Graph Expansion in Pruned Recurrent Neural Network Layers Preserve Performance
This work addresses the need for efficient sequence learning in resource-limited settings, but it is incremental as it builds on known pruning techniques by focusing on graph properties.
The authors tackled the problem of pruning recurrent neural networks (RNNs and LSTMs) for resource-constrained platforms by maintaining graph expansion properties, and they found that this approach preserved classification accuracy on benchmark datasets like MNIST, CIFAR-10, and Google speech command data.
Expansion property of a graph refers to its strong connectivity as well as sparseness. It has been reported that deep neural networks can be pruned to a high degree of sparsity while maintaining their performance. Such pruning is essential for performing real time sequence learning tasks using recurrent neural networks in resource constrained platforms. We prune recurrent networks such as RNNs and LSTMs, maintaining a large spectral gap of the underlying graphs and ensuring their layerwise expansion properties. We also study the time unfolded recurrent network graphs in terms of the properties of their bipartite layers. Experimental results for the benchmark sequence MNIST, CIFAR-10, and Google speech command data show that expander graph properties are key to preserving classification accuracy of RNN and LSTM.