{"id":13444443,"url":"https://github.com/yassouali/awesome-semi-supervised-learning","last_synced_at":"2026-02-10T15:43:20.680Z","repository":{"id":37427563,"uuid":"253946675","full_name":"yassouali/awesome-semi-supervised-learning","owner":"yassouali","description":"😎 An up-to-date \u0026 curated list of awesome semi-supervised learning papers, methods \u0026 resources.","archived":false,"fork":false,"pushed_at":"2024-05-14T14:11:41.000Z","size":249,"stargazers_count":1719,"open_issues_count":0,"forks_count":222,"subscribers_count":62,"default_branch":"master","last_synced_at":"2024-05-19T20:16:35.755Z","etag":null,"topics":["computer-vision","deep-learning","generative-model","graph-neural-networks","machine-learning","natural-language-processing","semi-supervised-learning"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/yassouali.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-04-08T00:43:22.000Z","updated_at":"2024-05-29T04:34:29.217Z","dependencies_parsed_at":"2024-05-29T04:34:28.931Z","dependency_job_id":"cd27fc22-15e7-497f-a2b9-fb1cd062738f","html_url":"https://github.com/yassouali/awesome-semi-supervised-learning","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yassouali%2Fawesome-semi-supervised-learning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yassouali%2Fawesome-semi-supervised-learning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yassouali%2Fawesome-semi-supervised-learning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yassouali%2Fawesome-semi-supervised-learning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/yassouali","download_url":"https://codeload.github.com/yassouali/awesome-semi-supervised-learning/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245258155,"owners_count":20585977,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["computer-vision","deep-learning","generative-model","graph-neural-networks","machine-learning","natural-language-processing","semi-supervised-learning"],"created_at":"2024-07-31T04:00:23.118Z","updated_at":"2026-02-10T15:43:15.955Z","avatar_url":"https://github.com/yassouali.png","language":null,"funding_links":[],"categories":["Uncategorized","Related Links","Table of Contents","Others","其他_机器学习与深度学习","Supervised Learning"],"sub_categories":["Uncategorized"],"readme":"\n# Awesome Semi-Supervised Learning\n\n[![Awesome](https://awesome.re/badge.svg)](https://awesome.re)\n[![MIT License](https://img.shields.io/badge/license-MIT-green.svg)](https://opensource.org/licenses/MIT)\n[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](http://makeapullrequest.com)\n[![Maintenance](https://img.shields.io/badge/Maintained%3F-yes-green.svg)](https://github.com/yassouali/awesome-semi-supervised-learning/graphs/commit-activity)\n\n\n\u003cp align=\"center\"\u003e\n  \u003cimg width=\"300\" src=\"https://i.imgur.com/Ky2jxnj.png\" \"Awesome!\"\u003e\n\u003c/p\u003e\n\nA curated list of awesome Semi-Supervised Learning resources. Inspired by [awesome-deep-vision](https://github.com/kjw0612/awesome-deep-vision), [awesome-deep-learning-papers](https://github.com/terryum/awesome-deep-learning-papers), and [awesome-self-supervised-learning](https://github.com/jason718/awesome-self-supervised-learning).\n\n## Background\n\n# [\u003cimg src=\"https://i.imgur.com/xXi9N40.png\"\u003e](https://github.com/yassouali/awesome-semi-supervised-learning/)\n\n#### What is Semi-Supervised Learning?\nIt is a special form of classification. Traditional classifiers use only labeled data (feature / label pairs)\nto train. Labeled instances however are often difficult, expensive, or time consuming to obtain, as they require the efforts\nof experienced human annotators. Meanwhile unlabeled data may be relatively easy to collect,\nbut there has been few ways to use them.  **Semi-supervised learning** addresses this problem by\nusing large amount of unlabeled data, together with the labeled data, to build better classifiers.\nBecause semi-supervised learning requires less human effort and gives higher accuracy, it is of great interest both in theory and in practice.\n\n#### How many semi-supervised learning methods are there?\nMany. Some often-used methods include: EM with generative mixture models, self-training, consistency regularization,\nco-training, transductive support vector machines, and graph-based methods.\nAnd with the advent of deep learning, the majority of these methods were adapted and intergrated\ninto existing deep learning frameworks to take advantage of unlabled data.\n\n#### How do semi-supervised learning methods use unlabeled data?\nSemi-supervised learning methods use unlabeled data to either modify or reprioritize hypotheses obtained\nfrom labeled data alone. Although not all methods are probabilistic, it is easier to look at methods that\nrepresent hypotheses by *p(y|x)*, and unlabeled data by *p(x)*. Generative models have common parameters\nfor the joint distribution *p(x,y)*.  It is easy to see that *p(x)* influences *p(y|x)*. \nMixture models with EM is in this category, and to some extent self-training.\nMany other methods are discriminative, including transductive SVM, Gaussian processes, information regularization,\ngraph-based and the majority of deep learning based methods.\nOriginal discriminative training cannot be used for semi-supervised learning, since *p(y|x)* is estimated ignoring *p(x)*. To solve the problem,\n*p(x)* dependent terms are often brought into the objective function, which amounts to assuming *p(y|x)* and *p(x)* share parameters\n\n(source: [SSL Literature Survey.](http://pages.cs.wisc.edu/~jerryzhu/pub/ssl_survey.pdf))\n\n \u003cfigure\u003e\n  \u003cp align=\"center\"\u003e\n    \u003cimg src=\"https://i.imgur.com/PJ340SK.png\" width=\"600\"\u003e\n    \u003cfigcaption\u003eAn example of the influence of unlabeled data in semi-supervised learning.\n    (Image source: \u003ca href=\"https://en.wikipedia.org/wiki/Semi-supervised_learning\"\u003eWikipedia\u003c/a\u003e)\n    \u003c/figcaption\u003e\n  \u003c/p\u003e\n\u003c/figure\u003e \n\n## Contributing\n\nIf you find any errors, or you wish to add some papers, please feel free to contribute to this list by contacting [me](https://yassouali.github.io/) or by creating a [pull request](https://github.com/yassouali/awesome-semi-supervised-learning/pulls) using the following Markdown format:\n\n```markdown\n- Paper Name. \n  [[pdf]](link) \n  [[code]](link)\n  - Author 1, Author 2, and Author 3. *Conference Year*\n```\n\nand adding them to the corresponding markdown file in `files/`.\n\n\u003c!-- \n## Table of contents\n\n  - [Books](#books)\n  - [Surveys \u0026 Overview](#surveys--overview)\n  - [Computer Vision](#computer-vision)\n  - [NLP](#nlp)\n  - [Generative Models \u0026 Tasks](#generative-models--tasks)\n  - [Graph Based SSL](#graph-based-ssl)\n  - [Theory](#theory)\n  - [Reinforcement Learning, Meta-Learning \u0026 Robotics](#reinforcement-learning-meta-learning--robotics)\n  - [Regression](#regression)\n  - [Other](#other)\n  - [Talks](#talks)\n  - [Thesis](#thesis)\n  - [Blogs](#blogs) --\u003e\n\n## Books\n\n- [Semi-Supervised Learning Book](http://www.acad.bg/ebook/ml/MITPress-%20SemiSupervised%20Learning.pdf). Olivier Chapelle, Bernhard Schölkopf, Alexander Zien. *IEEE Transactions on Neural Networks 2009*\n\n## Codebase\n\n- [Unified SSL Benchmark: A Unified Semi-supervised learning Benchmark for CV, NLP, and Audio](https://github.com/microsoft/Semi-supervised-learning).\n- [TorchSSL: A PyTorch-based Toolbox for Semi-Supervised Learning](https://github.com/TorchSSL/TorchSSL).