Abstract
Traditional machine learning excels in modeling scenarios where data points, such as images, are independent of each other. However, as the internet and human knowledge continue to grow, the world becomes increasingly interconnected—a connected world. Notable examples include social media, transportation systems, and e-commerce platforms. We can harness this interconnectedness for machine learning by developing innovative models capable of learning from neighboring data points or friends. In this presentation, I will commence by introducing state-of-the-art deep neural networks in this domain. Subsequently, I will delve into the utilization of textual information from the world to further enhance their capabilities, especially in the era of large language models like ChatGPT. Finally, I will share my insights and experiences on preparing for graduate studies.
Biography
Qiaoyu Tan is a tenure-track assistant professor in the Computer Science Department at NYU Shanghai. He earned his Ph.D. degree in the Department of Computer Science and Engineering at Texas A&M University in August 2023, supervised by Dr. Xia Hu. His research interests center around machine learning and data mining, with a particular focus on graph machine learning, foundation models, multimodal learning, and their applications in bioinformatics and healthcare. His research contributions to this area have led to numerous innovative works presented at top-tier conferences such as KDD, WWW, WSDM, SIGIR, NeurIPS, and TKDE. He was awarded the Best Student Paper Finalist at AMIA’23.