MUMBAI, India, July 13 -- Intellectual Property India has published a patent application (202621078489 A) filed by Parul University Parul Institute Of Engineering And Technology on June 25, 2026, for Temporal Multiplex Graph Neural Network System And Method For Predicting Educational Collaboration Formation.
Inventor includes Dr. Sanjay Agal.
The application for the patent was published on July 10, 2026, under issue no. 28/2026.
Abstract: A Temporal Multiplex Graph Neural Network (TM-GNN) system and method for predicting educational collaboration formation in academic departments. The invention constructs a four-layer temporal multiplex network from co-authorship, supervision, project co- membership, and course-based collaboration data. A Temporal Graph Attention Network (TGAT) with multi-head attention learns node embeddings capturing both structural position and temporal dynamics. A link prediction decoder estimates future collaboration probabilities. The system employs a rolling-window temporal validation scheme across eight non-overlapping folds, achieving a mean ROC-AUC of 0.872 for link prediction. SHAP-based interpretability identifies the Multiplex Participation Coefficient and change in betweenness centrality as top predictive features. Applications include collaboration recommendation, academic team formation, and research network management.
Disclaimer: Curated by HT Syndication.
