mlsanityData to 7 Oct 2026

Open-world Machine Learning: Applications, Challenges, and Opportunities

arXiv 2105.13448 ↗First posted 27 May 2021cs.LG cs.AIcited by 34

Not on the map. Why?

Abstract (arXiv)

Traditional machine learning mainly supervised learning, follows the assumptions of closed-world learning, i.e., for each testing class, a training class is available. However, such machine learning models fail to identify the classes which were not available during training time. These classes can be referred to as unseen classes. Whereas open-world machine learning (OWML) deals with unseen classes. In this paper, first, we present an overview of OWML with importance to the real-world context. Next, different dimensions of open-world machine learning are explored and discussed. The area of OWML gained the attention of the research community in the last decade only. We have searched through different online digital libraries and scrutinized the work done in the last decade. This paper presents a systematic review of various techniques for OWML. It also presents the research gaps, challenges, and future directions in open-world machine learning. This paper will help researchers understand the comprehensive developments of OWML and the likelihood of extending the research in suitable areas. It will also help to select applicable methodologies and datasets to explore this further.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). Builds on 63 of its 218 references that are in the map. First posted on arXiv 27 May 2021.

Builds on

63 of 218 references.

References · 63

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  6. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  7. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  8. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  9. 2016Learning without Forgettingcited by 2,465
  10. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  11. 2016Matching Networks for One Shot Learningcited by 2,246
  12. 2014Convolutional Neural Networks for Sentence Classificationcited by 1,124
38 more
  1. 2016End to End Learning for Self-Driving Carscited by 1,000
  2. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  3. 2019Large Scale Incremental Learningcited by 727
  4. 2015Image-based Recommendations on Styles and Substitutescited by 702
  5. 2018Overcoming catastrophic forgetting with hard attention to the taskcited by 672
  6. 2016MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognitioncited by 621
  7. 2020Deep Learning for Person Re-identification: A Survey and Outlookcited by 547
  8. 2015Towards Open Set Deep Networkscited by 533
  9. 2016Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filteringcited by 517
  10. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  11. 2018Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfacescited by 376
  12. 2018Recent Advances in Open Set Recognition: A Surveycited by 309
  13. 2015Highway Networkscited by 257
  14. 2017Overcoming Catastrophic Forgetting by Incremental Moment Matchingcited by 243
  15. 2014Towards Open World Recognitioncited by 226
  16. 2020A Survey on the Explainability of Supervised Machine Learningcited by 225
  17. 2017Generative OpenMax for Multi-Class Open Set Classificationcited by 157
  18. 2018Classification-Reconstruction Learning for Open-Set Recognitioncited by 146
  19. 2019C2AE: Class Conditioned Auto-Encoder for Open-set Recognitioncited by 142
  20. 2021OpenGAN: Open-Set Recognition via Open Data Generationcited by 135
  21. 2018Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgettingcited by 127
  22. 2017DOC: Deep Open Classification of Text Documentscited by 109
  23. 2017Deep Learning for Medical Image Processing: Overview, Challenges and Futurecited by 104
  24. 2018Semantic Parsing for Task Oriented Dialog using Hierarchical Representationscited by 101
  25. 2020OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in An Open Worldcited by 93
  26. 2020AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversariescited by 90
  27. 2020Incremental Learning In Online Scenariocited by 71
  28. 2019Deep Unknown Intent Detection with Margin Losscited by 66
  29. 2020Generative Adversarial Networks (GANs Survey): Challenges, Solutions, and Future Directionscited by 65
  30. 2017Open-World Knowledge Graph Completioncited by 64
  31. 2017On Quadratic Penalties in Elastic Weight Consolidationcited by 54
  32. 2018Learning a Neural-network-based Representation for Open Set Recognitioncited by 40
  33. 2018Open-world Learning and Application to Product Classificationcited by 39
  34. 2017Sparse Representation-based Open Set Recognitioncited by 36
  35. 2018Unseen Class Discovery in Open-world Classificationcited by 20
  36. 2020Towards Open-World Recommendation: An Inductive Model-based Collaborative Filtering Approachcited by 20
  37. 2016Classification under Streaming Emerging New Classes: A Solution using Completely Random Treescited by 17
  38. 2019An Open-World Extension to Knowledge Graph Completion Modelscited by 16

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 4; 2023: 12; 2024: 6; 2025: 6; 2026: 4.

