Efficient Architecture Search for Continual Learning
By Qiang Gao, Zhipeng Luo, Diego Klabjan. 2020
75 citations recorded by the source corpus.
Continual learning with neural networks, which aims to learn a sequence of tasks, is an important learning framework in artificial intelligence (AI). However, it often confronts three challenges: 1) overcome the catastrophic forgetting problem; 2) adapt the current network to new tasks; and 3) control its model complexity. To reach these goals, we propose a novel approach named continual learning with efficient architecture search (CLEAS). CLEAS works closely with neural architecture search (NAS), which leverages reinforcement learning techniques to search for the best neural architecture that fits a new task. In particular, we design a neuron-level NAS controller that decides which old neurons from previous tasks should be reused (knowledge transfer) and which new neurons should be added (to learn new knowledge). Such a fine-grained controller allows finding a very concise architecture that can fit each new task well. Meanwhile, since we do not alter the weights of the reused neurons, we perfectly memorize the knowledge learned from the previous tasks. We evaluate CLEAS on numerous sequential classification tasks, and the results demonstrate that CLEAS outperforms other state-of-the-art alternative methods, achieving higher classification accuracy while using simpler neural architectures.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
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
- Bernt Schiele
- Mehrdad Farajtabar
- Qianru Sun
- Yaoyao Liu
- Piyush Rai
- Seyed Iman Mirzadeh
- Vinay Kumar Verma
- Lawrence Carin
In Computer Vision and Pattern Recognition
- Bernt Schiele
- Qianru Sun
- Luc Van Gool
- Mehrdad Farajtabar
- Lawrence Carin
- Dacheng Tao
- Yaoyao Liu
- Trevor Darrell
Citations in the corpus
- RMM: Reinforced Memory Management for Class-Incremental Learning (2023, background): “In contrast, the related work [14, 54] could use only current-phase data to estimate a short-term reward.”
- Architecture Matters in Continual Learning (2022, background): “There have been some efforts on applying architecture search to continual learning (Xu and Zhu, 2018; Huang et al., 2019; Gao et al., 2020; Li et al., 2019; Lee et al., 2021).”
- Efficient Feature Transformations for Discriminative and Generative Continual Learning (2021, methodology): “A number of previous works [66, 59, 43, 57, 8, 45, 29, 30, 51, 58] have proposed methods for expanding a neural network to learn a sequence of tasks.”