Invited Talks


Dr. David Leake

Cases, Networks and Knowledge: Learning to Leverage Experiences

David Leake is Executive Associate Dean and Professor of Computer Science in the School of Informatics and Computing - Bloomington, at Indiana University. He is also an associate of the Indiana University Data to Insight Center and member of the faculty of the university's Cognitive Science and Human-Computer Interaction programs. He received his Ph.D. in Computer Science from Yale University in 1990. His research interests include case-based reasoning, context, explanation, human-centered computing, intelligent user interfaces, introspective reasoning, and knowledge capture and management. He has authored/edited over 175 publications in these areas, including winners of outstanding paper awards from the International Conference on Case-Based Reasoning. He has chaired the International Conference on Case-Based Reasoning and International Conference on Intelligent User Interfaces. He is Editor Emeritus of AI Magazine, the official magazine of the Association for the Advancement of Artificial Intelligence (AAAI), for which he was Editor in Chief for 17 years. He is a recipient of the AAAI Distinguished Service Award. He is a three-time recipient of the Indiana University Trustees' Teaching Award. His home page is http://www.cs.indiana.edu/~leake.


Dr. Shreyansh Bhatt

Shreyansh is a Machine Learning Scientist at Amazon.com. He works on developing domain knowledge driven machine learning solutions to facilitate decision making. Amazon sort center process millions of packages every day. In this talk, I will discuss how domain knowledge driven machine learning assist Amazon sort center site-leaders to make informed decision in order to meet millions of on time customer delivery promises.


Dr. Cory Henson

Knowledge-infused Learning for Autonomous Driving

Cory Henson is a Lead Research Scientist at the Bosch Research and Technology Center, Pittsburgh, PA. He also holds an Adjunct Faculty position at Wright State University. His primary research interest involves the use of knowledge representation and semantic technology to enable autonomous driving. More recently, he is focused on the application of knowledge graph embeddings for scene understanding and the advancement of perception systems. At Bosch, he leads a team of Ph.Ds persuing these topics while also staying within close proximity to the product development teams bringing these technologies to life. Over the past few years, he has been privileged to collaborate with distinguished researchers from the University of South Carolina, Max-Planck Institute, and the University of Trier.


Dr. Kavitha Srinivas

Making use of Knowledge Graphs for code

Graph4code is project examining whether we can build knowledge graphs that capture the semantics of code. Graph4code has built a knowledge graph for 1.3 million Python programs and corresponding artifacts for code such as StackOverflow posts, class hierarchy information as well as documentation about several hundred popular Python libraries. In this talk I will highlight some use cases for knowledge graphs for code, and highlight initial results for the use of these knowledge graphs.


Dr. Filip Ilievski

Building agents with commonsense knowledge

Filip Ilievski is a Computer Scientist in the Center on Knowledge Graphs within the Information Sciences Institute (ISI) at the USC Viterbi School of Engineering. He holds a Ph.D. in Natural Language Processing from the Vrije Universiteit (VU) in Amsterdam. His principal research interest concerns the role of background knowledge for filling gaps in human communication. He is leading the development of the Commonsense Knowledge Graph (CSKG), a resource which consolidates existing sources into a harmonized representation. CSKG allows us to enhance language models for zero-shot Question Answering with more knowledge, precisely select relevant subsets, or perform explainable inference. He has been heavily involved in the development of the Knowledge Graph ToolKit (KGTK) - a comprehensive set of operations for working with modern, hyper-relational graphs like Wikidata. In the past year, he has worked together with around 10 Ph.D. and Master students, and collaborated with researchers at CMU, Bosch Research, RPI, etc. He has been publishing this work in top-tier venues like AAAI, EMNLP, and ISWC. His home page is https://usc-isi-i2.github.io/ilievski/