English

Binary domain generalization for sparsifying binary neural networks

Machine Learning 2023-06-26 v1

Abstract

Binary neural networks (BNNs) are an attractive solution for developing and deploying deep neural network (DNN)-based applications in resource constrained devices. Despite their success, BNNs still suffer from a fixed and limited compression factor that may be explained by the fact that existing pruning methods for full-precision DNNs cannot be directly applied to BNNs. In fact, weight pruning of BNNs leads to performance degradation, which suggests that the standard binarization domain of BNNs is not well adapted for the task. This work proposes a novel more general binary domain that extends the standard binary one that is more robust to pruning techniques, thus guaranteeing improved compression and avoiding severe performance losses. We demonstrate a closed-form solution for quantizing the weights of a full-precision network into the proposed binary domain. Finally, we show the flexibility of our method, which can be combined with other pruning strategies. Experiments over CIFAR-10 and CIFAR-100 demonstrate that the novel approach is able to generate efficient sparse networks with reduced memory usage and run-time latency, while maintaining performance.

Keywords

Cite

@article{arxiv.2306.13515,
  title  = {Binary domain generalization for sparsifying binary neural networks},
  author = {Riccardo Schiavone and Francesco Galati and Maria A. Zuluaga},
  journal= {arXiv preprint arXiv:2306.13515},
  year   = {2023}
}

Comments

Accepted as conference paper at ECML PKDD 2023

R2 v1 2026-06-28T11:12:49.530Z