Manifold Constrained Tabular Deep Neural Networks

• URL: http://arxiv.org/abs/2607.09710v1
• Date: Tue, 23 Jun 2026 19:11:52 GMT
• Title: Manifold Constrained Tabular Deep Neural Networks
• Abstract summary: HDE-Net is a manifold-constrained deep neural network (DNN) that enables hierarchical decision modeling in hyperbolic space.<n>For numerical features, we introduce a Soft Decision Routing mechanism that approximates range-based local rules in a differentiable manner.<n>An entropy-aware capacity allocation algorithm further adapts the number of LDNs per numerical feature to balance expressiveness and complexity.
• Score: 5.737774893512779
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 Poincaré 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.

Related papers

• Compositional Sparsity as an Inductive Bias for Neural Architecture Design [35.06894725394093]
  We identify the structural priors that enable Deep Neural Networks to overcome the curse of dimensionality.<n>We present an interpretable pipeline in which abstraction emerges through hierarchical composition.<n>Across a broad suite of real-world datasets, HNNs consistently match or outperform dense baselines while using far fewer parameters.
  arXiv  Detail & Related papers  (2026-05-14T12:26:50Z)
• S$^2$NN: Sub-bit Spiking Neural Networks [53.08060832135342]
  Spiking Neural Networks (SNNs) offer an energy-efficient paradigm for machine intelligence.<n>Despite recent advances in binary SNNs, the storage and computational demands remain substantial for large-scale networks.<n>We propose Sub-bit Spiking Neural Networks (S$2$NNs) that represent weights with less than one bit.
  arXiv  Detail & Related papers  (2025-09-29T04:17:44Z)
• Deep Hierarchical Learning with Nested Subspace Networks [53.71337604556311]
  We propose Nested Subspace Networks (NSNs) for large neural networks.<n>NSNs enable a single model to be dynamically and granularly adjusted across a continuous spectrum of compute budgets.<n>We show that NSNs can be surgically applied to pre-trained LLMs and unlock a smooth and predictable compute-performance frontier.
  arXiv  Detail & Related papers  (2025-09-22T15:13:14Z)
• TopoTune : A Framework for Generalized Combinatorial Complex Neural Networks [5.966445718346143]
  Generalized CCNNs can be used to transform any (graph) neural network into its TDL counterpart.<n>TopoTune is a lightweight software for defining, building, and training GCCNs with unprecedented flexibility and ease.
  arXiv  Detail & Related papers  (2024-10-09T04:07:20Z)
• Bundle Neural Networks for message diffusion on graphs [28.19981068815194]
  We show that Bundle Neural Networks (BuNNs) can approximate any feature transformation over nodes on any graphs given injective positional encodings.<n>We also prove that BuNNs can approximate any feature transformation over nodes on any family of graphs given injective positional encodings, resulting in universal node-level expressivity.
  arXiv  Detail & Related papers  (2024-05-24T13:28:48Z)
• Neural Networks for Singular Perturbations [0.0]
  We prove expressivity rate bounds for solution sets of a model class of singularly perturbed, elliptic two-point boundary value problems. We establish expression rate bounds in Sobolev norms in terms of the NN size.
  arXiv  Detail & Related papers  (2024-01-12T16:02:18Z)
• Representation and decomposition of functions in DAG-DNNs and structural network pruning [3.04585143845864]
  We show that DAG-DNNs can be used to derive functions defined on various sub-architectures of a deep neural network (DNN) The lifting structure associated with lower-triangular matrices makes it possible to perform the structural pruning of a network in a systematic manner.
  arXiv  Detail & Related papers  (2023-06-16T09:18:36Z)
• Benign Overfitting in Deep Neural Networks under Lazy Training [72.28294823115502]
  We show that when the data distribution is well-separated, DNNs can achieve Bayes-optimal test error for classification. Our results indicate that interpolating with smoother functions leads to better generalization.
  arXiv  Detail & Related papers  (2023-05-30T19:37:44Z)
• Sequential three-way decisions with a single hidden layer feedforward neural network [5.943305068876161]
  Three-way decisions strategy has been employed to construct network topology in a single hidden layer feedforward neural network (SFNN) This paper proposes STWD with an SFNN (STWD-SFNN) to enhance the performance of networks on structured datasets.
  arXiv  Detail & Related papers  (2023-03-14T02:26:34Z)
• A Variational Edge Partition Model for Supervised Graph Representation Learning [51.30365677476971]
  This paper introduces a graph generative process to model how the observed edges are generated by aggregating the node interactions over a set of overlapping node communities. We partition each edge into the summation of multiple community-specific weighted edges and use them to define community-specific GNNs. A variational inference framework is proposed to jointly learn a GNN based inference network that partitions the edges into different communities, these community-specific GNNs, and a GNN based predictor that combines community-specific GNNs for the end classification task.
  arXiv  Detail & Related papers  (2022-02-07T14:37:50Z)
• Towards Deeper Graph Neural Networks with Differentiable Group Normalization [61.20639338417576]
  Graph neural networks (GNNs) learn the representation of a node by aggregating its neighbors. Over-smoothing is one of the key issues which limit the performance of GNNs as the number of layers increases. We introduce two over-smoothing metrics and a novel technique, i.e., differentiable group normalization (DGN)
  arXiv  Detail & Related papers  (2020-06-12T07:18:02Z)
• EdgeNets:Edge Varying Graph Neural Networks [179.99395949679547]
  This paper puts forth a general framework that unifies state-of-the-art graph neural networks (GNNs) through the concept of EdgeNet. An EdgeNet is a GNN architecture that allows different nodes to use different parameters to weigh the information of different neighbors. This is a general linear and local operation that a node can perform and encompasses under one formulation all existing graph convolutional neural networks (GCNNs) as well as graph attention networks (GATs)
  arXiv  Detail & Related papers  (2020-01-21T15:51:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.