Cross-Domain Feature Expansion for Tabular Medical Data via Knowledge Graphs Injection

2026-06-30

AI Summary

This work addresses the high cost and scarcity of cross-domain biomedical feature data in medical research by proposing MedKGTab, a novel framework that, for the first time, integrates the biomedical knowledge graph SPOKE with a dual row-column attention mechanism over raw tabular data to enable knowledge-guided, lossless cross-domain feature inference. By jointly leveraging statistical dependency priors and structured domain knowledge, MedKGTab injects semantic information while preserving the original numerical distributions, thereby circumventing structural degradation inherent in conventional tokenization-based approaches. Experimental results demonstrate that MedKGTab significantly outperforms existing medical foundation models and specialized tabular generation methods in both missing feature imputation and cross-cohort generalization tasks, achieving state-of-the-art performance.

Abstract

Acquiring comprehensive cross-domain biomedical profiles is often costly and time-consuming, resulting in severe data scarcity in medical research. To address this challenge, we propose MedKGTab, a knowledge-injected framework specifically engineered for cross-domain feature expansion in tabular medical data. MedKGTab seeks to infer uncollected biomedical features from available ones by exploiting their inherent statistical dependencies and established medical correlations. By employing a row-column dual-attention mechanism, MedKGTab operates directly on raw structured tabular data, inherently capturing exact numerical distributions without the structural loss caused by tokenization. Crucially, MedKGTab integrates data-driven statistical priors with the SPOKE biomedical knowledge graph, achieving an optimal synergy between the data and knowledge channels. Within this synergy, the representations derived from the data channel are modulated by the injected biomedical knowledge, ensuring the final generated data are grounded in empirical medical research. Experimental results demonstrate that MedKGTab achieves high data fidelity and realistic data representation in cross-domain feature expansion. It outperforms both SOTA medical large models (e.g., Baichuan M3-plus) and specialized tabular models designed for medical data generation. Furthermore, MedKGTab consistently delivers superior performance across various data generation scenarios, whether inferring missing features within the same dataset or generalizing across different medical cohorts.

Problem

• cross-domain feature expansion
• tabular medical data
• data scarcity
• biomedical knowledge graph
• missing feature inference

Innovation

• knowledge graph injection
• tabular medical data
• cross-domain feature expansion
• dual-attention mechanism
• data-knowledge synergy