mlsanityData to 7 Oct 2026

Open-environment Machine Learning

arXiv 2206.00423 ↗First posted 1 Jun 2022cs.LGcited by 48

Not on the map. Why?

Abstract (arXiv)

Conventional machine learning studies generally assume close-environment scenarios where important factors of the learning process hold invariant. With the great success of machine learning, nowadays, more and more practical tasks, particularly those involving open-environment scenarios where important factors are subject to change, called open-environment machine learning (Open ML) in this article, are present to the community. Evidently it is a grand challenge for machine learning turning from close environment to open environment. It becomes even more challenging since, in various big data tasks, data are usually accumulated with time, like streams, while it is hard to train the machine learning model after collecting all data as in conventional studies. This article briefly introduces some advances in this line of research, focusing on techniques concerning emerging new classes, decremental/incremental features, changing data distributions, varied learning objectives, and discusses some theoretical issues.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). Builds on 26 of its 96 references that are in the map. First posted on arXiv 1 Jun 2022.

Builds on

26 of 96 references.

References · 26

  1. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 536
  2. 2020Class-incremental learning: survey and performance evaluation on image classificationcited by 446
  3. 2019SelectiveNet: A Deep Neural Network with an Integrated Reject Optioncited by 333
  4. 2018Recent Advances in Open Set Recognition: A Surveycited by 309
  5. 2013Zero-Shot Learning Through Cross-Modal Transfercited by 237
  6. 2019A review of domain adaptation without target labelscited by 154
  7. 2018Adaptive Online Learning in Dynamic Environmentscited by 130
  8. 2021Non-stationary Reinforcement Learning without Prior Knowledge: An Optimal Black-box Approachcited by 98
  9. 2020Dynamic Regret of Convex and Smooth Functionscited by 90
  10. 2021A Simple Approach for Non-stationary Linear Banditscited by 54
  11. 2019Bandit Convex Optimization in Non-stationary Environmentscited by 41
  12. 2021Knowledge-aware Zero-Shot Learning: Survey and Perspectivecited by 41
14 more
  1. 2016A Unified View of Multi-Label Performance Measurescited by 36
  2. 2019A comprehensive, application-oriented study of catastrophic forgetting in DNNscited by 35
  3. 2021Open-world Machine Learning: Applications, Challenges, and Opportunitiescited by 34
  4. 2021Non-stationary Online Learning with Memory and Non-stochastic Controlcited by 33
  5. 2021Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Surveycited by 23
  6. 2016Classification under Streaming Emerging New Classes: A Solution using Completely Random Treescited by 17
  7. 2017Learning with Feature Evolvable Streamscited by 15
  8. 2018Handling Concept Drift via Model Reusecited by 15
  9. 2016One-Pass Learning with Incremental and Decremental Featurescited by 13
  10. 2019An Unbiased Risk Estimator for Learning with Augmented Classescited by 13
  11. 2017Distribution-Free One-Pass Learningcited by 10
  12. 2019Prediction with Unpredictable Feature Evolutioncited by 8
  13. 2020Exploratory Machine Learning with Unknown Unknownscited by 8
  14. 2018Robust Artificial Intelligence and Robust Human Organizationscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 15; 2024: 9; 2025: 12; 2026: 7.

48 papers.

Sort:

By area:

