{"slug": "manifold-constrained-tabular-deep-neural-networks", "title": "Manifold Constrained Tabular Deep Neural Networks", "summary": "Researchers propose HDE-Net, a manifold-constrained deep neural network that models tabular classification using hyperbolic space to better capture discrete, rule-based patterns. The method outperforms both gradient-boosted decision trees and existing tabular DNNs on the TALENT-tiny-core benchmark while maintaining high efficiency.", "body_md": "arXiv:2607.09710v1 Announce Type: new\nAbstract: Tabular classification is often governed by local, condition-triggered rules rather than smooth global patterns. However, tabular deep neural networks (DNNs) are typically built upon Euclidean representations that favor smooth variations and semantic locality. This potential geometric mismatch can make it challenging for tabular DNNs to efficiently represent the discrete, rule-partitioned structures often underlying tabular classification. To address this issue, we propose HDE-Net, a manifold-constrained DNN that enables hierarchical decision modeling in hyperbolic space. We first abstract heterogeneous features into unified Latent Decision Nodes (LDNs) and embed them in the Poincar\\'e ball, forming a continuous representation that resembles tree-structured reasoning. For numerical features, we introduce a Soft Decision Routing mechanism that approximates range-based local rules in a differentiable manner, bringing their LDN semantics closer to those of categorical features. An entropy-aware capacity allocation algorithm further adapts the number of LDNs per numerical feature to balance expressiveness and complexity. On the TALENT-tiny-core classification benchmark (30 datasets), HDE-Net achieves the \\textit{best average rank}, outperforming both industrial GBDTs and recent tabular DNNs while maintaining high efficiency.", "url": "https://wpnews.pro/news/manifold-constrained-tabular-deep-neural-networks", "canonical_source": "https://arxiv.org/abs/2607.09710", "published_at": "2026-07-14 04:00:00+00:00", "updated_at": "2026-07-14 04:22:49.186071+00:00", "lang": "en", "topics": ["machine-learning", "neural-networks"], "entities": ["HDE-Net", "TALENT-tiny-core"], "alternates": {"html": "https://wpnews.pro/news/manifold-constrained-tabular-deep-neural-networks", "markdown": "https://wpnews.pro/news/manifold-constrained-tabular-deep-neural-networks.md", "text": "https://wpnews.pro/news/manifold-constrained-tabular-deep-neural-networks.txt", "jsonld": "https://wpnews.pro/news/manifold-constrained-tabular-deep-neural-networks.jsonld"}}