# Open-world Learning and Application to Product Classification

arXiv: https://arxiv.org/abs/1809.06004 · HTML: https://mlsanity.com/paper/1809.06004/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2018.

## Built on by (most cited first, 30 of 39)

- [Generalized Out-of-Distribution Detection: A Survey](https://mlsanity.com/paper/2110.11334/) (2021)
- [Towards Open World Object Detection](https://mlsanity.com/paper/2103.02603/) (2021)
- [Large Language Models on Graphs: A Comprehensive Survey](https://mlsanity.com/paper/2312.02783/) (2023)
- [Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIP](https://mlsanity.com/paper/2109.02748/) (2021)
- [Evidential Deep Learning for Open Set Action Recognition](https://mlsanity.com/paper/2107.10161/) (2021)
- [PyCIL: A Python Toolbox for Class-Incremental Learning](https://mlsanity.com/paper/2112.12533/) (2021)
- [Towards Discovery and Attribution of Open-world GAN Generated Images](https://mlsanity.com/paper/2105.04580/) (2021)
- [UC-OWOD: Unknown-Classified Open World Object Detection](https://mlsanity.com/paper/2207.11455/) (2022)
- [Co-Transport for Class-Incremental Learning](https://mlsanity.com/paper/2107.12654/) (2021)
- [Open-world Machine Learning: Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2105.13448/) (2021)
- [A Survey on Out-of-Distribution Detection in NLP](https://mlsanity.com/paper/2305.03236/) (2023)
- [Revisiting Open World Object Detection](https://mlsanity.com/paper/2201.00471/) (2022)
- [Learngene: From Open-World to Your Learning Task](https://mlsanity.com/paper/2106.06788/) (2021)
- [Towards Realistic Semi-Supervised Learning](https://mlsanity.com/paper/2207.02269/) (2022)
- [AI Autonomy : Self-Initiated Open-World Continual Learning and Adaptation](https://mlsanity.com/paper/2203.08994/) (2022)
- [Open-World Continual Learning: Unifying Novelty Detection and Continual Learning](https://mlsanity.com/paper/2304.10038/) (2023)
- [OA-Mine: Open-World Attribute Mining for E-Commerce Products with Weak Supervision](https://mlsanity.com/paper/2204.13874/) (2022)
- [Pseudo Siamese Network for Few-shot Intent Generation](https://mlsanity.com/paper/2105.00896/) (2021)
- [Lifelong Learning on Evolving Graphs Under the Constraints of Imbalanced Classes and New Classes](https://mlsanity.com/paper/2112.10558/) (2021)
- [Delving into the Openness of CLIP](https://mlsanity.com/paper/2206.01986/) (2022)
- [Generalized Intent Discovery: Learning from Open World Dialogue System](https://mlsanity.com/paper/2209.06030/) (2022)
- [LEGO-Learn: Label-Efficient Graph Open-Set Learning](https://mlsanity.com/paper/2410.16386/) (2024)
- [Learning Instance-Level Representation for Large-Scale Multi-Modal Pretraining in E-commerce](https://mlsanity.com/paper/2304.02853/) (2023)
- [MOON: Generative MLLM-based Multimodal Representation Learning for E-commerce Product Understanding](https://mlsanity.com/paper/2508.11999/) (2025)
- [A Method for Discovering Novel Classes in Tabular Data](https://mlsanity.com/paper/2209.01217/) (2022)
- [WOT-Class: Weakly Supervised Open-world Text Classification](https://mlsanity.com/paper/2305.12401/) (2023)
- [Self-Initiated Open World Learning for Autonomous AI Agents](https://mlsanity.com/paper/2110.11385/) (2021)
- [Branch-Tuning: Balancing Stability and Plasticity for Continual Self-Supervised Learning](https://mlsanity.com/paper/2403.18266/) (2024)
- [Disentangling Transfer and Interference in Multi-Domain Learning](https://mlsanity.com/paper/2107.05445/) (2021)
- [OpenGCD: Assisting Open World Recognition with Generalized Category Discovery](https://mlsanity.com/paper/2308.06926/) (2023)

## Abstract (arXiv)

Classic supervised learning makes the closed-world assumption, meaning that classes seen in testing must have been seen in training. However, in the dynamic world, new or unseen class examples may appear constantly. A model working in such an environment must be able to reject unseen classes (not seen or used in training). If enough data is collected for the unseen classes, the system should incrementally learn to accept/classify them. This learning paradigm is called open-world learning (OWL). Existing OWL methods all need some form of re-training to accept or include the new classes in the overall model. In this paper, we propose a meta-learning approach to the problem. Its key novelty is that it only needs to train a meta-classifier, which can then continually accept new classes when they have enough labeled data for the meta-classifier to use, and also detect/reject future unseen classes. No re-training of the meta-classifier or a new overall classifier covering all old and new classes is needed. In testing, the method only uses the examples of the seen classes (including the newly added classes) on-the-fly for classification and rejection. Experimental results demonstrate the effectiveness of the new approach.