Dynamic Collective Intelligence Learning: Finding Efficient Sparse Model via Refined Gradients for Pruned Weights
This work addresses the challenge of deploying large DNN models on resource-limited embedded systems, though it appears incremental as it builds on existing dynamic pruning methods.
The paper tackles the problem of training instability and performance degradation in dynamic pruning methods for deep neural networks by introducing refined gradients for pruned weights, resulting in improved stability and outperforming previous pruning schemes on CIFAR and ImageNet datasets.
With the growth of deep neural networks (DNN), the number of DNN parameters has drastically increased. This makes DNN models hard to be deployed on resource-limited embedded systems. To alleviate this problem, dynamic pruning methods have emerged, which try to find diverse sparsity patterns during training by utilizing Straight-Through-Estimator (STE) to approximate gradients of pruned weights. STE can help the pruned weights revive in the process of finding dynamic sparsity patterns. However, using these coarse gradients causes training instability and performance degradation owing to the unreliable gradient signal of the STE approximation. In this work, to tackle this issue, we introduce refined gradients to update the pruned weights by forming dual forwarding paths from two sets (pruned and unpruned) of weights. We propose a novel Dynamic Collective Intelligence Learning (DCIL) which makes use of the learning synergy between the collective intelligence of both weight sets. We verify the usefulness of the refined gradients by showing enhancements in the training stability and the model performance on the CIFAR and ImageNet datasets. DCIL outperforms various previously proposed pruning schemes including other dynamic pruning methods with enhanced stability during training.