# Open-world machine learning: A review and new outlooks

arXiv: https://arxiv.org/abs/2403.01759 · HTML: https://mlsanity.com/paper/2403.01759/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Mar 2024.

## Built on by (most cited first, 27 of 27)

- [Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training](https://mlsanity.com/paper/2507.05386/) (2025)
- [SelEx: Self-Expertise in Fine-Grained Generalized Category Discovery](https://mlsanity.com/paper/2408.14371/) (2024)
- [Active Generalized Category Discovery](https://mlsanity.com/paper/2403.04272/) (2024)
- [ProtoGCD: Unified and Unbiased Prototype Learning for Generalized Category Discovery](https://mlsanity.com/paper/2504.03755/) (2025)
- [Happy: A Debiased Learning Framework for Continual Generalized Category Discovery](https://mlsanity.com/paper/2410.06535/) (2024)
- [Federated Continual Instruction Tuning](https://mlsanity.com/paper/2503.12897/) (2025)
- [Continual Learning for Generative AI: From LLMs to MLLMs and Beyond](https://mlsanity.com/paper/2506.13045/) (2025)
- [Evolution and The Knightian Blindspot of Machine Learning](https://mlsanity.com/paper/2501.13075/) (2025)
- [Revisiting Confidence Estimation: Towards Reliable Failure Prediction](https://mlsanity.com/paper/2403.02886/) (2024)
- [Dual Mean-Teacher: An Unbiased Semi-Supervised Framework for Audio-Visual Source Localization](https://mlsanity.com/paper/2403.03145/) (2024)
- [Aligned Better, Listen Better for Audio-Visual Large Language Models](https://mlsanity.com/paper/2504.02061/) (2025)
- [Deep Active Learning in the Open World](https://mlsanity.com/paper/2411.06353/) (2024)
- [Category Discovery: An Open-World Perspective](https://mlsanity.com/paper/2509.22542/) (2025)
- [Cross Pseudo-Labeling for Semi-Supervised Audio-Visual Source Localization](https://mlsanity.com/paper/2403.03095/) (2024)
- [Temp-SCONE: A Novel Out-of-Distribution Detection and Domain Generalization Framework for Wild Data with Temporal Shift](https://mlsanity.com/paper/2512.04571/) (2025)
- [T-QPM: Enabling Temporal Out-Of-Distribution Detection and Domain Generalization for Vision-Language Models in Open-World](https://mlsanity.com/paper/2603.18481/) (2026)
- [Reconciling Privacy and Explainability in High-Stakes: A Systematic Inquiry](https://mlsanity.com/paper/2412.20798/) (2024)
- [Towards Efficient and General-Purpose Few-Shot Misclassification Detection for Vision-Language Models](https://mlsanity.com/paper/2503.20492/) (2025)
- [ClearGCD: Mitigating Shortcut Learning For Robust Generalized Category Discovery](https://mlsanity.com/paper/2511.22892/) (2025)
- [Exploring the Impact of Parameter Update Magnitude on Forgetting and Generalization of Continual Learning](https://mlsanity.com/paper/2602.20796/) (2026)
- [Seeing Beyond: Extrapolative Domain Adaptive Panoramic Segmentation](https://mlsanity.com/paper/2603.15475/) (2026)
- [TrustLoRA: Low-Rank Adaptation for Failure Detection under Out-of-distribution Data](https://mlsanity.com/paper/2504.14545/) (2025)
- [Contrastive Learning with Enhanced Abstract Representations using Grouped Loss of Abstract Semantic Supervision](https://mlsanity.com/paper/2509.12771/) (2025)
- [Vehicle Dynamics Embedded World Models for Autonomous Driving](https://mlsanity.com/paper/2512.02417/) (2025)
- [InfoSculpt: Sculpting the Latent Space for Generalized Category Discovery](https://mlsanity.com/paper/2601.10098/) (2026)
- [SeNeDiF-OOD: Semantic Nested Dichotomy Fusion for Out-of-Distribution Detection Methodology in Open-World Classification. A Case Study on Monument Style Classification](https://mlsanity.com/paper/2601.18739/) (2026)
- [Criteria-first, semantics-later: reproducible structure discovery in image-based sciences](https://mlsanity.com/paper/2602.15712/) (2026)

## Abstract (arXiv)

Machine learning has achieved remarkable success in many applications. However, existing studies are largely based on the closed-world assumption, which assumes that the environment is stationary, and the model is fixed once deployed. In many real-world applications, this fundamental and rather naive assumption may not hold because an open environment is complex, dynamic, and full of unknowns. In such cases, rejecting unknowns, discovering novelties, and then continually learning them, could enable models to be safe and evolve continually as biological systems do. This article presents a holistic view of open-world machine learning by investigating unknown rejection, novelty discovery, and continual learning in a unified paradigm. The challenges, principles, and limitations of current methodologies are discussed in detail. Furthermore, widely used benchmarks, metrics, and performances are summarized. Finally, we discuss several potential directions for further progress in the field. By providing a comprehensive introduction to the emerging open-world machine learning paradigm, this article aims to help researchers build more powerful AI systems in their respective fields, and to promote the development of artificial general intelligence.