# Hyperbolic Manifold Constrained Tabular Neural Network

arXiv: https://arxiv.org/abs/2607.09710 · HTML: https://mlsanity.com/paper/2607.09710/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 30 references that are in the map.
- First posted on arXiv 23 Jun 2026.

## Builds on (most cited first, 25 of 25)

- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021)
- [Poincar'e Embeddings for Learning Hierarchical Representations](https://mlsanity.com/paper/1705.08039/) (2017)
- [TabNet: Attentive Interpretable Tabular Learning](https://mlsanity.com/paper/1908.07442/) (2019)
- [Deep Neural Networks and Tabular Data: A Survey](https://mlsanity.com/paper/2110.01889/) (2021)
- [TabTransformer: Tabular Data Modeling Using Contextual Embeddings](https://mlsanity.com/paper/2012.06678/) (2020)
- [Hyperbolic Graph Convolutional Neural Networks](https://mlsanity.com/paper/1910.12933/) (2019)
- [Implicit Regularization in Matrix Factorization](https://mlsanity.com/paper/1705.09280/) (2017)
- [TabICL: A Tabular Foundation Model for In-Context Learning on Large Data](https://mlsanity.com/paper/2502.05564/) (2025)
- [On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization](https://mlsanity.com/paper/1802.06509/) (2018)
- [Riemannian Adaptive Optimization Methods](https://mlsanity.com/paper/1810.00760/) (2018)
- [On Embeddings for Numerical Features in Tabular Deep Learning](https://mlsanity.com/paper/2203.05556/) (2022)
- [Well-tuned Simple Nets Excel on Tabular Datasets](https://mlsanity.com/paper/2106.11189/) (2021)
- [TabICLv2: A better, faster, scalable, and open tabular foundation model](https://mlsanity.com/paper/2602.11139/) (2026)
- [Hyperbolic Image-Text Representations](https://mlsanity.com/paper/2304.09172/) (2023)
- [TabDPT: Scaling Tabular Foundation Models on Real Data](https://mlsanity.com/paper/2410.18164/) (2024)
- [TabM: Advancing Tabular Deep Learning with Parameter-Efficient Ensembling](https://mlsanity.com/paper/2410.24210/) (2024)
- [TabR: Tabular Deep Learning Meets Nearest Neighbors in 2023](https://mlsanity.com/paper/2307.14338/) (2023)
- [A Hyperbolic-to-Hyperbolic Graph Convolutional Network](https://mlsanity.com/paper/2104.06942/) (2021)
- [A Closer Look at TabPFN v2: Understanding Its Strengths and Extending Its Capabilities](https://mlsanity.com/paper/2502.17361/) (2025)
- [Revisiting Nearest Neighbor for Tabular Data: A Deep Tabular Baseline Two Decades Later](https://mlsanity.com/paper/2407.03257/) (2024)
- [xRFM: Accurate, scalable, and interpretable feature learning models for tabular data](https://mlsanity.com/paper/2508.10053/) (2025)
- [Fully Hyperbolic Convolutional Neural Networks](https://mlsanity.com/paper/1905.10484/) (2019)
- [Fast hyperboloid decision tree algorithms](https://mlsanity.com/paper/2310.13841/) (2023)
- [Crafting Imperceptible On-Manifold Adversarial Attacks for Tabular Data](https://mlsanity.com/paper/2507.10998/) (2025)

## Abstract (arXiv)

Tabular prediction is central to a wide range of real-world applications. Tabular data typically contain heterogeneous features as well as rich and complex relational information that can imply a latent structural manifold. Hyperbolic geometry can help capture complex structural relations in data. However, most existing tabular prediction models are constructed and optimized in Euclidean space. How to incorporate hyperbolic geometry into supervised tabular learning remains underexplored. We propose HTNN, a supervised hyperbolic manifold constrained tabular neural network for tabular prediction. HTNN consists of a hyperbolic feature-value representation layer for heterogeneous categorical and numerical features, followed by a conventional MLP predictor. HTNN employs a geometry-aware training and geometry-free inference optimization framework. The geometry-aware training allows hyperbolic geometry to shape the latent representation learning of heterogeneous feature values. After training, the latent hyperbolic representations can be converted into ordinary Euclidean space for efficient geometry-free inference. We conducted extensive experiments on the TALENT benchmark. HTNN ranks first among 36 methods on 200 classification datasets and third among 34 methods on 100 regression datasets. Experimental results show that the proposed hyperbolic manifold constrained tabular neural network is effective.