Using Task Descriptions in Lifelong Machine Learning for Improved Performance and Zero-Shot Transfer

By David Isele, Mohammad Rostami, Eric Eaton. 2017

42 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

ConTinTin: Continual Learning from Task Instructions (2022, background): “sembling ours is (Rostami et al., 2020), in which task descriptions were incorporated into lifelong learning for zero-shot transfer.”
Detection and Continual Learning of Novel Face Presentation Attacks (2021, background): “The learning setting that we explore is more related to the zero-shot learning (ZSL) formulation [9, 37, 38, 25].”
A Theory for Knowledge Transfer in Continual Learning (2022, background): “Knowledge transfer has been proposed as a mechanism to achieve this (Ke et al., 2020; Rostami et al., 2020; Benavides-Prado, 2020).”
How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition (2022, background): “, 2015), and another extension leverages task descriptors to achieve zero-shot transfer to unseen tasks (Isele et al., 2016; Rostami et al., 2020).”
Learning Transferable Knowledge Through Embedding Spaces (2019, methodology): “Results of this chapter have been presented in [168; 61].”