Lifelong and Continual Learning

Learn as "Humans" do for Artificial General Intelligence (AGI)

Second Edition: "Lifelong Machine Learning." by Z. Chen and B. Liu, Morgan & Claypool, August 2018 (1st edition, 2016).
  • Added three new chapters: (4) Continual Learning and Catastrophic Forgetting, (5) Open-world Learning, (8) Continuous Knowledge Learning in Chatbots
  • Introduced the concept of learning on the job or learning while working.
  • Updated and/or reorganized the other chapters.
  • Download the first edition, Lifelong Machine Learning, Nov 2016.

  • An Interview in Nature Outlook, July 20, 2022.

    Tutorials, Short Courses and Survey

    1. New Survey: Continual Learning of Natural Language Processing Tasks: A Survey. arXiv:2211.12701, 11/23/2022.
    2. Continual Learning Dialogue Systems - Learning during Conversation. Tutorial @ SIGIR-2022, Madrid | July 11-15, 2022. (Sahisnu Mazumder and Bing Liu)
    3. Lifelong and Continual Learning. A Short PhD Course (8 hours), Aalborg University, June 14 and 16, 2022. (Bing Liu and Zixuan Ke)
    4. Continual Learning Dialogue Systems - Learning on the Job after Model Deployment. Tutorial (Aug. 20) @ IJCAI-2021 August 21-26, 2021, Montreal, Canada. (Sahisnu Mazumder and Bing Liu)
    5. Lifelong Machine Learning Tutorial. Title: lifelong machine learning and computer reading the Web, KDD-2016, August 13-17, 2016, San Francisco, USA.
    6. Lifelong Machine Learning Tutorial, IJCAI-2015, July 25-31, 2015, Buenos Aires, Argentina.

    Keynote and Invited Talks (not updated)

    1. Unifying Continual Learning, OOD Detection and Open World Learning. Keynote talk @ Second Conference on Lifelong Learning Agents (CoLLAs-2023), Montreal, August 22-25, 2023.
    2. Continual Learning: Theory and Algorithms. Invited talk @ International Congress on Basic Sciences, Beijing, July 21, 2023.
    3. Unifying Continual Learning, OOD Detection and Open World Learning. Invited talk @ Institute of Automation and Institute of Computer Technology, Beijing, July 19, 2023.
    4. AI Autonomy: Open World Continual Learning. Invited Talk @ JSAI 2023 Special Session on “Recent Trends in Open-world Continual Learning” Japan, June 6, 2023.
    5. Autonomous AI: Open World Learning and Adaptation. Invited talk @ Peking University, May 26, 2023.
    6. Theory and Algorithms for Continual Learning Invited talk @ Peking University, May 24, 2023.
    7. Unifying Continual Learning and OOD Detection. Invited talk @ Grab Technology Company, Singapore, Feb. 22, 2023.
    8. Unifying Continual Learning and OOD Detection. Invited talk @ Agency for Science, Technology and Research (A*STAR), Singapore, Feb. 21, 2023.
    9. Unifying Continual Learning and OOD Detection. Distinguished Speaker - invited talk @ Institute of Data Science, National University of Singapore, Feb. 16, 2023.
    10. Theory and Algorithms for Open-World Continual Learning. Keynote talk @ ATAL Faculty Development Program on “Social Media and Social Network Data Mining (SMSNDM)”. India. Jan. 7, 2023.
    11. Continual Learning: Theory and Algorithms. Invited talk @ Shenzhen University, Dec. 16, 2022.
    12. Theory and Algorithms for Open World Continual Learning. Keynote talk @ IEEE Inter. Conf. on Cloud Computing and Intelligent Systems (CCIS-2022), Nov. 27, 2022.
    13. Continual Learning: From Theory to Algorithms. Invited talk @ CCF BigBdata 2022, Nov. 18-20, 2022.
    14. Continual Learning of Natural Language Processing Tasks. Invited talk @ CDSC-WEST-2022, Nov. 1, 2022.
    15. Autonomous AI: Self-Initiated Continual Learning in the Open World. Invited talk @ CIIS Open-world Learning Forum, Sept. 18, 2022.
    16. Autonomous Machine Learning: Continual Learning in the Open World. Invited talk @ Intel Labs, July 25, 2022.
    17. AI Autonomy: Pre- and Post-deployment Continual Learning. Invited talk @ PyData Chicago, June 30, 2022.
    18. Post-deployment Contiunal Learning. Invited talk @ CVPR workshop - CLVision: Workshop on Continual Learning in Computer Vision (3rd Edition), June 20, 2022.
    19. Continual Learning in Pre- and Post-Deployment. Invited talk @ Megagon Labs, June 10, 2022.
    20. Batch and Online Continual Learning and Beyond. Invited talk @ Zhenjiang Labs, May 26, 2022.
    21. AI Autonomy: Continual Learning on the Job. Distinguished research talk @ Amazon Alexa, Mar. 4, 2022.
    22. Self-Motivated and Self-Supervised Open-World Continual Learning. Invited talk @ Mind & Machine Intelligence Summit @ UCSB, Feb. 16-17, 2022.
    23. Self-Initiated Continual Learning for Autonomous Agents. Keynote talk @ The 16th International Conference on Intelligent Systems and Knowledge Engineering (ISKE 2021), Nov. 27, 2021.
    24. Self-Initiated Open World Learning for Autonomous Agents. Talk @ A DARPA Sail-On Program meeting. Oct 29, 2021.
    25. Self-motivated Continual Learning for Knowledge Accumulation. Invited talk @ NeSy-2021 Continual Learning Session, Oct. 25, 2021.
    26. Continual and On-the-Job Learning. Invited talk @ IJCAI-2021 Workshop on Continual Semi-supervised Learning, Aug.19-20, 2021.
    27. Continual and Interactive Learning after Model Deployment. Invited talk @ Baidu Research, July 27, 2021.
    28. Continual and Interactive Learning after Model Deployment. Keynote talk @ International Conference on Data Intelligence and Knowledge Services, July 10, 2021.
    29. Continual and Interactive Learning after Model Deployment. Invited talk @ Allen Institute for Artificial Intelligence (AI2), June 18, 2021.
    30. Continual Learning Dialogue Systems - Learning after Model Deployment. Invited talk @ ICLR-21 Workshop on Neural Conversational AI, May 7, 2021.
    31. Learning on the Job in the Open World. Invited talk @ Information Sciences Institute, Univesity of Southern California, Sept.11, 2020.
    32. Learning on the Job in the Open World. Invited talk @ ICML-2020 Workshop on Continual Learning, July 17, 2020.
    A Podcast: "Machines that Learn Like Humans" by my former student Zhiyuan Chen and Francesco Gadaleta (host).
    A Resource Site maintained by Eric Eaton's group
    DARPA program: Lifelong Learning Machines (L2M), 3/16/2017

