# Learning Enhanced Representations for Tabular Data via Neighborhood Propagation

arXiv: https://arxiv.org/abs/2206.06587 · HTML: https://mlsanity.com/paper/2206.06587/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 38 references that are in the map.
- First posted on arXiv 14 Jun 2022.

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

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [Wide & Deep Learning for Recommender Systems](https://mlsanity.com/paper/1606.07792/) (2016)
- [Session-based Recommendations with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06939/) (2015)
- [DeepFM: A Factorization-Machine based Neural Network for CTR Prediction](https://mlsanity.com/paper/1703.04247/) (2017)
- [Deep Interest Network for Click-Through Rate Prediction](https://mlsanity.com/paper/1706.06978/) (2017)
- [Hypergraph Neural Networks](https://mlsanity.com/paper/1809.09401/) (2018)
- [Deep Interest Evolution Network for Click-Through Rate Prediction](https://mlsanity.com/paper/1809.03672/) (2018)
- [HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data](https://mlsanity.com/paper/2004.07347/) (2020)
- [Neural Attentive Session-based Recommendation](https://mlsanity.com/paper/1711.04725/) (2017)
- [Hypergraph Convolution and Hypergraph Attention](https://mlsanity.com/paper/1901.08150/) (2019)
- [Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning](https://mlsanity.com/paper/1803.04765/) (2018)
- [Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction](https://mlsanity.com/paper/2006.05639/) (2020)
- [Handling Missing Data with Graph Representation Learning](https://mlsanity.com/paper/2010.16418/) (2020)
- [Stability and Generalization of Graph Convolutional Neural Networks](https://mlsanity.com/paper/1905.01004/) (2019)
- [Translation-based Recommendation](https://mlsanity.com/paper/1707.02410/) (2017)
- [Product-based Neural Networks for User Response Prediction over Multi-field Categorical Data](https://mlsanity.com/paper/1807.00311/) (2018)
- [User Behavior Retrieval for Click-Through Rate Prediction](https://mlsanity.com/paper/2005.14171/) (2020)
- [An Embedding Learning Framework for Numerical Features in CTR Prediction](https://mlsanity.com/paper/2012.08986/) (2020)
- [TabGNN: Multiplex Graph Neural Network for Tabular Data Prediction](https://mlsanity.com/paper/2108.09127/) (2021)
- [Retrieval & Interaction Machine for Tabular Data Prediction](https://mlsanity.com/paper/2108.05252/) (2021)
- [Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach](https://mlsanity.com/paper/2110.04514/) (2021)
- [Learning over Families of Sets -- Hypergraph Representation Learning for Higher Order Tasks](https://mlsanity.com/paper/2101.07773/) (2021)

## Built on by (most cited first, 6 of 6)

- [HYTREL: Hypergraph-enhanced Tabular Data Representation Learning](https://mlsanity.com/paper/2307.08623/) (2023)
- [Testing the Limits of Unified Sequence to Sequence LLM Pretraining on Diverse Table Data Tasks](https://mlsanity.com/paper/2310.00789/) (2023)
- [GCondNet: A Novel Method for Improving Neural Networks on Small High-Dimensional Tabular Data](https://mlsanity.com/paper/2211.06302/) (2022)
- [Between-Sample Relationship in Learning Tabular Data Using Graph and Attention Networks](https://mlsanity.com/paper/2306.06772/) (2023)
- [DictLLM: Harnessing Key-Value Data Structures with Large Language Models for Enhanced Medical Diagnostics](https://mlsanity.com/paper/2402.11481/) (2024)
- [Retrieval-Oriented Knowledge for Click-Through Rate Prediction](https://mlsanity.com/paper/2404.18304/) (2024)

## Abstract (arXiv)

Prediction over tabular data is an essential and fundamental problem in many important downstream tasks. However, existing methods either take a data instance of the table independently as input or do not fully utilize the multi-rows features and labels to directly change and enhance the target data representations. In this paper, we propose to 1) construct a hypergraph from relevant data instance retrieval to model the cross-row and cross-column patterns of those instances, and 2) perform message Propagation to Enhance the target data instance representation for Tabular prediction tasks. Specifically, our specially-designed message propagation step benefits from 1) fusion of label and features during propagation, and 2) locality-aware high-order feature interactions. Experiments on two important tabular data prediction tasks validate the superiority of the proposed PET model against other baselines. Additionally, we demonstrate the effectiveness of the model components and the feature enhancement ability of PET via various ablation studies and visualizations. The code is included in https://github.com/KounianhuaDu/PET.