2020/06/11 by Ami Abutbul, Gal Elidan, Abutbul, Ami +6 · 15 citations
Computer Science · Mathematics · #Adversarial Robustness in Machine Learning #Algorithm #Architecture #Artificial intelligence #Artificial neural network #Computer science #Disjunctive normal form #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Locality #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification #Machine learning #Mathematics #Net (polyhedron) #Theoretical computer science #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.2006.06465
published in arXiv (Cornell University) (Cornell University)
arxiv created 2020/06/11 · openalex publication_date 2020/06/11 · arxiv updated 2020/06/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
A challenging open question in deep learning is how to handle tabular data. Unlike domains such as image and natural language processing, where deep architectures prevail, there is still no widely accepted neural architecture that dominates tabular data. As a step toward bridging this gap, we present DNF-Net a novel generic architecture whose inductive bias elicits models whose structure corresponds to logical Boolean formulas in disjunctive normal form (DNF) over affine soft-threshold decision terms. In addition, DNF-Net promotes localized decisions that are taken over small subsets of the features. We present an extensive empirical study showing that DNF-Nets significantly and consistently outperform FCNs over tabular data. With relatively few hyperparameters, DNF-Nets open the door to practical end-to-end handling of tabular data using neural networks. We present ablation studies, which justify the design choices of DNF-Net including the three inductive bias elements, namely, Boolean formulation, locality, and feature selection.