Weights Having Stable Signs Are Important: Finding Primary Subnetworks and Kernels to Compress Binary Weight Networks

Binary Weight Networks (BWNs) have significantly lower computational and memory costs compared to their full-precision counterparts. To address the non-differentiable issue of BWNs, existing methods usually use the Straight-Through-Estimator (STE). In the optimization, they learn optimal binary weight outputs represented as a combination of scaling factors and weight signs to approximate 32-bit floating-point weight values, usually with a layer-wise quantization scheme. In this paper, we begin with an empirical study of training BWNs with STE under the settings of using common techniques and tricks. We show that in the context of using batch normalization after convolutional layers, adapting scaling factors with either hand-crafted or learnable methods brings marginal or no accuracy gain to final model, while the change of weight signs is crucial in the training of BWNs. Furthermore, we observe two astonishing training phenomena. Firstly, the training of BWNs demonstrates the process of seeking primary binary sub-networks whose weight signs are determined and fixed at the early training stage, which is akin to recent findings on the lottery ticket hypothesis for efficient learning of sparse neural networks. Secondly, we find binary kernels in the convolutional layers of final models tend to be centered on a limited number of fixed structural patterns, showing binary weight networks may has the potential to be further compressed, which breaks the common wisdom that representing each weight with a single bit puts the quantization to the extreme compression. To testify this hypothesis, we additionally propose a binary kernel quantization method, and we call resulting models Quantized Binary-Kernel Networks (QBNs). We hope these new experimental observations would shed new design insights to improve the training and broaden the usages of BWNs.