Keywords: catastrophic forgetting, sample weighting, deep generalization
TL;DR: We show that catastrophic forgetting occurs within what is considered to be a single task and find that examples that are not prone to forgetting can be removed from the training set without loss of generalization.
Abstract: Inspired by the phenomenon of catastrophic forgetting, we investigate the learning dynamics of neural networks as they train on single classification tasks. Our goal is to understand whether a related phenomenon occurs when data does not undergo a clear distributional shift. We define a ``forgetting event'' to have occurred when an individual training example transitions from being classified correctly to incorrectly over the course of learning. Across several benchmark data sets, we find that: (i) certain examples are forgotten with high frequency, and some not at all; (ii) a data set's (un)forgettable examples generalize across neural architectures; and (iii) based on forgetting dynamics, a significant fraction of examples can be omitted from the training data set while still maintaining state-of-the-art generalization performance.
Code: [![github](/images/github_icon.svg) mtoneva/example_forgetting](https://github.com/mtoneva/example_forgetting) + [![Papers with Code](/images/pwc_icon.svg) 1 community implementation](https://paperswithcode.com/paper/?openreview=BJlxm30cKm)