Efficient Meta Lifelong-Learning with Limited Memory

Zirui Wang, Sanket Vaibhav Mehta, Barnabas Poczos, Jaime Carbonell


Abstract
Current natural language processing models work well on a single task, yet they often fail to continuously learn new tasks without forgetting previous ones as they are re-trained throughout their lifetime, a challenge known as lifelong learning. State-of-the-art lifelong language learning methods store past examples in episodic memory and replay them at both training and inference time. However, as we show later in our experiments, there are three significant impediments: (1) needing unrealistically large memory module to achieve good performance, (2) suffering from negative transfer, (3) requiring multiple local adaptation steps for each test example that significantly slows down the inference speed. In this paper, we identify three common principles of lifelong learning methods and propose an efficient meta-lifelong framework that combines them in a synergistic fashion. To achieve sample efficiency, our method trains the model in a manner that it learns a better initialization for local adaptation. Extensive experiments on text classification and question answering benchmarks demonstrate the effectiveness of our framework by achieving state-of-the-art performance using merely 1% memory size and narrowing the gap with multi-task learning. We further show that our method alleviates both catastrophic forgetting and negative transfer at the same time.
Anthology ID:
2020.emnlp-main.39
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
535–548
Language:
URL:
https://aclanthology.org/2020.emnlp-main.39
DOI:
10.18653/v1/2020.emnlp-main.39
Bibkey:
Cite (ACL):
Zirui Wang, Sanket Vaibhav Mehta, Barnabas Poczos, and Jaime Carbonell. 2020. Efficient Meta Lifelong-Learning with Limited Memory. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 535–548, Online. Association for Computational Linguistics.
Cite (Informal):
Efficient Meta Lifelong-Learning with Limited Memory (Wang et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.39.pdf
Video:
 https://slideslive.com/38939206
Data
AG NewsQuACSQuADTriviaQA