Continual Learning through Retrieval and Imagination


  • Zhen Wang The University of Sydney
  • Liu Liu The University of Sydney
  • Yiqun Duan University of Technology Sydney
  • Dacheng Tao JD Explore Academy The University of Sydney



Machine Learning (ML)


Continual learning is an intellectual ability of artificial agents to learn new streaming labels from sequential data. The main impediment to continual learning is catastrophic forgetting, a severe performance degradation on previously learned tasks. Although simply replaying all previous data or continuously adding the model parameters could alleviate the issue, it is impractical in real-world applications due to the limited available resources. Inspired by the mechanism of the human brain to deepen its past impression, we propose a novel framework, Deep Retrieval and Imagination (DRI), which consists of two components: 1) an embedding network that constructs a unified embedding space without adding model parameters on the arrival of new tasks; and 2) a generative model to produce additional (imaginary) data based on the limited memory. By retrieving the past experiences and corresponding imaginary data, DRI distills knowledge and rebalances the embedding space to further mitigate forgetting. Theoretical analysis demonstrates that DRI can reduce the loss approximation error and improve the robustness through retrieval and imagination, bringing better generalizability to the network. Extensive experiments show that DRI performs significantly better than the existing state-of-the-art continual learning methods and effectively alleviates catastrophic forgetting.




How to Cite

Wang, Z., Liu, L., Duan, Y., & Tao, D. (2022). Continual Learning through Retrieval and Imagination. Proceedings of the AAAI Conference on Artificial Intelligence, 36(8), 8594-8602.



AAAI Technical Track on Machine Learning III