Junheng is a researcher at Microsoft and a member of the Knowledge and Language Team in the Cognitive Services Research Group. His research interests include knowledge graph and knowledge-driven interdisciplinary applications. He obtained his Ph.D. in Computer Science from University of California, Los Angeles (UCLA), advised by Prof. Wei Wang and Prof. Yizhou Sun. He received B.S. from Tsinghua University.
Talks and Events
Incorporating Ontological Information in Knowledge Graph Learning and Empowered NLP Applications
In this talk, we explore how such hierarchical ontological components in knowledge graphs are incorporated into KG representation learning. We present multiple practical machine learning methods, such as hierarchical graph modeling, graph neural networks, self-supervised learning, and language models, that can effectively and efficiently capture ontological information, given different knowledge graph formulations. As a result, our proposed approaches address various real-world challenges in multiple domains, from knowledge graph itself to diverse disciplines including natural language processing (language models), recommender systems, bioinformatics, and societal studies, and expand ML frontiers to knowledge graphs to multi-modal applications.
Track: Deep Learning for and with Knowledge Graphs
- Knowledge graph
- Graph neural network
- Language model
- Multimodal AI