PruneFuse: Efficient Data Selection via Weight Pruning and Network Fusion

TL;DR

PruneFuse is a novel method that combines network pruning and fusion to efficiently select training data, reducing computational costs and improving deep neural network training performance.

Contribution

It introduces a two-stage approach using pruned networks for data selection and fusing them with the original network to enhance training efficiency.

Findings

PruneFuse significantly reduces data selection computational costs.

It outperforms baseline methods in data selection quality.

The method accelerates overall neural network training.

Abstract

Efficient data selection is crucial for enhancing the training efficiency of deep neural networks and minimizing annotation requirements. Traditional methods often face high computational costs, limiting their scalability and practical use. We introduce PruneFuse, a novel strategy that leverages pruned networks for data selection and later fuses them with the original network to optimize training. PruneFuse operates in two stages: First, it applies structured pruning to create a smaller pruned network that, due to its structural coherence with the original network, is well-suited for the data selection task. This small network is then trained and selects the most informative samples from the dataset. Second, the trained pruned network is seamlessly fused with the original network. This integration leverages the insights gained during the training of the pruned network to facilitate the learning process of the fused network while leaving room for the network to discover more robust solutions. Extensive experimentation on various datasets demonstrates that PruneFuse significantly reduces computational costs for data selection, achieves better performance than baselines, and accelerates the overall training process.