How to RETIRE Tabular Data in Favor of Discrete Digital Signal Representation

2025-03-25

AI Summary

Addressing the incompatibility of tabular data with convolutional neural networks (CNNs), existing discretization-based encoding methods suffer from limited dimensionality and weak modeling capacity. This paper proposes a radar chart encoding paradigm that maps each instance to a discrete digital signal in a multidimensional polar coordinate space, explicitly capturing feature distributions and relative importance. The encoding enables end-to-end CNN training while preserving interpretability and cross-task transferability. On multiclass classification tasks, our approach achieves significantly higher accuracy and lower computational overhead compared to state-of-the-art multidimensional encoders (e.g., TabNet, DeepFM). Rigorous validation—including statistical significance testing, benchmarking against XGBoost, and visual interpretability analysis—demonstrates its effectiveness, robustness, and transparency.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Computer Vision: Multi-modal Vision

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

The successes achieved by deep neural networks in computer vision tasks have led in recent years to the emergence of a new research area dubbed Multi-Dimensional Encoding (MDE). Methods belonging to this family aim to transform tabular data into a homogeneous form of discrete digital signals (images) to apply convolutional networks to initially unsuitable problems. Despite the successive emerging works, the pool of multi-dimensional encoding methods is still low, and the scope of research on existing modality encoding techniques is quite limited. To contribute to this area of research, we propose the Radar-based Encoding from Tabular to Image REpresentation (RETIRE), which allows tabular data to be represented as radar graphs, capturing the feature characteristics of each problem instance. RETIRE was compared with a pool of state-of-the-art MDE algorithms as well as with XGBoost in terms of classification accuracy and computational complexity. In addition, an analysis was carried out regarding transferability and explainability to provide more insight into both RETIRE and existing MDE techniques. The results obtained, supported by statistical analysis, confirm the superiority of RETIRE over other established MDE methods.

Problem

• Transform tabular data into discrete digital signals
• Expand limited multi-dimensional encoding methods
• Improve classification accuracy and computational complexity

Innovation

• Transforms tabular data into radar graphs
• Applies convolutional networks via image representation
• Enhances classification accuracy and explainability