Forward and Backward Lifelong Learning with Time-dependent Tasks
Lists
Only you see this
Abstract
For a sequence of classification tasks that arrive over time, lifelong learning methods can boost the effective sample size of each task by leveraging information from preceding and succeeding tasks (forward and backward learning). However, backward learning is often prone to a so-called catastrophic forgetting in which a task’s performance gets worse while trying to repeatedly incorporate information from succeeding tasks. In addition, current lifelong learning techniques are designed for i.i.d. tasks and cannot capture the usual higher similarities between consecutive tasks. This paper presents lifelong learning methods based on minimax risk classifiers (LMRCs) that effectively exploit forward and backward learning and account for time-dependent tasks. In addition, we analytically characterize the increase in effective sample size provided by forward and backward learning in terms of the tasks’ expected quadratic change. The experimental evaluation shows that LMRCs can result in a significant performance improvement, especially for reduced sample sizes.
BibTeX
@inproceedings{alvarez2023forward,
author = {Veronica Alvarez and Santiago Mazuelas and Jose A. Lozano},
title = {{Forward and Backward Lifelong Learning with Time-dependent Tasks}},
booktitle = {International Conference on Learning Representations},
year = {2023},
url = {https://openreview.net/forum?id=WK22pk7bSFR},
}Loading related content...