EAPCR: A Universal Feature Extractor for Scientific Data without Explicit Feature Relation Patterns

TL;DR

EAPCR is a universal feature extractor designed for scientific data lacking explicit feature relation patterns, outperforming traditional and deep learning methods in various tasks.

Contribution

The paper introduces EAPCR, a novel feature extraction method that effectively handles heterogeneous scientific data without explicit feature relations, addressing a key challenge for deep learning.

Findings

EAPCR outperforms traditional methods across multiple scientific tasks.

EAPCR demonstrates robustness on synthetic datasets without explicit FRPs.

Deep learning models like CNNs, GCNs, and Transformers struggle without explicit FRPs.

Abstract

Conventional methods, including Decision Tree (DT)-based methods, have been effective in scientific tasks, such as non-image medical diagnostics, system anomaly detection, and inorganic catalysis efficiency prediction. However, most deep-learning techniques have struggled to surpass or even match this level of success as traditional machine-learning methods. The primary reason is that these applications involve multi-source, heterogeneous data where features lack explicit relationships. This contrasts with image data, where pixels exhibit spatial relationships; textual data, where words have sequential dependencies; and graph data, where nodes are connected through established associations. The absence of explicit Feature Relation Patterns (FRPs) presents a significant challenge for deep learning techniques in scientific applications that are not image, text, and graph-based. In this paper, we introduce EAPCR, a universal feature extractor designed for data without explicit FRPs. Tested across various scientific tasks, EAPCR consistently outperforms traditional methods and bridges the gap where deep learning models fall short. To further demonstrate its robustness, we synthesize a dataset without explicit FRPs. While Kolmogorov-Arnold Network (KAN) and feature extractors like Convolutional Neural Networks (CNNs), Graph Convolutional Networks (GCNs), and Transformers struggle, EAPCR excels, demonstrating its robustness and superior performance in scientific tasks without FRPs.