# Solving In-Table Prediction Problems by Deep Neural Networks with Performance Evaluation Using Synthetic Data

arXiv: https://arxiv.org/abs/2609.01262 · HTML: https://mlsanity.com/paper/2609.01262/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 38 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021)
- [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)
- [TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data](https://mlsanity.com/paper/2005.08314/) (2020)
- [SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training](https://mlsanity.com/paper/2106.01342/) (2021)
- [CatBoost: gradient boosting with categorical features support](https://mlsanity.com/paper/1810.11363/) (2018)
- [SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption](https://mlsanity.com/paper/2106.15147/) (2021)
- [Handling Incomplete Heterogeneous Data using VAEs](https://mlsanity.com/paper/1807.03653/) (2018)
- [TransTab: Learning Transferable Tabular Transformers Across Tables](https://mlsanity.com/paper/2205.09328/) (2022)
- [SubTab: Subsetting Features of Tabular Data for Self-Supervised Representation Learning](https://mlsanity.com/paper/2110.04361/) (2021)
- [XTab: Cross-table Pretraining for Tabular Transformers](https://mlsanity.com/paper/2305.06090/) (2023)
- [MisGAN: Learning from Incomplete Data with Generative Adversarial Networks](https://mlsanity.com/paper/1902.09599/) (2019)
- [The gap between theory and practice in function approximation with deep neural networks](https://mlsanity.com/paper/2001.07523/) (2020)
- [Revisiting Pretraining Objectives for Tabular Deep Learning](https://mlsanity.com/paper/2207.03208/) (2022)
- [SwitchTab: Switched Autoencoders Are Effective Tabular Learners](https://mlsanity.com/paper/2401.02013/) (2024)
- [Approximation capability of two hidden layer feedforward neural networks with fixed weights](https://mlsanity.com/paper/2101.09181/) (2021)
- [Improving Missing Data Imputation with Deep Generative Models](https://mlsanity.com/paper/1902.10666/) (2019)
- [A Survey on Deep Tabular Learning](https://mlsanity.com/paper/2410.12034/) (2024)
- [Missing Value Imputation Based on Deep Generative Models](https://mlsanity.com/paper/1808.01684/) (2018)

## Abstract (arXiv)

Tabular deep learning (TDL) leverages neural networks (NN) to extract patterns from tabular data. Traditional TDL methods follow a supervised learning paradigm, where a target feature is explicitly given. In this work, however, we explore a different approach by employing deep NNs to learn relationships among individual columns within a given table. We investigate whether NNs can predict the values of arbitrarily selected columns in a given table based on the remaining known columns. We call this problem In-Table Prediction (ITB), which is slightly different from table imputation methods and the pretraining task of TDL. Three potential usage scenarios are identified, which, to our best knowledge, have not been extensively studied in the literature. A self-supervised learning approach is applied to address this problem by randomly selecting columns to be masked out and used as learning targets. This work focuses on tabular datasets containing only continuous features. To handle missing values in continuous features, a novel neural layer is proposed to embed both numerical and empty values. Synthetic data is generated based on predefined column relationships, with empty values inserted using two distinct mechanisms. Additionally, an adapted masking strategy is employed to create test data. Performances of three NN architectures, namely MLP, Resnet and Transformer, are evaluated using the generated synthetic data. We conclude that, the attention-based structure outperforms the other two networks, when a sufficiently large number of training examples is available and a relatively large embedding length is chosen. We stress that these findings are obtained under controlled, synthetic conditions with a small number of columns and it should therefore be regarded as an initial, narrowly-scoped investigation rather than a general characterization of ITP on real-world tabular data.