Interdisciplinary Studies

ACCELERATING SCIENTIFIC DISCOVERY WITH GENERATIVE KNOWLEDGE EXTRACTION, GRAPH-BASED REPRESENTATION, AND MULTIMODAL INTELLIGENT GRAPH REASONING

M. J. Buehler

Discover how Markus J. Buehler transformed a dataset of 1,000 scientific papers on biological materials into an innovative ontological knowledge graph using generative AI. This groundbreaking research uncovers interdisciplinary relationships and reveals unexpected connections, inviting you to explore the parallels between biology and music, art, and architecture.

00:00

Playback language: English

Index

Abstract

Leveraging generative AI, a dataset of 1,000 scientific papers on biological materials was transformed into a comprehensive ontological knowledge graph. Structural analysis revealed a scale-free graph with high connectedness, enabling graph reasoning to uncover interdisciplinary relationships. Deep node representations and combinatorial node similarity ranking facilitated a path sampling strategy, linking dissimilar concepts. Examples included parallels between biological materials and Beethoven's 9th Symphony, and the proposal of a hierarchical mycelium-based composite inspired by Kandinsky's 'Composition VII'. The method's multimodality (graphs, images, text, numerical data) enhanced novelty and explorative capacity, establishing a framework for innovation by revealing hidden connections.

Publisher

Published On

Authors

Markus J. Buehler

Related Publications

Explore these studies to deepen your understanding of the subject.

Physics

Evolving scientific discovery by unifying data and background knowledge with AI Hilbert

R. Cory-wright, C. Cornelio, et al.

Interdisciplinary Studies

SciAGENTS: Automating Scientific Discovery Through Multi-Agent Intelligent Graph Reasoning

A. Ghafarollahi and M. J. Buehler

Psychology

Effectiveness of Augmented and Virtual Reality-Based Interventions in Improving Knowledge, Attitudes, Empathy and Stigma Regarding People with Mental Illnesses-A Scoping Review

T. J.l., X. H., et al.

Medicine and Health

DKE-Research at SemEval-2024 Task 2: Incorporating Data Augmentation with Generative Models and Biomedical Knowledge to Enhance Inference Robustness

Y. Wang, Z. Wang, et al.

Listen, Learn & Level Up

Over 10,000 hours of research content in 25+ fields, available in 12+ languages.

No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.

listen to research audio papers with researchbunny