# Network On Network for Tabular Data Classification in Real-world Applications

arXiv: https://arxiv.org/abs/2005.10114 · HTML: https://mlsanity.com/paper/2005.10114/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 May 2020.

## Built on by (most cited first, 17 of 17)

- [Deep Neural Networks and Tabular Data: A Survey](https://mlsanity.com/paper/2110.01889/) (2021)
- [TransTab: Learning Transferable Tabular Transformers Across Tables](https://mlsanity.com/paper/2205.09328/) (2022)
- [Are Your Sensitive Attributes Private? Novel Model Inversion Attribute Inference Attacks on Classification Models](https://mlsanity.com/paper/2201.09370/) (2022)
- [Click-Through Rate Prediction in Online Advertising: A Literature Review](https://mlsanity.com/paper/2202.10462/) (2022)
- [A Survey on Deep Tabular Learning](https://mlsanity.com/paper/2410.12034/) (2024)
- [A Data-Centric Perspective on Evaluating Machine Learning Models for Tabular Data](https://mlsanity.com/paper/2407.02112/) (2024)
- [CL4CTR: A Contrastive Learning Framework for CTR Prediction](https://mlsanity.com/paper/2212.00522/) (2022)
- [Deep Feature Embedding for Tabular Data](https://mlsanity.com/paper/2408.17162/) (2024)
- [DIWIFT: Discovering Instance-wise Influential Features for Tabular Data](https://mlsanity.com/paper/2207.02773/) (2022)
- [Use of What-if Scenarios to Help Explain Artificial Intelligence Models for Neonatal Health](https://mlsanity.com/paper/2410.09635/) (2024)
- [TabGSL: Graph Structure Learning for Tabular Data Prediction](https://mlsanity.com/paper/2305.15843/) (2023)
- [Pretrained deep models outperform GBDTs in Learning-To-Rank under label scarcity](https://mlsanity.com/paper/2308.00177/) (2023)
- [Global Layers: Non-IID Tabular Federated Learning](https://mlsanity.com/paper/2305.19290/) (2023)
- [MonoSparse-CAM: Efficient Tree Model Processing via Monotonicity and Sparsity in CAMs](https://mlsanity.com/paper/2407.11071/) (2024)
- [A Deep Learning Approach for Imbalanced Tabular Data in Advertiser Prospecting: A Case of Direct Mail Prospecting](https://mlsanity.com/paper/2410.01157/) (2024)
- [How to RETIRE Tabular Data in Favor of Discrete Digital Signal Representation](https://mlsanity.com/paper/2503.19733/) (2025)
- [Distribution-Aware End-to-End Embedding for Streaming Numerical Features in Click-Through Rate Prediction](https://mlsanity.com/paper/2602.03223/) (2026)

## Abstract (arXiv)

Tabular data is the most common data format adopted by our customers ranging from retail, finance to E-commerce, and tabular data classification plays an essential role to their businesses. In this paper, we present Network On Network (NON), a practical tabular data classification model based on deep neural network to provide accurate predictions. Various deep methods have been proposed and promising progress has been made. However, most of them use operations like neural network and factorization machines to fuse the embeddings of different features directly, and linearly combine the outputs of those operations to get the final prediction. As a result, the intra-field information and the non-linear interactions between those operations (e.g. neural network and factorization machines) are ignored. Intra-field information is the information that features inside each field belong to the same field. NON is proposed to take full advantage of intra-field information and non-linear interactions. It consists of three components: field-wise network at the bottom to capture the intra-field information, across field network in the middle to choose suitable operations data-drivenly, and operation fusion network on the top to fuse outputs of the chosen operations deeply. Extensive experiments on six real-world datasets demonstrate NON can outperform the state-of-the-art models significantly. Furthermore, both qualitative and quantitative study of the features in the embedding space show NON can capture intra-field information effectively.