34 papers.

Sort:

  1. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  2. 2023Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulationcited by 60
  3. 2022Open-environment Machine Learningcited by 48
  4. 2023MCU: An Evaluation Framework for Open-Ended Game Agentscited by 33
  5. 2022AI Autonomy : Self-Initiated Open-World Continual Learning and Adaptationcited by 23
  6. 2023Open-World Continual Learning: Unifying Novelty Detection and Continual Learningcited by 22
  7. 2022Rainproof: An Umbrella To Shield Text Generators From Out-Of-Distribution Datacited by 21
  8. 2025Handling Out-of-Distribution Data: A Surveycited by 14
  9. 2023Lifelong Continual Learning for Anomaly Detection: New Challenges, Perspectives, and Insightscited by 8
  10. 2023Aux-Drop: Handling Haphazard Inputs in Online Learning Using Auxiliary Dropoutscited by 5
  11. 2024Towards Few-Shot Learning in the Open World: A Review and Beyondcited by 5
  12. 2021Self-Initiated Open World Learning for Autonomous AI Agentscited by 4
22 more
  1. 2023Multiobjective Evolutionary Pruning of Deep Neural Networks with Transfer Learning for improving their Performance and Robustnesscited by 4
  2. 2023Real-time Safety Assessment of Dynamic Systems in Non-stationary Environments: A Review of Methods and Techniquescited by 4
  3. 2023Managing the unknown: a survey on Open Set Recognition and tangential areascited by 4
  4. 2025Realistic Evaluation of TabPFN v2 in Open Environmentscited by 3
  5. 2024A Contrastive Symmetric Forward-Forward Algorithm (SFFA) for Continual Learning Taskscited by 2
  6. 2022Open World Learning Graph Convolution for Latency Estimation in Routing Networkscited by 1
  7. 2023Detecting Novelties with Empty Classescited by 1
  8. 2023General Purpose Artificial Intelligence Systems (GPAIS): Properties, Definition, Taxonomy, Societal Implications and Responsible Governancecited by 1
  9. 2023Enhancing Open-World Bacterial Raman Spectra Identification by Feature Regularization for Improved Resilience against Unknown Classescited by 1
  10. 2023A Metalearned Neural Circuit for Nonparametric Bayesian Inferencecited by 1
  11. 2024LB-KBQA: Large-language-model and BERT based Knowledge-Based Question and Answering Systemcited by 1
  12. 2024Exploiting Fine-Grained Prototype Distribution for Boosting Unsupervised Class Incremental Learningcited by 1
  13. 2024Uncertainty Quantification in Continual Open-World Learningcited by 1
  14. 2025Temporally Consistent Unsupervised Segmentation for Mobile Robot Perceptioncited by 1
  15. 2026CL-VISTA: Benchmarking Continual Learning in Video Large Language Modelscited by 1
  16. 2024POWN: Prototypical Open-World Node Classificationcited by 0
  17. 2025Exploring the Tradeoff Between Diversity and Discrimination for Continuous Category Discoverycited by 0
  18. 2025Information Theory in Open-world Machine Learning Foundations, Frameworks, and Future Directioncited by 0
  19. 2025Open Horizons: Evaluating Deep Models in the Wildcited by 0
  20. 2026How to Achieve Prototypical Birth and Death for OOD Detection?cited by 0
  21. 2026Uncertainty Estimation for the Open-Set Text Classification systemscited by 0
  22. 2026Mixed-Prior Decision Risk for Open-Set Recognitioncited by 0