Tutorial 1

Title: Mining of Real-world Hypergraphs: Patterns, Tools, and Generators


09:00 ~ 10:45 am, 14 February 2023 (Tuesday), MasonGlad Hotel, Jeju, South Korea


Ki-Jung Shin/Geon Lee




Group interactions are prevalent in various complex systems (e.g., collaborations of researchers and group discussions on online Q\&A sites), and they are commonly modeled as hypergraphs. Hyperedges, which compose a hypergraph, are non-empty subsets of any number of nodes, and thus each hyperedge naturally represents a group interaction among entities. The higher-order nature of hypergraphs brings about unique structural properties that have not been considered in ordinary pairwise graphs. In this tutorial, we offer a comprehensive overview of a new research topic called hypergraph mining. Specifically, we first present recently revealed structural properties of real-world hypergraphs, including (a) static and dynamic patterns, (b) global and local patterns, and (c) connectivity and overlapping patterns.  Together with the patterns, we describe advanced data mining tools used for their discovery. Lastly, we introduce simple yet realistic hypergraph generative models that provide an explanation of the structural properties.



Geon Lee is a Ph.D. student at the Kim Jaechul Graduate School of AI at KAIST. He received his B.S. degree in Computer Science and Engineering from Sungkyunkwan University in 2019. His research interests include graph mining and its applications, and especially, his studies of hypergraphs have appeared in major data mining venues, including VLDB, WWW, and  ICDM. More details can be found at https://geonlee0325.github.io.

Kijung Shin is an Ewon Endowed Assistant Professor (jointly affiliated) in the Kim Jaechul Graduate School of AI and the School of Electrical Engineering at KAIST. He received his Ph.D. from the Computer Science Department at Carnegie Mellon University in 2019.  He has published more than 50 referred articles in major data mining venues, including KDD, WWW, and ICDM, and he won the best research paper award at KDD 2016. His research interests span a wide range of topics on graph mining, with a focus on scalable algorithm design and empirical analysis of real-world hypergraphs. More details can be found at https://kijungs.github.io/.


Tutorial 2

Title: Machine Learning Fairness and its Convergence with Robustness


13:15 ~ 15:00 pm, 14 February 2023 (Tuesday), MasonGlad Hotel, Jeju, South Korea


Steven Euijong Whang/Yuji Roh




Responsible AI becomes critical where fairness and robustness must be satisfied together. Traditionally, the two topics have been studied by different communities for different applications. Fair training primarily deals with biased data where structured data is typically considered. In comparison, robust training is designed for noisy or poisoned data where image data is typically considered. Nevertheless, fair training and robust training are fundamentally similar in fixing inherent flaws of real-world data. In this tutorial, we will first cover fairness techniques that consist of pre-processing, in-processing, and post-processing unfairness mitigation techniques, depending on whether the mitigation occurs before, during, or after the model training. Next, we will briefly give an overview of robust training techniques where most of the research is on combating various label noises. Finally, we will cover the recent trend of combining fair and robust training in three flavors: fairness-oriented, robust-oriented, and equal mergers.



Steven Euijong Whang is an associate professor at KAIST EE and AI. His research interests include Responsible AI and Data-centric AI. Previously he was a Research Scientist at Google Research and co-developed the data infrastructure of the TensorFlow Extended (TFX) machine learning platform. Steven received his Ph.D. in computer science in 2012 from Stanford University and his B.S. in computer science from KAIST in 2003. He is a Kwon Oh-Hyun Endowed Chair Professor (2020-2023) and received a Google Research Award (2022) and a Google AI Focused Research Award (2018, the first in Asia). Homepage: https://stevenwhang.com

Yuji Roh is a Ph.D. candidate at KAIST EE. Her research interests include Responsible AI, model fairness, and human-centered AI. She is a recipient of the Microsoft Research Ph.D. Fellowship in 2022 and Qualcomm Innovation Fellowship Korea in 2020. She recently worked as a research intern at NVIDIA Research. She received her B.S. degree in Electrical Engineering from KAIST in 2018. Homepage: https://www.yujiroh.com/



ⓒ Copyright 2023 KIISE – All Rights Reserved.

[KIISE] Korean Institute of Information Scientists and Engineers

#401 Meorijae Bldg., 76, Bangbae-ro, Seocho-gu, Seoul 06704, Korea

Email: mkim@kiise.or.kr | Fax: +82-2-521-1352 | Homepage: www.kiise.or.kr

Business Registration Number: 114-82-03170