Progressive Data Dropout: An Adaptive Training Strategy for Large-Scale Supervised Learning

David Lee Patrick, Zachary Seligman, Amanda S Fernandez

Keywords: data dropout, training optimization, adaptive training, classification, large-scale

Abstract: Common training strategies for deep neural networks are computationally expensive, continuing to redundantly train and evaluate on classes already well-understood by the model. A common strategy to diminish this cost is to reduce data used in training, however this often comes at the expense of the model's accuracy or an additional computational cost in training. We propose progressive data dropout (PDD), an adaptive training strategy which performs class-level data dropout from the training set as the network develops an understanding for each class. Our experiments on large-scale image classification demonstrate PDD reduces the total number of datapoints needed to train the network by a factor of 10, reducing the overall training time without significantly impacting accuracy or modifying the model architecture. We additionally demonstrate improvements via experiments and ablations on computer vision benchmarks, including MNIST, Fashion-MNIST, SVHN, CIFAR, and ImageNet datasets.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: General Machine Learning (ie none of the above)

TL;DR: PDD is a model-agnostic strategy for removing class-level data as learned by the model during training.