5 papers · 1 filter
From Uniform to Learned Knots: A Study of Spline-Based Numerical Encodings for Tabular Deep Learning
Manish Kumar, Anton Frederik Thielmann, Christoph Weisser +2
Numerical preprocessing remains a critical component of tabular deep learning, as the representation of continuous features can strongly affect downstream performance. We systemati…
EviNAM: Intelligibility and Uncertainty via Evidential Neural Additive Models
Sören Schleibaum, Anton Frederik Thielmann, Julian Teusch +2
Intelligibility and accurate uncertainty estimation are crucial for reliable decision-making. In this paper, we propose EviNAM, an extension of evidential learning that integrates…
Beyond Black-Box Predictions: Identifying Marginal Feature Effects in Tabular Transformer Networks
Anton Thielmann, Arik Reuter, Benjamin Saefken
In recent years, deep neural networks have showcased their predictive power across a variety of tasks. Beyond natural language processing, the transformer architecture has proven e…
Mambular: A Sequential Model for Tabular Deep Learning
Anton Frederik Thielmann, Manish Kumar, Christoph Weisser +3
The analysis of tabular data has traditionally been dominated by gradient-boosted decision trees (GBDTs), known for their proficiency with mixed categorical and numerical features.…
On the Efficiency of NLP-Inspired Methods for Tabular Deep Learning
Anton Frederik Thielmann, Soheila Samiee
Recent advancements in tabular deep learning (DL) have led to substantial performance improvements, surpassing the capabilities of traditional models. With the adoption of techniqu…