-based contrastive learning with combinatorial patches","author":"Ci","year":"2022"},{"key":"10.1016\/j.eswa.2026.132355_bib0011","series-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","author":"Coates","year":"2011"},{"key":"10.1016\/j.eswa.2026.132355_bib0012","unstructured":"van den, O. A., Li, Y., & Vinyals, O. (2018). Representation learning with contrastive predictive coding. .arXiv: 1807.03748."},{"key":"10.1016\/j.eswa.2026.132355_bib0013","unstructured":"Deng, Z., Shi, J., Zhang, H., Cui, P., Lu, C., & Zhu, J. (2022). Neural eigenfunctions are structured representation learners.arXiv: 2210.12637>."},{"key":"10.1016\/j.eswa.2026.132355_bib0014","series-title":"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)","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.eswa.2026.132355_bib0015","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"9588","article-title":"With a little help from my friends: Nearest-neighbor contrastive learning of visual representations","author":"Dwibedi","year":"2021"},{"key":"10.1016\/j.eswa.2026.132355_bib0016","doi-asserted-by":"crossref","unstructured":"Fang, H., Wang, S., Zhou, M., Ding, J., & Xie, P. (2020). Cert: Contrastive self-supervised learning for language understanding.arXiv: 2005.12766.","DOI":"10.36227\/techrxiv.12308378"},{"key":"10.1016\/j.eswa.2026.132355_bib0017","series-title":"EMNLP 2021-2021 conference on empirical methods in natural language processing, proceedings","article-title":"SimCSE: Simple contrastive learning of sentence embeddings","author":"Gao","year":"2021"},{"key":"10.1016\/j.eswa.2026.132355_bib0018","first-page":"21271","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","volume":"33","author":"Grill","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132355_bib0019","series-title":"2006\u202fIEEE computer society conference on computer vision and pattern recognition (CVPR\u201906)","first-page":"1735","article-title":"Dimensionality reduction by learning an invariant mapping","volume":"vol. 2","author":"Hadsell","year":"2006"},{"key":"10.1016\/j.eswa.2026.132355_bib0020","series-title":"International conference on machine learning","first-page":"4116","article-title":"Contrastive multi-view representation learning on graphs","author":"Hassani","year":"2020"},{"key":"10.1016\/j.eswa.2026.132355_bib0021","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"9729","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He","year":"2020"},{"key":"10.1016\/j.eswa.2026.132355_bib0022","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.eswa.2026.132355_bib0023","series-title":"International conference on learning representations","article-title":"Learning deep representations by mutual information estimation and maximization","author":"Hjelm","year":"2018"},{"key":"10.1016\/j.eswa.2026.132355_bib0024","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132355_bib0025","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Sant, G., Moryossef, A., M\u00fcller, M., Sennrich, R., & Ebling, S. (2024). SignCLIP: Connecting text and sign language by contrastive learning. https:\/\/arxiv.org\/abs\/2407.01264.","DOI":"10.18653\/v1\/2024.emnlp-main.518"},{"key":"10.1016\/j.eswa.2026.132355_bib0026","unstructured":"Jing, L., Vincent, P., LeCun, Y., & Tian, Y. (2021). Understanding dimensional collapse in contrastive self-supervised learning.arXiv: 2110.09348."},{"key":"10.1016\/j.eswa.2026.132355_bib0027","unstructured":"Ju, W., Wang, Y., Qin, Y., Mao, Z., Xiao, Z., Luo, J., Yang, J., Gu, Y., Wang, D., Long, Q. et al. (2024). Towards graph contrastive learning: A survey and beyond.arXiv: 2405.11868."},{"key":"10.1016\/j.eswa.2026.132355_bib0028","first-page":"21798","article-title":"Hard negative mixing for contrastive learning","volume":"33","author":"Kalantidis","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132355_bib0029","unstructured":"Khan, A., Asmatullah, L., Malik, A., Khan, S., & Asif, H. (2025). A survey on self-supervised contrastive learning for multimodal text-image analysis. arXiv: 2503.11101."