Year: 2020
Type: preprint
Abstract: Despite significant advances, continual learning models still suffer from catastrophic forgetting when exposed to incrementally available data from non-stationary distributions. Rehearsal approaches alleviate the problem by maintaining and replaying a small episodic memory of previous samples, often implemented as an array of independent memory slots. In this work, we propose to augment such an array with a learnable random graph that captures pairwise similarities between its samples, and use it not only to learn new tasks but also to guard against forgetting. Empirical results on several benchmark datasets show that our model consistently outperforms recently proposed baselines for task-free continual learning.
Source: arXiv (Cornell University)
Authors: Tang, Binh, Matteson, David S.
Institution: Cornell University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: Collaborative Research: Predictive Risk Investigation SysteM (PRISM) for Multi-layer Dynamic Interconnection Analysis, HDR TRIPODS: Collaborative Research: Foundations of Greater Data Science, CAREER: New Frontiers in Time Series Analysis, Collaborative Research: Atomic Level Structural Dynamics in Catalysts
OpenAlex ID: W3041281879