-演講時間: 115年4月1日（三） 14:00~16:00
-演講地點: E6-A207教室
-演講者: Dr. Cheng-Te Li (Department of Computer Science and Information Engineering, National Cheng Kung University)
-演講主題: From Rows to Relations: Graph Neural Networks for Tabular Data Learning
-演講摘要: Tabular data remain the backbone of scientific discovery, industrial decision-making, and financial modeling, yet the methods that dominate—most notably gradient-boosted trees—still treat tables as isolated rows of features. This perspective overlooks a crucial truth: even in "flat" data, hidden relational structures exist. Instances may cluster, features may correlate, and missing values may reveal patterns of dependence. Such latent structure, if uncovered, can dramatically improve prediction, generalization, and interpretability. Graph machine learning offers exactly this lens: it transforms a table into a network of instances and features, enabling the flow of information across related entities and embedding inductive biases that trees and transformers alone cannot capture. In this talk, I will survey four converging directions that exemplify this paradigm. We begin with graph structure learning for tables (TabGSL), dynamically inducing edges to uncover implicit correlations. We then explore bipartite graph neural networks (GTab), which enable holistic learning, zero-shot transfer across divergent schemas, and feature-incremental inference. Next, we examine missingness-aware GNNs (MissGNN), which unify imputation and prediction in a single relational framework. Finally, we highlight graph-regularized boosting (gbtGNN), where trees and GNNs co-train in a synergistic loop, setting new benchmarks across both full-data and few-shot regimes. Together these efforts chart a new research frontier: reimagining tabular learning not as isolated row-wise classification, but as relational reasoning over learned graphs. By embracing this view, we unlock models that are more adaptable, robust, and generalizable, pointing toward the next generation of tabular AI.
講者簡介：Dr. Cheng-Te Li is currently Full Professor at the Department of Computer Science and Information Engineering, National Cheng Kung University (NCKU) in Tainan, Taiwan. He earned his Ph.D. degree in 2013 from the Graduate Institute of Networking and Multimedia at National Taiwan University. Prior to joining NCKU, Dr. Li served as an Assistant Research Fellow at CITI, Academia Sinica, from 2014 to 2016. Focusing on Graph Machine Learning and Data Mining, Dr. Li's research explores their applications in Social Networks, Social Media, Recommender Systems, and Natural Language Processing. His work has been featured at premier conferences such as KDD, TheWebConf (WWW), ICDM, CIKM, SIGIR, IJCAI, ACL, EMNLP, and NAACL. Recently, his group has presented lecture-style tutorials on Graph Neural Networks at top conferences, including WWW, IEEE ICDE, and ACML. Dr. Li's academic achievements have been widely recognized, earning him important awards including the CIEE Outstanding Youth Electrical Engineer Award (2023), Y. Z. Hsu Scientific Paper Award (2022), FAOS Young Scholars' Creativity Award (2021), NSTC Future Tech Awards (2025, 2023, 2021, 2020), TAAI Domestic Track Best Paper Award (2020), K. T. Li Young Researcher Award (2019), and MOST Young Scholar Fellowship (2018). Dr. Li leads the Networked Artificial Intelligence Laboratory (NetAI Lab) at NCKU.
