Skip to yearly menu bar Skip to main content


Poster

An Empirical Study of Example Forgetting during Deep Neural Network Learning

Mariya Toneva · Alessandro Sordoni · Remi Combes · Adam Trischler · Yoshua Bengio · Geoffrey Gordon

Great Hall BC #44

Keywords: [ catastrophic forgetting ] [ sample weighting ] [ deep 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.

Live content is unavailable. Log in and register to view live content