ViNNPruner: Visual Interactive Pruning for Deep Learning

TL;DR

ViNNPruner is an interactive visual tool that combines automatic pruning algorithms with manual user input to effectively reduce neural network sizes while maintaining performance, enhancing understanding and customization of the pruning process.

Contribution

It introduces a visual interactive platform that integrates state-of-the-art pruning algorithms with manual pruning capabilities, facilitating better understanding and customization.

Findings

Enables semi-automatic pruning of large neural networks.

Provides visual insights into pruning algorithms.

Supports user-guided network size reduction.

Abstract

Neural networks grow vastly in size to tackle more sophisticated tasks. In many cases, such large networks are not deployable on particular hardware and need to be reduced in size. Pruning techniques help to shrink deep neural networks to smaller sizes by only decreasing their performance as little as possible. However, such pruning algorithms are often hard to understand by applying them and do not include domain knowledge which can potentially be bad for user goals. We propose ViNNPruner, a visual interactive pruning application that implements state-of-the-art pruning algorithms and the option for users to do manual pruning based on their knowledge. We show how the application facilitates gaining insights into automatic pruning algorithms and semi-automatically pruning oversized networks to make them more efficient using interactive visualizations.