Let's agree to agree: Neural networks share classification order on real datasets

Guy Hacohen, Leshem Choshen, Daphna Weinshall

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

13 Scopus citations

Abstract

We report a series of robust empirical observations, demonstrating that deep Neural Networks learn the examples in both the training and test sets in a similar order. This phenomenon is observed in all the commonly used benchmarks we evaluated, including many image classification benchmarks, and one text classification benchmark. While this phenomenon is strongest for models of the same architecture, it also crosses architectural boundaries - models of different architectures start by learning the same examples, after which the more powerful model may continue to learn additional examples. We further show that this pattern of results reflects the interplay between the way neural networks learn benchmark datasets. Specifically, when fixing the architecture, we describe synthetic datasets for which this pattern is no longer observed. When fixing the dataset, we show that other learning paradigms may learn the data in a different order. We hypothesize that our results reflect how neural networks discover structure in natural datasets.

Original languageAmerican English
Title of host publication37th International Conference on Machine Learning, ICML 2020
EditorsHal Daume, Aarti Singh
PublisherInternational Machine Learning Society (IMLS)
Pages3908-3918
Number of pages11
ISBN (Electronic)9781713821120
StatePublished - 2020
Event37th International Conference on Machine Learning, ICML 2020 - Virtual, Online
Duration: 13 Jul 202018 Jul 2020

Publication series

Name37th International Conference on Machine Learning, ICML 2020
VolumePartF168147-6

Conference

Conference37th International Conference on Machine Learning, ICML 2020
CityVirtual, Online
Period13/07/2018/07/20

Bibliographical note

Publisher Copyright:
© International Conference on Machine Learning, ICML 2020. All rights reserved.

Fingerprint

Dive into the research topics of 'Let's agree to agree: Neural networks share classification order on real datasets'. Together they form a unique fingerprint.

Cite this