Interpretable Mesomorphic Networks for Tabular Data

2023-05-22 · Arlind Kadra, Sebastian Pineda Arango, Josif Grabocka

Even though neural networks have been long deployed in applications involving tabular data, still existing neural architectures are not explainable by design. In this paper, we propose a new class of interpretable neural networks for tabular data that are both deep and linear at the same time (i.e. mesomorphic). We optimize deep hypernetworks to generate explainable linear models on a per-instance basis. As a result, our models retain the accuracy of black-box deep networks while offering free-lunch explainability for tabular data by design. Through extensive experiments, we demonstrate that our explainable deep networks have comparable performance to state-of-the-art classifiers on tabular data and outperform current existing methods that are explainable by design.

📄 PDF Abstract BibTeX arXiv:2305.13072

Code (1)

arlindkadra/imn 공식 구현 pytorch

Tasks

Deep Learning

ECG-IMN: Interpretable Mesomorphic Neural Networks for 12-Lead Electrocardiogram Interpretation

2026-02-10 · Vajira Thambawita, Jonas L. Isaksen, Jørgen K. Kanters, Hugo L. Hammer 외 arxiv

Deep learning has achieved expert-level performance in automated electrocardiogram (ECG) diagnosis, yet the "black-box" nature of these models hinders their clinical deployment. Trust in medical AI requires not just high…

ECG Classification

Improved Predictive Performance and Interpretability for Mesomorphic Neural Networks Using Local Fidelity Regularization

2026-06-29 · Hugo L. Hammer, Vajira Thambawita, Kristoffer Herland Hellton, Pål Halvorsen arxiv

Interpretable Mesomorphic Neural Networks (IMNs) offer a promising framework that combines the predictive power of deep neural networks with the interpretability of linear models. However, the original formulation lacks …

TabNet: Attentive Interpretable Tabular Learning

2019-08-20 · Sercan O. Arik, Tomas Pfister

We propose a novel high-performance and interpretable canonical deep tabular data learning architecture, TabNet. TabNet uses sequential attention to choose which features to reason from at each decision step, enabling in…

Decision Making Poker Hand Classification Representation Learning Self-Supervised Learning

Towards Interpretable Deep Neural Networks for Tabular Data

2025-09-10 · Khawla Elhadri, Jörg Schlötterer, Christin Seifert arxiv

Tabular data is the foundation of many applications in fields such as finance and healthcare. Although DNNs tailored for tabular data achieve competitive predictive performance, they are blackboxes with little interpreta…

Interpretable Graph Neural Networks for Tabular Data

2023-08-17 · Amr AlKhatib, Sofiane Ennadir, Henrik Boström, Michalis Vazirgiannis

Data in tabular format is frequently occurring in real-world applications. Graph Neural Networks (GNNs) have recently been extended to effectively handle such data, allowing feature interactions to be captured through re…

Graph Neural Network Representation Learning