Graph-Based Machine Learning: Higher-Order Interactions, Guided Generation, And Knowledge-Graph Tools

This dissertation brings the power of graph thinking to three key challenges in modern AI, making complex data more transparent, generative design more controllable, and scholarly exploration more intuitive. First, we introduce Local CorEx, a new machine learning technique that uncovers hidden relationships among variables, making it easier to understand complex datasets without heavy computation. Next, we show how to guide the creation of new molecules by viewing the generation process itself as a walk through a "state graph," letting researchers steer outcomes toward desired chemical properties—without any extra model training. Finally, we deliver an open-source toolkit that builds interactive knowledge graphs from academic articles and web sources, automatically linking papers, citations, and concepts so anyone can navigate and update their mental map of a research field. Together, these advances accelerate data analysis, speed up molecular discovery, and foster collaboration across fields. By emphasizing user-friendly approaches and free access, this work empowers both experts and newcomers to leverage AI for solving real-world challenges. Overall, the dissertation showcases how transparent, accessible AI innovations can transform research in health, materials, and knowledge management.