Mining the Weights Knowledge for Optimizing Neural Network Structures

TL;DR

This paper proposes a neural network architecture learning method that mines knowledge from weights to automatically optimize network structure, improving accuracy and compression without manual tuning.

Contribution

Introduces a switcher neural network (SNN) that automatically learns to optimize the structure of a task-specific neural network using weight-based knowledge mining.

Findings

Outperforms baseline networks in accuracy on multiple datasets.

Achieves network compression without sparse induction mechanisms.

Produces more reasonable network structures tailored to tasks.

Abstract

Knowledge embedded in the weights of the artificial neural network can be used to improve the network structure, such as in network compression. However, the knowledge is set up by hand, which may not be very accurate, and relevant information may be overlooked. Inspired by how learning works in the mammalian brain, we mine the knowledge contained in the weights of the neural network toward automatic architecture learning in this paper. We introduce a switcher neural network (SNN) that uses as inputs the weights of a task-specific neural network (called TNN for short). By mining the knowledge contained in the weights, the SNN outputs scaling factors for turning off and weighting neurons in the TNN. To optimize the structure and the parameters of TNN simultaneously, the SNN and TNN are learned alternately under the same performance evaluation of TNN using stochastic gradient descent. We test our method on widely used datasets and popular networks in classification applications. In terms of accuracy, we outperform baseline networks and other structure learning methods stably and significantly. At the same time, we compress the baseline networks without introducing any sparse induction mechanism, and our method, in particular, leads to a lower compression rate when dealing with simpler baselines or more difficult tasks. These results demonstrate that our method can produce a more reasonable structure.