mlsanityData to 7 Oct 2026

Interpretable Mesomorphic Networks for Tabular Data

arXiv 2305.13072 ↗First posted 22 May 2023cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 32 of its 57 references that are in the map. First posted on arXiv 22 May 2023.

Builds on

32 of 57 references.

References · 32

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  2. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  3. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  4. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,455
  5. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  6. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  7. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  8. 2016HyperNetworkscited by 1,003
  9. 2021Revisiting Deep Learning Models for Tabular Datacited by 725
  10. 2022TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Secondcited by 643
  11. 2019TabNet: Attentive Interpretable Tabular Learningcited by 640
  12. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
20 more
  1. 2021Deep Neural Networks and Tabular Data: A Surveycited by 489
  2. 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 467
  3. 2019A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAIcited by 403
  4. 2017Snapshot Ensembles: Train 1, get M for freecited by 349
  5. 2020Neural Additive Models: Interpretable Machine Learning with Neural Netscited by 318
  6. 2019On the (In)fidelity and Sensitivity for Explanationscited by 309
  7. 2015Explaining NonLinear Classification Decisions with Deep Taylor Decompositioncited by 248
  8. 2018Learning to Explain: An Information-Theoretic Perspective on Model Interpretationcited by 248
  9. 2017Distilling a Neural Network Into a Soft Decision Treecited by 230
  10. 2020A Survey on the Explainability of Supervised Machine Learningcited by 225
  11. 2017OpenML Benchmarking Suitescited by 169
  12. 2021Well-tuned Simple Nets Excel on Tabular Datasetscited by 151
  13. 2020Explainable Deep Learning: A Field Guide for the Uninitiatedcited by 127
  14. 2019An Open Source AutoML Benchmarkcited by 85
  15. 2018Model Agnostic Supervised Local Explanationscited by 83
  16. 2021Synthetic Benchmarks for Scientific Research in Explainable Machine Learningcited by 59
  17. 2019Leveraging Latent Features for Local Explanationscited by 21
  18. 2018Global Model Interpretation via Recursive Partitioningcited by 17
  19. 2018Explanations of model predictions with live and breakDown packagescited by 17
  20. 2023HyperTab: Hypernetwork Approach for Deep Learning on Small Tabular Datasetscited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 3.

6 papers.

  1. 2026End-to-End Compression for Tabular Foundation Modelscited by 5
  2. 2025Explanations Go Linear: Post-hoc Explainability for Tabular Data with Interpretable Meta-Encodingcited by 1
  3. 2025HyConEx: Hypernetwork classifier with counterfactual explanations for tabular datacited by 0
  4. 2025NIMO: a Nonlinear Interpretable MOdelcited by 0
  5. 2026From Uniform to Learned Knots: A Study of Spline-Based Numerical Encodings for Tabular Deep Learningcited by 0
  6. 2026Improved Predictive Performance and Interpretability for Mesomorphic Neural Networks Using Local Fidelity Regularizationcited by 0