Learning Enhanced Representations for Tabular Data via Neighborhood Propagation
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.
Code (1)
Tasks
PredictionRetrievalSimilar Papers 제목 키워드 기반
Graph Elimination Networks
Graph Neural Networks (GNNs) are widely applied across various domains, yet they perform poorly in deep layers. Existing research typically attributes this problem to node over-smoothing, where node representations becom…
Generalizing Aggregation Functions in GNNs:High-Capacity GNNs via Nonlinear Neighborhood Aggregators
Graph neural networks (GNNs) have achieved great success in many graph learning tasks. The main aspect powering existing GNNs is the multi-layer network architecture to learn the nonlinear graph representations for the s…
Graph LearningFixed Aggregation Features Can Rival GNNs
Graph neural networks (GNNs) are widely believed to excel at node representation learning through trainable neighborhood aggregations. We challenge this view by introducing Fixed Aggregation Features (FAFs), a training-f…
Representation LearningGraph LearningConverting tabular data into images for deep learning with convolutional neural networks
Convolutional neural networks (CNNs) have been successfully used in many applications where important information about data is embedded in the order of features, such as speech and imaging. However, most tabular data do…
Modern Neighborhood Components Analysis: A Deep Tabular Baseline Two Decades Later
The growing success of deep learning in various domains has prompted investigations into its application to tabular data, where deep models have shown promising results compared to traditional tree-based methods. In this…