},{"key":"10.1016\/j.eswa.2026.132355_bib0030","first-page":"18661","article-title":"Supervised contrastive learning","volume":"33","author":"Khosla","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132355_bib0031","unstructured":"Koromilas, P., Bouritsas, G., Giannakopoulos, T., Nicolaou, M., & Panagakis, Y. (2024). Bridging mini-batch and asymptotic analysis in contrastive learning: From InfoNCE to kernel-based losses. .arXiv: 2405.18045."},{"key":"10.1016\/j.eswa.2026.132355_bib0032","unstructured":"Krizhevsky, A. (2009). Learning multiple layers of features from tiny images. Master\u2019s thesis, University of Tront."},{"key":"10.1016\/j.eswa.2026.132355_bib0033","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"13918","article-title":"Timesurl: Self-supervised contrastive learning for universal time series representation learning","volume":"vol. 38","author":"Liu","year":"2024"},{"key":"10.1016\/j.eswa.2026.132355_bib0034","unstructured":"Lu, Y., Zhang, G., Sun, S., Guo, H., & Yu, Y. (2024). f-MICL: Understanding and generalizing InfoNCE-based contrastive learning..arXiv: 2402.10150."},{"key":"10.1016\/j.eswa.2026.132355_bib0035","series-title":"Proceedings of the 8th international workshop on semantic evaluation (semeval 2014)","first-page":"1","article-title":"Semeval-2014 task 1: Evaluation of compositional distributional semantic models on full sentences through semantic relatedness and textual entailment","author":"Marelli","year":"2014"},{"key":"10.1016\/j.eswa.2026.132355_bib0036","unstructured":"Morris, C., Kriege, N. M., Bause, F., Kersting, K., Mutzel, P., & Neumann, M. (2020). Tudataset: A collection of benchmark datasets for learning with graphs. .arXiv: 2007.08663."},{"key":"10.1016\/j.eswa.2026.132355_bib0037","article-title":"Wasserstein dependency measure for representation learning","volume":"32","author":"Ozair","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132355_bib0038","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1016\/j.neunet.2022.12.012","article-title":"Improving fine-tuning of self-supervised models with contrastive initialization","volume":"159","author":"Pan","year":"2023","journal-title":"Neural Networks"},{"key":"10.1016\/j.eswa.2026.132355_bib0039","series-title":"International conference on machine learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.eswa.2026.132355_bib0040","unstructured":"Robinson, J., Chuang, C.-Y., Sra, S., & Jegelka, S. (2020). Contrastive learning with hard negative samples. arXiv: 2010.04592."},{"key":"10.1016\/j.eswa.2026.132355_bib0041","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10684","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"key":"10.1016\/j.eswa.2026.132355_bib0042","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"Imagenet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.eswa.2026.132355_bib0043","series-title":"International conference on machine learning","first-page":"5628","article-title":"A theoretical analysis of contrastive unsupervised representation learning","author":"Saunshi","year":"2019"},{"issue":"1","key":"10.1016\/j.eswa.2026.132355_bib0044","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on image data augmentation for deep learning","volume":"6","author":"Shorten","year":"2019","journal-title":"Journal of Big Data"},{"key":"10.1016\/j.eswa.2026.132355_bib0045","article-title":"Improved deep metric learning with multi-class n-pair loss objective","volume":"29","author":"Sohn","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132355_bib0046","series-title":"ICLR","article-title":"Contrastive learning is spectral clustering on similarity graph","author":"Tan","year":"2024"},{"key":"10.1016\/j.eswa.2026.132355_bib0047","series-title":"Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, proceedings, part XI 16","first-page":"776","article-title":"Contrastive multiview coding","author":"Tian","year":"2020"},{"key":"10.1016\/j.eswa.2026.132355_bib0048","series-title":"Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, proceedings, part XI 16","first-page":"776","article-title":"Contrastive multiview coding","author":"Tian","year":"2020"},{"key":"10.1016\/j.eswa.2026.132355_bib0049","unstructured":"Tishby, N., Pereira, F. C., & Bialek, W. (2000). The information bottleneck method. arXiv preprint physics\/0004057."