Random path selection for continual learning

Jathushan Rajasegaran, Munawar Hayat, Salman Khan, Fahad Shahbaz Khan, Ling Shao

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

Abstract

Incremental life-long learning is a main challenge towards the long-standing goal of Artificial General Intelligence. In real-life settings, learning tasks arrive in a sequence and machine learning models must continually learn to increment already acquired knowledge. The existing incremental learning approaches fall well below the state-of-the-art cumulative models that use all training classes at once. In this paper, we propose a random path selection algorithm, called RPS-Net, that progressively chooses optimal paths for the new tasks while encouraging parameter sharing and reuse. Our approach avoids the overhead introduced by computationally expensive evolutionary and reinforcement learning based path selection strategies while achieving considerable performance gains. As an added novelty, the proposed model integrates knowledge distillation and retrospection along with the path selection strategy to overcome catastrophic forgetting. In order to maintain an equilibrium between previous and newly acquired knowledge, we propose a simple controller to dynamically balance the model plasticity. Through extensive experiments, we demonstrate that the proposed method surpasses the state-of-the-art performance on incremental learning and by utilizing parallel computation this method can run in constant time with nearly the same efficiency as a conventional deep convolutional neural network.
Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems 32 (NIPS 2019)
EditorsH. Wallach, H. Larochelle, A. Beygelzimer, F. d' Alché-Buc, E. Fox, R. Garnett
Place of PublicationSan Diego CA USA
PublisherNeural Information Processing Systems (NIPS)
Number of pages11
Publication statusPublished - 2019
Externally publishedYes
EventAdvances in Neural Information Processing Systems 2019 - Vancouver, Canada
Duration: 8 Dec 201914 Dec 2019
Conference number: 32nd
https://nips.cc/Conferences/2019 (Proceedings)
https://papers.nips.cc/book/advances-in-neural-information-processing-systems-32-2019 (Proceedings)

Conference

ConferenceAdvances in Neural Information Processing Systems 2019
Abbreviated titleNIPS 2019
CountryCanada
CityVancouver
Period8/12/1914/12/19
Internet address

Cite this