文章基本信息

标题：Using Task Descriptions in Lifelong Machine Learning for Improved Performance and Zero-Shot Transfer
本地全文：下载
作者：Mohammad Rostami ; David Isele ; Eric Eaton 等
期刊名称：Journal of Artificial Intelligence Research
印刷版ISSN：1076-9757
出版年度：2020
卷号：67
页码：673-704
出版社：American Association of Artificial
摘要：Knowledge transfer between tasks can improve the performance of learned models, but requires an accurate estimate of inter-task relationships to identify the relevant knowledge to transfer. These inter-task relationships are typically estimated based on training data for each task, which is inefficient in lifelong learning settings where the goal is to learn each consecutive task rapidly from as little data as possible. To reduce this burden, we develop a lifelong learning method based on coupled dictionary learning that utilizes high-level task descriptions to model inter-task relationships. We show that using task descriptors improves the performance of the learned task policies, providing both theoretical justification for the benefit and empirical demonstration of the improvement across a variety of learning problems. Given only the descriptor for a new task, the lifelong learner is also able to accurately predict a model for the new task through zero-shot learning using the coupled dictionary, eliminating the need to gather training data before addressing the task.
关键词：lifelong learning;zero shot learning;knolwedge transfer;multitask learning