{"slug": "beyond-a-single-sign-bite-for-branch-preserving-binary-threshold-expansion", "title": "Beyond a Single Sign: BiTE for Branch-Preserving Binary Threshold Expansion", "summary": "A new arXiv paper (2611.17576v1) proposes BiTE (Branch-Preserving Binary Threshold Expansion), a method that evaluates each feature direction against K ordered thresholds and keeps the resulting binary responses as separate inputs to the next learned operator, letting binary neural networks distinguish up to K+1 ordered activation states instead of a single sign. On BinaryViT, BiTE raised mean final-epoch Top-1 accuracy from 74.60±0.30% to 75.83±0.15% on CIFAR-10 and from 42.80±0.46% to 44.07±0.32% on CIFAR-100 with nearly unchanged trainable parameter counts, while a matched uniform-collapse control reached 75.33±0.15% on CIFAR-10. Binary VGG-16 experiments included a configuration achieving 0.64 percentage points higher mean accuracy with 21.8% fewer parameters than conventional width scaling.", "body_md": "arXiv:2611.17576v1 Announce Type: new \nAbstract: Binary neural networks (BNNs) reduce model storage and replace many arithmetic operations with efficient bitwise computations, but the single-sign activation limits their representational capacity. Each preactivation direction is compared with one threshold and reduced to one of two values, discarding variation within each sign region. We propose \\textbf{BiTE} (Branch-Preserving Binary Threshold Expansion), which evaluates each feature direction against $K$ ordered thresholds and retains the resulting binary responses as separate inputs to the following learned operator. BiTE can distinguish up to $K+1$ ordered activation states while allowing the following operator to learn a separate transformation for each threshold response. It also enables a controllable trade-off between the number of independently constructed feature directions and the number of ordered responses extracted from each direction. On BinaryViT, BiTE improves mean final-epoch Top-1 accuracy from $74.60\\pm0.30\\%$ to $75.83\\pm0.15\\%$ on CIFAR-10 and from $42.80\\pm0.46\\%$ to $44.07\\pm0.32\\%$ on CIFAR-100, with nearly unchanged trainable parameter counts. A matched uniform-collapse control reaches $75.33\\pm0.15\\%$ on CIFAR-10, supporting the value of retaining the threshold responses separately relative to the evaluated scalar collapse. Binary VGG-16 experiments further show a favorable observed parameter--accuracy trade-off, including a configuration that achieves $0.64$ percentage points higher mean accuracy with $21.8\\%$ fewer parameters than conventional width scaling. Overall, these results support branch-preserving threshold expansion as an effective way to improve binary representations and the observed parameter--accuracy trade-off.", "url": "https://wpnews.pro/news/beyond-a-single-sign-bite-for-branch-preserving-binary-threshold-expansion", "canonical_source": "https://arxiv.org/abs/2611.17576", "published_at": "2026-11-16 05:00:00+00:00", "updated_at": "2026-11-16 05:24:17.652098+00:00", "lang": "en", "topics": ["machine-learning", "neural-networks", "ai-research"], "entities": ["BiTE", "BinaryViT", "Binary VGG-16", "CIFAR-10", "CIFAR-100", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/beyond-a-single-sign-bite-for-branch-preserving-binary-threshold-expansion", "markdown": "https://wpnews.pro/news/beyond-a-single-sign-bite-for-branch-preserving-binary-threshold-expansion.md", "text": "https://wpnews.pro/news/beyond-a-single-sign-bite-for-branch-preserving-binary-threshold-expansion.txt", "jsonld": "https://wpnews.pro/news/beyond-a-single-sign-bite-for-branch-preserving-binary-threshold-expansion.jsonld"}}