Learning Compact Boolean Networks

2026-02-05

AI Summary

This work addresses the challenge of efficiently learning high-accuracy, low-overhead Boolean neural networks under resource-constrained conditions by introducing three key techniques: a learnable sparse connectivity mechanism without additional parameters, a locality-aware compact Boolean convolutional architecture, and an adaptive discretization method that mitigates accuracy degradation. By jointly optimizing network topology and binarization, the proposed approach enables a smooth transition from full-precision models to highly efficient Boolean networks. Evaluated on standard vision benchmarks, the method significantly outperforms existing approaches, achieving higher accuracy with up to 37× fewer Boolean operations, thereby striking an effective balance between computational efficiency and model performance.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Floating-point neural networks dominate modern machine learning but incur substantial inference cost, motivating interest in Boolean networks for resource-constrained settings. However, learning compact and accurate Boolean networks is challenging due to their combinatorial nature. In this work, we address this challenge from three different angles: learned connections, compact convolutions and adaptive discretization. First, we propose a novel strategy to learn efficient connections with no additional parameters and negligible computational overhead. Second, we introduce a novel convolutional Boolean architecture that exploits the locality with reduced number of Boolean operations than existing methods. Third, we propose an adaptive discretization strategy to reduce the accuracy drop when converting a continuous-valued network into a Boolean one. Extensive results on standard vision benchmarks demonstrate that the Pareto front of accuracy vs. computation of our method significantly outperforms prior state-of-the-art, achieving better accuracy with up to 37x fewer Boolean operations.

Problem

• Boolean networks
• compact models
• resource-constrained learning
• combinatorial optimization
• neural network quantization

Innovation

• Boolean networks
• compact architecture
• adaptive discretization
• efficient connections
• binary convolution