Invited Speakers
|
Prof. Wei Wang
The Hong Kong University of Science and Technology(Guangzhou)
Title: On Application of AI Methods to Algorithmic Problems on
Graphs
26 November 2022 14:00pm
|
Abstract: With the rapid development of machine learning and deep learning models, there is increasing interest in applying these AI methods to graph computational problems. In this talk, we will introduce some representative work, including some of our recent works, for several algorithmic problem on graph data, such as shortest path queries, subgraph matching, subgraph counting, and querying noisy graphs. We will also outline other promising problems where AI methods may help and list open problems.
Short Biography:
Dr. Wei Wang is a currently a Professor in the Data Science and Analytics
Thrust, Information Hub, The Hong Kong University of Science and Technology
(Guangzhou), China. Before that, he was a Professor in the School of Computer
Science and Engineering, The University of New South Wales, Australia. His
current research interests include Similarity Query Processing, Artificial
Intelligence, Knowledge Graphs, Security for AI Models, and AI for Science.
He has published more than 160 papers in reputed journals and conferences, and
has won the Best Paper Awards in SIGCOMM 2022, ICMR 2021, and the Best Student
Paper at DASFAA 2016. He is an Associate Editor of IEEE Transactions on
Knowledge and Data Engineering and Journal of Materials Informatics, and
program committee members in various first-tier conferences (SIGMOD, VLDB, ICDE,
SIGIR, SIGKDD, etc.).
|
Prof. Haofen Wang
Tongji University
Title: Knowledge enhanced medical visual question answering:
challenges and key technologies
26 November 2022 14:40pm
|
Abstract: In the process of digitization of medical services, a large amount of multi-modal data are generated, including text, images, videos etc. These data contain rich knowledge, but they are not well exploited at present. Multi-modal learning associates and fuses information from different modalities, which complements and enhances knowledge, and enables machines to have the ability to understand multi-modal information closer to humans. This talk mainly introduces the main research direction of multi-modal learning - Visual Question Answering (VQA). Users give clinically relevant questions and medical images in the form of natural language, and the VQA system is able to give an accurate and convincing answer. A mature and complete medical VQA system can directly view patient images and answer any questions. However, medical VQA is technically more challenging than VQA in general domains. This talk will specifically share the related research, potential applications and corresponding challenges of medical VQA based on the characteristics of multi-modal data in the medical field.
Short Biography: Haofen Wang is a research professor at College of Design & Innovation, Tongji University. Prior to that, He served as CTOs for two well-known AI startups. He is also one of the co-founders of OpenKG, the world-largest Chinese open knowledge graph community. He has taken charge of several national AI projects and published more than 100 related papers on top-tier conferences and journals. He developed the first interactive emotional virtual idol in the world. The intelligent assistant he built has answered questions from more than one billion users when they did online shopping. He has also served as deputy directors or chairs for several NGOs like CCF, CIPS and SCS.
|
Dr. Meng Wang
Southeast University
Title: Multimodal Knowledge Discovery: Opportunities and
Challenges
26 November 2022 15:20pm
|
Abstract: Multimodal knowledge has become a popular research topic in many fields, such as knowledge graphs and natural language processing, from online shopping to medical care. Whether it is theoretical research or engineering application, the representation, discovery, and inference of multimodal knowledge have become the core technologies of the academic and industrial concern. This talk focuses on the state of the art of multimodal knowledge discovery and inference and presents future research opportunities and challenges
Short Biography: Meng Wang obtained the doctoral degree from, Xi’an Jiaotong University and was a visiting scholar at the University of Queensland. He was awarded the CCF-Tencent Rhino-Bird Open Fund Award (46 young scientists in the world selected) and the CCF-Baidu Open Fund Award (23 young scientists in the world selected). His research area is in the knowledge graph and cross-modal data.