\n\n## Surveys \u0026 Overview\n\n- [Realistic Evaluation of Deep Semi-Supervised Learning Algorithms](https://arxiv.org/abs/1804.09170). Avital Oliver, Augustus Odena, Colin Raffel, Ekin D. Cubuk, Ian J. Goodfellow. *NeurIPS 2018*\n- [Semi-Supervised Learning Literature Survey](http://pages.cs.wisc.edu/~jerryzhu/pub/ssl_survey.pdf). Xiaojin Zhu. *2008*\n- [An Overview of Deep Semi-Supervised Learning](https://arxiv.org/abs/2006.05278). Yassine Ouali, Céline Hudelot, Myriam Tami. *2020*\n- [A survey on semi-supervised learning](https://link.springer.com/content/pdf/10.1007/s10994-019-05855-6.pdf). Jesper E Van Engelen, Holger H Hoos. *2020*\n- [A Survey on Deep Semi-Supervised Learning](https://arxiv.org/pdf/2103.00550.pdf). Xiangli Yang, Zixing Song, Irwin King. *2021*\n\n## Computer Vision\n\n- Image Classification: [list of papers here](files/img_classification.md)\n- Semantic and Instance Segmentation: [list of papers here](files/img_segmentation.md)\n- Object Detection: [list of papers here](files/obj_detection.md)\n- Other tasks: [list of papers here](files/cv_other_tasks.md)\n\nNote that for Image and Object segmentation tasks, we also include weakly-supervised\nlearning methods, that uses weak labels (eg, image classes) for detection and segmentation.\n\n## NLP\n#### [List of papers here](files/nlp.md)\n\n## Generative Models \u0026 Tasks\n#### [List of papers here](files/generative_models.md)\n\n## Graph Based SSL\n#### [List of papers here](files/graph_ssl.md)\n\n## Theory\n#### [List of papers here](files/theory.md)\n\n## Reinforcement Learning, Meta-Learning \u0026 Robotics\n#### [List of papers here](files/reinforcement_learning.md)\n\n## Regression\n#### [List of papers here](files/regression.md)\n\n## Other\n#### [List of papers here](files/other_papers.md)\n\n\n## Talks\n- [Semi-Supervised Learning and Unsupervised Distribution Alignment](https://www.youtube.com/watch?v=PXOhi6m09bA). *CS294-158-SP20 UC Berkeley.* \n- [Semi-supervised learning with GANs](https://www.youtube.com/watch?v=j_-JaMPnhr0). *Pydata, Andreas Merentitis, Carmine Paolino, Vaibhav Singh.*\n- [Overview of Unsupervised \u0026 Semi-supervised learning](https://www.youtube.com/watch?v=tnpXLK_AS_U). *AISC, Shazia Akbar.* \n- [Semi-Supervised Learning](https://www.youtube.com/watch?v=OMRlnKupsXM), [[slides]](https://www.cs.cmu.edu/%7Etom/10701_sp11/slides/LabUnlab-3-17-2011.pdf). *CMU Machine Learning 10-701, Tom M. Mitchell.* \n\n## Thesis\n- [Fundamental limitations of semi-supervised learning](https://uwspace.uwaterloo.ca/bitstream/handle/10012/4387/lumastersthesis_electronic.pdf). *Tyler Tian Lu*.\n- [Semi-Supervised Learning with Graphs](http://pages.cs.wisc.edu/~jerryzhu/pub/thesis.pdf). *Xiaojin Zhu*.\n- [Semi-Supervised Learning for Natural Language](https://www-cs.stanford.edu/~pliang/papers/meng-thesis.pdf). *Percy Liang*.\n\n## Blogs\n- [Learning with not Enough Data Part 1: Semi-Supervised Learning](https://lilianweng.github.io/posts/2021-12-05-semi-supervised/). *Lilian Weng*.\n- [An overview of proxy-label approaches for semi-supervised learning](https://ruder.io/semi-supervised/index.html). *Sebastian Ruder*.\n- [The Illustrated FixMatch for Semi-Supervised Learning](https://amitness.com/2020/03/fixmatch-semi-supervised/). *Amit Chaudhary*.\n- [An Overview of Deep Semi-Supervised Learning](https://yassouali.github.io/ml-blog/deep-semi-supervised/). *Yassine Ouali*.\n- [Semi-Supervised Learning in Computer Vision](https://amitness.com/2020/07/semi-supervised-learning/). *Amit Chaudhary*.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyassouali%2Fawesome-semi-supervised-learning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyassouali%2Fawesome-semi-supervised-learning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyassouali%2Fawesome-semi-supervised-learning/lists"}