Efficient Meta Lifelong-Learning with Limited Memory

by   Zirui Wang, et al.

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 with multi-task learning. We further show that our method alleviates both catastrophic forgetting and negative transfer at the same time.



There are no comments yet.


page 7


Episodic Memory in Lifelong Language Learning

We introduce a lifelong language learning setup where a model needs to l...

Representation Memorization for Fast Learning New Knowledge without Forgetting

The ability to quickly learn new knowledge (e.g. new classes or data dis...

Meta-Learning with Sparse Experience Replay for Lifelong Language Learning

Lifelong learning requires models that can continuously learn from seque...

MetaICL: Learning to Learn In Context

We introduce MetaICL (Meta-training for In-Context Learning), a new meta...

Learning Neural Models for Natural Language Processing in the Face of Distributional Shift

The dominating NLP paradigm of training a strong neural predictor to per...

REMIND Your Neural Network to Prevent Catastrophic Forgetting

In lifelong machine learning, a robotic agent must be incrementally upda...

Towards Lifelong Learning of Multilingual Text-To-Speech Synthesis

This work presents a lifelong learning approach to train a multilingual ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.