Learning Enhanced Representations for Tabular Data via Neighborhood Propagation

Add code
Jun 14, 2022
Kounianhua Du, Weinan Zhang, Ruiwen Zhou, Yangkun Wang, Xilong Zhao, Jiarui Jin, Quan Gan, Zheng Zhang, David Wipf

Figure 1 for Learning Enhanced Representations for Tabular Data via Neighborhood Propagation
Figure 2 for Learning Enhanced Representations for Tabular Data via Neighborhood Propagation
Figure 3 for Learning Enhanced Representations for Tabular Data via Neighborhood Propagation
Figure 4 for Learning Enhanced Representations for Tabular Data via Neighborhood Propagation

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

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.

View paper onarxiv icon

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon