Conference proceeding
Improved Schemes for Episodic Memory-based Lifelong Learning
Advances in Neural Information Processing Systems, Vol.33, pp.1023-1035
2020
Abstract
Current deep neural networks can achieve remarkable performance on a single
task. However, when the deep neural network is continually trained on a
sequence of tasks, it seems to gradually forget the previous learned knowledge.
This phenomenon is referred to as \textit{catastrophic forgetting} and
motivates the field called lifelong learning. Recently, episodic memory based
approaches such as GEM \cite{lopez2017gradient} and A-GEM
\cite{chaudhry2018efficient} have shown remarkable performance. In this paper,
we provide the first unified view of episodic memory based approaches from an
optimization's perspective. This view leads to two improved schemes for
episodic memory based lifelong learning, called MEGA-I and MEGA-II. MEGA-I and
MEGA-II modulate the balance between old tasks and the new task by integrating
the current gradient with the gradient computed on the episodic memory.
Notably, we show that GEM and A-GEM are degenerate cases of MEGA-I and MEGA-II
which consistently put the same emphasis on the current task, regardless of how
the loss changes over time. Our proposed schemes address this issue by using
novel loss-balancing updating rules, which drastically improve the performance
over GEM and A-GEM. Extensive experimental results show that the proposed
schemes significantly advance the state-of-the-art on four commonly used
lifelong learning benchmarks, reducing the error by up to 18\%.
Details
- Title: Subtitle
- Improved Schemes for Episodic Memory-based Lifelong Learning
- Creators
- Yunhui GuoMingrui LiuTianbao YangTajana Rosing
- Resource Type
- Conference proceeding
- Publication Details
- Advances in Neural Information Processing Systems, Vol.33, pp.1023-1035
- Language
- English
- Date published
- 2020
- Academic Unit
- Computer Science
- Record Identifier
- 9984259488102771
Metrics
30 Record Views