  1. 2025Representation Learning for Tabular Data: A Comprehensive Surveycited by 36
  2. 2025Multi-agent Embodied AI: Advances and Future Directionscited by 36
  3. 2022Adapting to Online Label Shift with Provable Guaranteescited by 26
  4. 2022Rainproof: An Umbrella To Shield Text Generators From Out-Of-Distribution Datacited by 21
  5. 2024Happy: A Debiased Learning Framework for Continual Generalized Category Discoverycited by 18
  6. 2022Learnware: Small Models Do Bigcited by 16
  7. 2023Adapting to Continuous Covariate Shift via Online Density Ratio Estimationcited by 15
  8. 2023Robust multi-agent coordination via evolutionary generation of auxiliary adversarial attackerscited by 15
  9. 2023Efficient Methods for Non-stationary Online Learningcited by 15
  10. 2022Dynamic Regret of Online Markov Decision Processescited by 13
  11. 2024Parametric Feature Transfer: One-shot Federated Learning with Foundation Modelscited by 13
  12. 2024Robust Semi-Supervised Learning in Open Environmentscited by 8
36 more
  1. 2023Learnability with Time-Sharing Computational Resource Concernscited by 7
  2. 2023Towards Unbiased Training in Federated Open-world Semi-supervised Learningcited by 6
  3. 2023Communication-Robust Multi-Agent Learning by Adaptable Auxiliary Multi-Agent Adversary Generationcited by 6
  4. 2023Physics Inspired Hybrid Attention for SAR Target Recognitioncited by 6
  5. 2022LAMDA-SSL: Semi-Supervised Learning in Pythoncited by 5
  6. 2023Aux-Drop: Handling Haphazard Inputs in Online Learning Using Auxiliary Dropoutscited by 5
  7. 2026Revisiting Weighted Strategy for Non-stationary Parametric Bandits and MDPscited by 5
  8. 2023Multiobjective Evolutionary Pruning of Deep Neural Networks with Transfer Learning for improving their Performance and Robustnesscited by 4
  9. 2023Real-time Safety Assessment of Dynamic Systems in Non-stationary Environments: A Review of Methods and Techniquescited by 4
  10. 2024Open Continual Feature Selection via Granular-Ball Knowledge Transfercited by 4
  11. 2025Understanding the Limits of Deep Tabular Methods with Temporal Shiftcited by 4
  12. 2023OEBench: Investigating Open Environment Challenges in Real-World Relational Data Streamscited by 3
  13. 2024Towards Trustworthy Machine Learning in Production: An Overview of the Robustness in MLOps Approachcited by 3
  14. 2025BackMix: Regularizing Open Set Recognition by Removing Underlying Fore-Background Priorscited by 3
  15. 2025Realistic Evaluation of TabPFN v2 in Open Environmentscited by 3
  16. 2026Can Agents Generalize to the Open World? Unveiling the Fragility of Static Training in Tool Usecited by 3
  17. 2023OmniForce: On Human-Centered, Large Model Empowered and Cloud-Edge Collaborative AutoML Systemcited by 2
  18. 2024Dynamic Against Dynamic: An Open-set Self-learning Frameworkcited by 1
  19. 2024Exploiting Fine-Grained Prototype Distribution for Boosting Unsupervised Class Incremental Learningcited by 1
  20. 2025Mitigating Negative Transfer via Reducing Environmental Disagreementcited by 1
  21. 2026Online Learning with Gradient-Variation Interval Regretcited by 1
  22. 2023Universal Online Optimization in Dynamic Environments via Uniclass Predictioncited by 0
  23. 2023Revisiting Weighted Strategy for Non-stationary Parametric Banditscited by 0
  24. 2023Rethinking the Value of Labels for Instance-Dependent Label Noise Learningcited by 0
  25. 2024Theory-inspired Label Shift Adaptation via Aligned Distribution Mixturecited by 0
  26. 2024Theoretically Guaranteed Distribution Adaptable Learningcited by 0
  27. 2025On the Learning with Augmented Class via Forestscited by 0
  28. 2025Awesome-OL: An Extensible Toolkit for Online Learningcited by 0
  29. 2025Exploring the Tradeoff Between Diversity and Discrimination for Continuous Category Discoverycited by 0
  30. 2025DCV-ROOD Evaluation Framework: Dual Cross-Validation for Robust Out-of-Distribution Detectioncited by 0
  31. 2025Information Theory in Open-world Machine Learning Foundations, Frameworks, and Future Directioncited by 0
  32. 2025Feature-aware Modulation for Learning from Temporal Tabular Datacited by 0
  33. 2026Exploring the Impact of Parameter Update Magnitude on Forgetting and Generalization of Continual Learningcited by 0
  34. 2026Continual Quadruped Robots Coordination via Semantic Skill Discoverycited by 0
  35. 2026Offline Multi-agent Continual Cooperation via Skill Partition and Reusecited by 0
  36. 2026On the Relation Between Interval Regret and Dynamic Regretcited by 0