Lifelong Learning - Continual Learning
(aka: Continuous Machine Learning)
Learn as "Humans" Do for Artificial General Intelligence (AGI)
"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.
Lifelong Machine Learning Tutorial. Title: lifelong machine learning and computer reading the Web, KDD-2016, August 13-17, 2016, San Francisco, USA.
Lifelong Machine Learning Tutorial, IJCAI-2015, July 25-31, 2015, Buenos Aires, Argentina.
A Podcast: "Machines that Learn Like Humans" by my former student Zhiyuan Chen and Francesco Gadaleta (host).
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.
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.
- Continual Learning (ICLR-2019 paper). Overcoming catastrophic forgetting via model adaptation for continual learning.
- Lifelong Unsupervised Learning:
- Lifelong topic modeling (ICML-2014, KDD-2014, WWW-2016):
retain the topics learned from previous domains and uses the knowledge for future modeling in other domains.
- Lifelong belief propagation (EMNLP-2016): use the knowledge
learned previously to expand the graph and to obtain more accurate prior
- Lifelong information extraction (AAAI-2016): make use of previously learned knowledge for better extraction.
- Lifelong Supervised Learning (ACL-2015, ACL-2017):
- Using a generative model (ACL-2015): The ACL-2015 work is about lifelong learning using a generative model. It is used for sentiment classification.
- Learning on the Job (ACL-2017): This work is about learning during testing or after model building based on model application results.
- Open world Learning (a.k.a. open world classification or open classification) (KDD-2016, EMNLP-2017): this learning paradigm is becoming very important as AI agents (e.g., self-driving cars and chatbots)
are increasingly facing the real-world open and dynamic environments, where there are always new or unexpected objects.
But traditional learning makes the close-world assumption: test instances must be from only the training/seen classes, which is not true in the open world.
Ideally, an open-world learner should be able to do the following:
In this process, the system becomes more and more knowledgeable and better
at learning. It also knows what it does and does not know.
- detecting instances of unseen classes - not seen in training (the DOC algorithm (EMNLP-2017) is quite powerful for this task for both text and images),
- autmatically identifying unseen classes from the detected instances in a self-supervised manner, and
- incrementally learning the new/unseen classes.
- Continuous Learning in Chatbots (2018 paper): Chatbots have been very popular in recent years, but they cannot learn new knowledge during the conversation process, i.e., their knowledge is fixed beforehand and cannot be expanded during conversations. In this work, we aim to build a lifelong knowledge learning engine for chatbots.
Related Learning Paradigms: Transfer learning, multitask learning, and lifelong learning
- Characterisitcs of lifelong learning: (1) learning continuously (ideally in the open world), (2) accumulating the previously learned knowledge to become more and more knowledgeable, (3) using the knowledge to learn more knowledge and adapting it for problem solving, (4) discovering new problems/tasks to be learned and learning them incrementally, and (5) learning on the job or learning while working, improving model during testing or model applications.
- Transfer learning vs. lifelong learning: Transfer learning
uses the source domain labeled data to help target domain learning.
Unlike lifelong learning, transfer learning is not continual and has
no knowledge retention (as it uses source labeled data, not learned
knowledge). The source must be similar to the target (which
are normally selected by the user). It is also only one-directional:
source helps target, but not the other way around because the target has no
or little labeled data.
- Multitask learning vs. lifelong learning: Multitask learning
optimizes learning of multiple tasks. Although it is possible to make
it continual, multitask learning does not retain any explicit knowledge
except data, and when the number of task is really large, it is hard to
re-learn everything when faced with a new task.
TextBook: Zhiyuan Chen and Bing Liu. Lifelong Machine Learning. Morgan & Claypool, 2018 (2nd edition), 2016 (1st edition).
- Wenpeng Hu, Zhou Lin, Bing Liu, Chongyang Tao, Zhengwei Tao, Jinwen Ma, Dongyan Zhao, Rui Yan. Overcoming Catastrophic Forgetting via Model Adaptation for Continual Learning. to appear in Proceedings of the Seventh International Conference on Learning Representations (ICLR-2019), New Orleans, Louisiana, May 6 – 9, 2019.
