More Like this

1. Open-world continual learning: Unifying novelty detection and continual learning

   Kim, Gyuhak; Xiao, Changnan; Konishi, Tatsuya; Ke, Zixuan; Liu, Bing (October 2024, Artificial intelligence)
2. In-Context Continual Learning Assisted by an External Continual Learner

   Momeni, Saleh; Mazumder, Sahisnu; Ke, Zixuan; Liu, Bing (January 2025, The 31st International Conference on Computational Linguistics (COLING-2025))

   Existing continual learning (CL) methods mainly rely on fine-tuning or adapting large language mod- els (LLMs). They still suffer from catastrophic for- getting (CF). Little work has been done to exploit in-context learning (ICL) to leverage the extensive knowledge within LLMs for CL without updating any parameters. However, incrementally learning each new task in ICL necessitates adding training examples from each class of the task to the prompt, which hampers scalability as the prompt length in- creases. This issue not only leads to excessively long prompts that exceed the input token limit of the underlying LLM but also degrades the model’s performance due to the overextended context. To address this, we introduce InCA, a novel approach that integrates an external continual learner (ECL) with ICL to enable scalable CL without CF. The ECL is built incrementally to pre-select a small subset of likely classes for each test instance. By restricting the ICL prompt to only these selected classes, InCA prevents prompt lengths from becom- ing excessively long, while maintaining high per- formance. Experimental results demonstrate that InCA significantly outperforms existing CL base- lines, achieving substantial performance gains. 

   more » « less
3. Open-world continual learning: Unifying novelty detection and continual learning

   https://doi.org/10.1016/j.artint.2024.104237  

   Kim, Gyuhak; Xiao, Changnan; Konishi, Tatsuya; Ke, Zixuan; Liu, Bing (January 2025, Artificial Intelligence)

   As AI agents are increasingly used in the real open world with unknowns or novelties, they need the ability to (1) recognize objects that (a) they have learned before and (b) detect items that they have never seen or learned, and (2) learn the new items incrementally to become more and more knowledgeable and powerful. (1) is called novelty detection or out-of-distribution (OOD) detection and (2) is called class incremental learning (CIL), which is a setting of continual learning (CL). In existing research, OOD detection and CIL are regarded as two completely different problems. This paper first provides a theoretical proof that good OOD detection for each task within the set of learned tasks (called closed-world OOD detection) is necessary for successful CIL. We show this by decomposing CIL into two sub-problems: within-task prediction (WP) and task-id prediction (TP), and proving that TP is correlated with closed-world OOD detection. The key theoretical result is that regardless of whether WP and OOD detection (or TP) are defined explicitly or implicitly by a CIL algorithm, good WP and good closed-world OOD detection are necessary and sufficient conditions for good CIL, which unifies novelty or OOD detection and continual learning (CIL, in particular). We call this traditional CIL the closed-world CIL as it does not detect future OOD data in the open world. The paper then proves that the theory can be generalized or extended to open-world CIL, which is the proposed open-world continual learning, that can perform CIL in the open world and detect future or open-world OOD data. Based on the theoretical results, new CIL methods are also designed, which outperform strong baselines in CIL accuracy and in continual OOD detection by a large margin. 

   more » « less
4. CODA-Prompt: COntinual Decomposed Attention-Based Prompting for Rehearsal-Free Continual Learning

   https://doi.org/10.1109/CVPR52729.2023.01146  

   Smith, James Seale; Karlinsky, Leonid; Gutta, Vyshnavi; Cascante-Bonilla, Paola; Kim, Donghyun; Arbelle, Assaf; Panda, Rameswar; Feris, Rogerio; Kira, Zsolt (June 2023, Proceedings IEEE Computer Society Conference on Computer Vision and Pattern Recognition)

   Computer vision models suffer from a phenomenon known as catastrophic forgetting when learning novel concepts from continuously shifting training data. Typical solutions for this continual learning problem require extensive rehearsal of previously seen data, which increases memory costs and may violate data privacy. Recently, the emergence of large-scale pre-trained vision transformer models has enabled prompting approaches as an alternative to data-rehearsal. These approaches rely on a key-query mechanism to generate prompts and have been found to be highly resistant to catastrophic forgetting in the well-established rehearsal-free continual learning setting. However, the key mechanism of these methods is not trained end-to-end with the task sequence. Our experiments show that this leads to a reduction in their plasticity, hence sacrificing new task accuracy, and inability to benefit from expanded parameter capacity. We instead propose to learn a set of prompt components which are assembled with input-conditioned weights to produce input-conditioned prompts, resulting in a novel attention-based end-to-end key-query scheme. Our experiments show that we outperform the current SOTA method DualPrompt on established benchmarks by as much as 4.5% in average final accuracy. We also outperform the state of art by as much as 4.4% accuracy on a continual learning benchmark which contains both class-incremental and domain-incremental task shifts, corresponding to many practical settings. 

   more » « less
5. Adversarially Robust Continual Learning

   https://doi.org/10.1109/IJCNN55064.2022.9892970  

   Khan, Hikmat; Bouaynaya, Nidhal Carla; Rasool, Ghulam (July 2022, 2022 International Joint Conference on Neural Networks (IJCNN))