},{"key":"10.1016\/j.eswa.2026.132355_bib0050","series-title":"9th international conference on learning representations, ICLR 2021","article-title":"Self-supervised representation learning with relative predictive coding","author":"Tsai","year":"2021"},{"key":"10.1016\/j.eswa.2026.132355_bib0051","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2495","article-title":"Understanding the behaviour of contrastive loss","author":"Wang","year":"2021"},{"key":"10.1016\/j.eswa.2026.132355_bib0052","series-title":"NAACL-HLT","article-title":"Large language models can contrastively refine their generation for better sentence representation learning","author":"Wang","year":"2024"},{"key":"10.1016\/j.eswa.2026.132355_bib0053","series-title":"Proceedings of the ACM web conference 2022","first-page":"1070","article-title":"Simgrace: A simple framework for graph contrastive learning without data augmentation","author":"Xia","year":"2022"},{"key":"10.1016\/j.eswa.2026.132355_bib0054","first-page":"16129","article-title":"Simple and asymmetric graph contrastive learning without augmentations","volume":"36","author":"Xiao","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132355_bib0055","doi-asserted-by":"crossref","unstructured":"Xu, J., Shao, W., Chen, L., & Liu, L. (2023). SimCSE++: Improving contrastive learning for sentence embeddings from two perspectives. arXiv: 2305.13192>.","DOI":"10.18653\/v1\/2023.emnlp-main.737"},{"key":"10.1016\/j.eswa.2026.132355_bib0056","unstructured":"Yan, Y., Li, R., Wang, S., Zhang, F., Wu, W., & Xu, W. (2021). Consert: A contrastive framework for self-supervised sentence representation transfer. arXiv: 2105.11741."},{"key":"10.1016\/j.eswa.2026.132355_bib0057","series-title":"Proceedings of the 21th ACM SIGKDD international conference on knowledge discovery and data mining","first-page":"1365","article-title":"Deep graph kernels","author":"Yanardag","year":"2015"},{"key":"10.1016\/j.eswa.2026.132355_bib0058","series-title":"European conference on computer vision","first-page":"668","article-title":"Decoupled contrastive learning","author":"Yeh","year":"2022"},{"key":"10.1016\/j.eswa.2026.132355_bib0059","series-title":"International conference on machine learning","first-page":"12121","article-title":"Graph contrastive learning automated","author":"You","year":"2021"},{"key":"10.1016\/j.eswa.2026.132355_bib0060","first-page":"5812","article-title":"Graph contrastive learning with augmentations","volume":"33","author":"You","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132355_bib0061","series-title":"European conference on computer vision","first-page":"430","article-title":"Contrastive learning with synthetic positives","author":"Zeng","year":"2024"},{"key":"10.1016\/j.eswa.2026.132355_bib0062","series-title":"International conference on learning representations","article-title":"How does simsiam avoid collapse without negative samples? A unified understanding with self-supervised contrastive learning","author":"Zhang","year":"2022"},{"issue":"11","key":"10.1016\/j.eswa.2026.132355_bib0063","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3732282","article-title":"Data augmentation on graphs: a technical survey","volume":"57","author":"Zhou","year":"2025","journal-title":"ACM Computing Surveys"},{"key":"10.1016\/j.eswa.2026.132355_bib0064","doi-asserted-by":"crossref","unstructured":"Zou, Z., Jiang, Y., Shen, L., Liu, J., & Liu, X. (2025). Loha: Direct graph spectral contrastive learning between low-pass and high-pass views.arXiv: 2501.02969.","DOI":"10.1609\/aaai.v39i12.33473"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426012686?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426012686?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T00:00:43Z","timestamp":1781308843000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426012686"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":64,"alternative-id":["S0957417426012686"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132355","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Understanding InfoNCE: Transition probability matrix induced feature clustering","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132355","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"132355"}}