Work

Topic Modeling and Link-Prediction for Material Property Discovery

Year: 2025

Type: conference-paper

Abstract: Link prediction is a key network analysis technique that infers missing or future relations between nodes in a graph, based on observed patterns of connectivity. Scientific literature networks and knowledge graphs are typically large, sparse, and noisy, and often contain missing links, potential but unobserved connections, between concepts, entities, or methods. Here, we present an AI-driven hierarchical link prediction framework that integrates matrix factorization to infer hidden associations and steer discovery in complex material domains. Our method combines Hierarchical Nonnegative Matrix Factorization (HNMFk), Boolean matrix factorization (BNMFk) with automatic model selection. These discrete factors are then fused with Logistic matrix factorization (LMF), we use to construct a three-level topic tree from a 46,862-document corpus focused on 73 transition-metal dichalcogenides (TMDs). This class of materials has been studied in a variety of physics fields and has a multitude of current and potential applications.

Source: ACM Symposium on Document Engineering (DocEng)

DOI: 10.1145/3704268.3748680

Authors: Ryan C. Barron, Maksim E. Eren, Valentin Stanev, Cynthia Matuszek, Boian S. Alexandrov

Institutions: Los Alamos National Laboratory, University of Maryland, Baltimore County, University of Maryland, College Park

Language: English

Topic: Machine Learning in Materials Science

Subfield: Materials Chemistry

Field: Materials Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: U.S. Department of Energy, National Nuclear Security Administration, Office of Defense Nuclear Nonproliferation, Los Alamos National Laboratory

Awards: G1017065088, G1279347439, G2028332453, G6410514744, G6563880843