XNNTab -- Interpretable Neural Networks for Tabular Data using Sparse Autoencoders

• URL: http://arxiv.org/abs/2512.13442v1
• Date: Mon, 15 Dec 2025 15:39:59 GMT
• Title: XNNTab -- Interpretable Neural Networks for Tabular Data using Sparse Autoencoders
• Authors: Khawla Elhadri, Jörg Schlötterer, Christin Seifert,
• Abstract summary: We present XNNTab, a neural architecture that combines the expressiveness of neural networks and interpretability.<n>XNNTab first learns highly non-linear feature representations, which are decomposed into monosemantic features.<n>These features are then assigned human-interpretable concepts, making the overall model prediction intrinsically interpretable.
• Score: 11.062610312729865
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: In data-driven applications relying on tabular data, where interpretability is key, machine learning models such as decision trees and linear regression are applied. Although neural networks can provide higher predictive performance, they are not used because of their blackbox nature. In this work, we present XNNTab, a neural architecture that combines the expressiveness of neural networks and interpretability. XNNTab first learns highly non-linear feature representations, which are decomposed into monosemantic features using a sparse autoencoder (SAE). These features are then assigned human-interpretable concepts, making the overall model prediction intrinsically interpretable. XNNTab outperforms interpretable predictive models, and achieves comparable performance to its non-interpretable counterparts.

Related papers

• Towards Interpretable Deep Neural Networks for Tabular Data [11.062610312729865]
  We introduce XNNTab, a neural architecture that learns a dictionary of monosemantic features within the latent space used for prediction.<n>XNNTab attains performance on par with or exceeding that of state-of-the-art, black-box neural models and classical machine learning approaches.
  arXiv  Detail & Related papers  (2025-09-10T14:14:43Z)
• Making Pre-trained Language Models Great on Tabular Prediction [50.70574370855663]
  The transferability of deep neural networks (DNNs) has made significant progress in image and language processing. We present TP-BERTa, a specifically pre-trained LM for tabular data prediction. A novel relative magnitude tokenization converts scalar numerical feature values to finely discrete, high-dimensional tokens, and an intra-feature attention approach integrates feature values with the corresponding feature names.
  arXiv  Detail & Related papers  (2024-03-04T08:38:56Z)
• Interpretable Graph Neural Networks for Tabular Data [18.30325076881234]
  IGNNet constrains the learning algorithm to produce an interpretable model. A large-scale empirical investigation is presented, showing that IGNNet is performing on par with state-of-the-art machine-learning algorithms.
  arXiv  Detail & Related papers  (2023-08-17T12:35:02Z)
• Set-based Neural Network Encoding Without Weight Tying [91.37161634310819]
  We propose a neural network weight encoding method for network property prediction.<n>Our approach is capable of encoding neural networks in a model zoo of mixed architecture.<n>We introduce two new tasks for neural network property prediction: cross-dataset and cross-architecture.
  arXiv  Detail & Related papers  (2023-05-26T04:34:28Z)
• Neural networks trained with SGD learn distributions of increasing complexity [78.30235086565388]
  We show that neural networks trained using gradient descent initially classify their inputs using lower-order input statistics. We then exploit higher-order statistics only later during training. We discuss the relation of DSB to other simplicity biases and consider its implications for the principle of universality in learning.
  arXiv  Detail & Related papers  (2022-11-21T15:27:22Z)
• Dynamic Inference with Neural Interpreters [72.90231306252007]
  We present Neural Interpreters, an architecture that factorizes inference in a self-attention network as a system of modules. inputs to the model are routed through a sequence of functions in a way that is end-to-end learned. We show that Neural Interpreters perform on par with the vision transformer using fewer parameters, while being transferrable to a new task in a sample efficient manner.
  arXiv  Detail & Related papers  (2021-10-12T23:22:45Z)
• Combining Discrete Choice Models and Neural Networks through Embeddings: Formulation, Interpretability and Performance [10.57079240576682]
  This study proposes a novel approach that combines theory and data-driven choice models using Artificial Neural Networks (ANNs) In particular, we use continuous vector representations, called embeddings, for encoding categorical or discrete explanatory variables. Our models deliver state-of-the-art predictive performance, outperforming existing ANN-based models while drastically reducing the number of required network parameters.
  arXiv  Detail & Related papers  (2021-09-24T15:55:31Z)
• XBNet : An Extremely Boosted Neural Network [0.0]
  XBNet tries to combine tree-based models with that of neural networks to create a robust architecture trained by using a novel optimization technique, Boosted Gradient Descent for Tabular Data. In this paper, we describe a novel architecture XBNet, which tries to combine tree-based models with that of neural networks to create a robust architecture trained by using a novel optimization technique, Boosted Gradient Descent for Tabular Data.
  arXiv  Detail & Related papers  (2021-06-09T17:31:50Z)
• Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking [63.49779304362376]
  Graph neural networks (GNNs) have become a popular approach to integrating structural inductive biases into NLP models. We introduce a post-hoc method for interpreting the predictions of GNNs which identifies unnecessary edges. We show that we can drop a large proportion of edges without deteriorating the performance of the model.
  arXiv  Detail & Related papers  (2020-10-01T17:51:19Z)
• Neural Additive Models: Interpretable Machine Learning with Neural Nets [77.66871378302774]
  Deep neural networks (DNNs) are powerful black-box predictors that have achieved impressive performance on a wide variety of tasks. We propose Neural Additive Models (NAMs) which combine some of the expressivity of DNNs with the inherent intelligibility of generalized additive models. NAMs learn a linear combination of neural networks that each attend to a single input feature.
  arXiv  Detail & Related papers  (2020-04-29T01:28:32Z)
• Adaptive Explainable Neural Networks (AxNNs) [8.949704905866888]
  We develop a new framework called Adaptive Explainable Neural Networks (AxNN) for achieving the dual goals of good predictive performance and model interpretability. For predictive performance, we build a structured neural network made up of ensembles of generalized additive model networks and additive index models. For interpretability, we show how to decompose the results of AxNN into main effects and higher-order interaction effects.
  arXiv  Detail & Related papers  (2020-04-05T23:40:57Z)

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.