- Shuai Wang, Guangyi Lv, Sahisnu Mazumder, Geli Fei, and Bing Liu. Lifelong Learning Memory Networks for Aspect Sentiment Classification. Proceedings of 2018 IEEE International Conference on Big Data (IEEE BigData 2018), Seattle, December 10-13, 2018.
- Lei Shu, Hu Xu, and Bing Liu.
Unseen Class Discovery in Open-world Classification. arXiv:1801.05609 [cs.LG], 18 Jan. 2018.
- Sahisnu Mazumder, Nianzu Ma, and Bing Liu.
Towards a Continuous Knowledge Learning Engine for Chatbots. arXiv:1802.06024 [cs.CL], 16 Feb. 2018. Previous title: "Towards an Engine for Lifelong Interactive Knowledge Learning in Human-Machine Conversations".
- Hu Xu, Bing Liu, Lei Shu and Philip S. Yu. Lifelong Domain Word Embedding via Meta-Learning. Proceedings of International Conference on Artificial Intelligence (IJCAI-ECAI-2018). July 13-19 2018, Stockholm, Sweden.
- Bing Liu. Lifelong Machine Learning: a Paradigm for Continuous Learning. Frontier Computer Science, 2017, 11(3): 359–361.
- Lei Shu, Hu Xu, Bing Liu. DOC: Deep Open Classification of Text Documents. Proceedings of 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP-2017, oral presentation short paper), September 7–11, 2017, Copenhagen, Denmark.
- Lei Shu, Hu Xu, and Bing Liu. Lifelong Learning CRF for Supervised Aspect Extraction. Proceedings of Annual Meeting of the Association for Computational Linguistics (ACL-2017, oral presentation short paper), July 30-August 4, 2017, Vancouver, Canada.
- Lei Shu, Bing Liu, Hu Xu, and Annice Kim. Lifelong-RL: Lifelong Relaxation Labeling for Separating Entities and Aspects in Opinion Targets. Proceedings of 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP-2016), November 1–5, 2016, Austin, Texas, USA.
- Geli Fei, Shuai Wang, and Bing Liu. 2016. Learning Cumulatively to Become More Knowledgeable. Proceedings of SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2016), August 13-17, San Francisco, USA.
- Geli Fei, and Bing Liu. 2016. Breaking the Closed World Assumption in Text Classification. Proceedings of NAACL-HLT 2016 , June 12-17, San Diego, USA.
- Shuai Wang, Zhiyuan Chen, and Bing Liu. Mining Aspect-Speciﬁc Opinion using a Holistic Lifelong Topic Model. Proceedings of the International World Wide Web Conference (WWW-2016), April 11-15, 2016, Montreal, Canada.
- Qian Liu, Bing Liu, Yuanlin Zhang, Doo Soon Kim and Zhiqiang Gao. Improving Opinion Aspect Extraction using Semantic Similarity and Aspect Associations. Proceedings of Thirtieth AAAI Conference on Artificial Intelligence (AAAI-2016), February 12–17, 2016, Phoenix, Arizona, USA.
- Zhiyuan Chen, Nianzu Ma and Bing Liu. Lifelong Learning for Sentiment Classification. Proceedings of the 53st Annual Meeting of the Association for Computational Linguistics (ACL-2015, short paper), 26-31, July 2015, Beijing, China.
- Zhiyuan Chen and Bing Liu. Mining Topics in Documents: Standing on the Shoulders of Big Data.. Proceedings of the 20th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2014), August 24-27, New York, USA. [Code] [Dataset]
- Zhiyuan Chen and Bing Liu. Topic Modeling using Topics from Many Domains, Lifelong Learning and Big Data. Proceedings of the 31st International Conference on Machine Learning (ICML 2014), June 21-26, Beijing, China.
- Zhiyuan Chen, Arjun Mukherjee, and Bing Liu. Aspect Extraction with Automated Prior Knowledge Learning. Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL 2014), June 22-27, 2014, Baltimore, USA.
Created on Sep 24, 2014 by Bing Liu.