ViNNPruner: Visual Interactive Pruning for Deep Learning
This tool addresses the need for more interpretable and user-controllable pruning methods for practitioners dealing with oversized deep learning models, though it is incremental as it builds on existing pruning algorithms.
The paper tackles the problem of deploying large neural networks on specific hardware by introducing ViNNPruner, a visual interactive pruning application that allows users to apply state-of-the-art algorithms and incorporate domain knowledge through manual pruning, resulting in more efficient networks with minimal performance loss.
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.