Paper Info
Title
Learning to Learn without Forgetting By Maximizing Transfer and Minimizing Interference.
Abstract
Lack of performance when it comes to continual learning over non-stationary distributions of data remains a major challenge in scaling neural network learning to more human realistic settings. In this work we propose a new conceptualization of the continual learning problem in terms of a temporally symmetric trade-off between transfer and interference that can be optimized by enforcing gradient alignment across examples. We then propose a new algorithm, Meta-Experience Replay (MER), that directly exploits this view by combining experience replay with optimization based meta-learning. This method learns parameters that make interference based on future gradients less likely and transfer based on future gradients more likely. We conduct experiments across continual lifelong supervised learning benchmarks and non-stationary reinforcement learning environments demonstrating that our approach consistently outperforms recently proposed baselines for continual learning. Our experiments show that the gap between the performance of MER and baseline algorithms grows both as the environment gets more non-stationary and as the fraction of the total experiences stored gets smaller.
Year
Venue
Field
2018
international conference on learning representations
Forgetting,Conceptualization,Baseline (configuration management),Supervised learning,Exploit,Interference (wave propagation),Artificial intelligence,Machine learning,Mathematics,Reinforcement learning,Learning to learn
DocType
Volume
Citations 
Journal
abs/1810.11910
10
PageRank 
References 
Authors
0.48
22
7
Name
Order
Citations
PageRank
matthew riemer1257.86
Ignacio Cases2285.60
Robert Ajemian3100.81
Miao Liu4396.28
irina rish591281.78
Yuhai Tu614122.81
Gerald J. Tesauro731301048.34