Three scenarios for continual learning

By Gido M. van de Ven, Andreas S. Tolias. 2019

1,067 citations recorded by the source corpus.

Standard artificial neural networks suffer from the well-known issue of catastrophic forgetting, making continual or lifelong learning difficult for machine learning. In recent years, numerous methods have been proposed for continual learning, but due to differences in evaluation protocols it is difficult to directly compare their performance. To enable more structured comparisons, we describe three continual learning scenarios based on whether at test time task identity is provided and--in case it is not--whether it must be inferred. Any sequence of well-defined tasks can be performed according to each scenario. Using the split and permuted MNIST task protocols, for each scenario we carry out an extensive comparison of recently proposed continual learning methods. We demonstrate substantial differences between the three scenarios in terms of difficulty and in terms of how efficient different methods are. In particular, when task identity must be inferred (i.e., class incremental learning), we find that regularization-based approaches (e.g., elastic weight consolidation) fail and that replaying representations of previous experiences seems required for solving this scenario.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing, Meta & Continual Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Yoshua Bengio
  2. Sergey Levine
  3. Mohit Bansal
  4. Dacheng Tao
  5. Jianfeng Gao
  6. Quoc V. Le
  7. Percy Liang
  8. Bing Liu

In Computer Vision and Pattern Recognition

  1. Luc Van Gool
  2. Dacheng Tao
  3. Trevor Darrell
  4. Bernt Schiele
  5. Ming-Hsuan Yang
  6. Andrea Vedaldi
  7. Xiaogang Wang
  8. Andrew Zisserman

In Natural Language Processing

  1. Mohit Bansal
  2. Jianfeng Gao
  3. Kyunghyun Cho
  4. Yejin Choi
  5. Graham Neubig
  6. Xiang Ren
  7. Luke S. Zettlemoyer
  8. Bing Liu

In Meta & Continual Learning

  1. Bing Liu
  2. Joost van de Weijer
  3. Zixuan Ke
  4. Tinne Tuytelaars
  5. Liyuan Wang
  6. Gyuhak Kim
  7. Jorge Armando Mendez Mendez
  8. Eric Eaton

Citations in the corpus