Pruning-based Data Selection and Network Fusion for Efficient Deep Learning
This addresses the need for more efficient data selection to reduce annotation costs and improve training scalability in deep learning, though it appears incremental as it builds on existing pruning and fusion techniques.
The paper tackled the problem of computationally expensive data selection for deep neural network training by introducing PruneFuse, which uses pruning and network fusion to reduce costs and accelerate training, achieving better performance than baselines.
Efficient data selection is essential for improving the training efficiency of deep neural networks and reducing the associated annotation costs. However, traditional methods tend to be computationally expensive, limiting their scalability and real-world applicability. We introduce PruneFuse, a novel method that combines pruning and network fusion to enhance data selection and accelerate network training. In PruneFuse, the original dense network is pruned to generate a smaller surrogate model that efficiently selects the most informative samples from the dataset. Once this iterative data selection selects sufficient samples, the insights learned from the pruned model are seamlessly integrated with the dense model through network fusion, providing an optimized initialization that accelerates training. 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.