    The classic machine learning paradigm learns in isolation. Given a dataset, a learning algorithm is applied to a dataset to produce a model without considering any previously learned knowledge. This paradigm needs a large number of training examples and is only suitable for well-defined and narrow tasks in closed environments. Looking ahead, to deal with these limitations and to learn more like humans, I believe that it is necessary to do lifelong machine learning or simply lifelong learning (also called continual learning or even continuous learning), which tries to mimic "human learning" to build a lifelong learning machine. The key characteristic of "human learning" is the continual learning and adaptation to new environments - we accumulate the knowledge gained in the past and use the knowledge to help future learning and problem solving with possible adaptations. Ideally, it should also be able to discover new tasks and learn on the job in open environments in a self-supervised manner. Without the lifelong learning capability, AI systems will probably never be truly intelligent. learning machine or agent to continually learn and accumulate knowledge, and to become more and more knowledgeable and better and better at learning.

    Human learning is very different: I believe that no human being has ever been given 1000 positive and 1000 negative documents (or images) and asked to learn a text classifier. As we have accumulated so much knowledge in the past and understand it, we can usually learn with little effort and few examples. If we don't have the accumulated knowledge, even if we are given 2000 training examples, it is very hard to learn manually. For example, I don't understand Arabic. If you give me 2000 Arabic documents and ask me to build a classifier, I cannot do it. But that is exactly what current machine learning is doing. That is not how humans learn.

    Our Work (not updated)

    Some of my work uses sentiment analysis (SA) tasks and data because it is the problems that I encountered in a SA startup that motivated me to work on lifelong learning or continual learning. SA is very hard to scale-up without lifelong learning.

    Related Learning Paradigms: Transfer learning, multitask learning, and lifelong learning


             TextBook: Zhiyuan Chen and Bing Liu. Lifelong Machine Learning. Morgan & Claypool, 2018 (2nd edition), 2016 (1st edition).

    Created on Sep 24, 2014 by Bing Liu.