Transfer Learning with Network Embeddings under Structured Missingness

2026-02-23

AI Summary

Cross-site data migration is often hindered by feature inconsistency and population heterogeneity, which impede effective knowledge transfer. This work proposes TransNEST, a novel framework that, for the first time, integrates structured missingness patterns with network embedding. By jointly leveraging graph structures and prior grouping information from both source and target domains, TransNEST adaptively models intra-group heterogeneity and inter-site discrepancies. The framework further enhances embedding quality through group-wise regularization and a hierarchical ontology structure. Evaluated under limited feature overlap and small-sample settings, TransNEST significantly outperforms existing methods, demonstrating its efficacy and practical utility in a multicenter pediatric electronic health record study where it accurately identifies specific relational pairs.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Natural Language Processing: Machine Translation, Multilinguality, Cross-Lingual NLP

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Web Mining and Content Analysis: Bridging structured and unstructured data

Abstract

Modern data-driven applications increasingly rely on large, heterogeneous datasets collected across multiple sites. Differences in data availability, feature representation, and underlying populations often induce structured missingness, complicating efforts to transfer information from data-rich settings to those with limited data. Many transfer learning methods overlook this structure, limiting their ability to capture meaningful relationships across sites. We propose TransNEST (Transfer learning with Network Embeddings under STructured missingness), a framework that integrates graphical data from source and target sites with prior group structure to construct and refine network embeddings. TransNEST accommodates site-specific features, captures within-group heterogeneity and between-site differences adaptively, and improves embedding estimation under partial feature overlap. We establish the convergence rate for the TransNEST estimator and demonstrate strong finite-sample performance in simulations. We apply TransNEST to a multi-site electronic health record study, transferring feature embeddings from a general hospital system to a pediatric hospital system. Using a hierarchical ontology structure, TransNEST improves pediatric embeddings and supports more accurate pediatric knowledge extraction, achieving the best accuracy for identifying pediatric-specific relational feature pairs compared with benchmark methods.

Problem

• transfer learning
• structured missingness
• network embeddings
• multi-site data
• feature heterogeneity

Innovation

• Transfer Learning
• Network Embeddings
• Structured Missingness
• Multi-site Data
• Hierarchical Ontology