Trustworthy Machine Learning under Imperfect Data

The subject of this book centres around trustworthy machine learning under imperfect data. It is primarily designed for scientists, researchers, practitioners, professionals, postgraduates and undergraduates in the field of machine learning and artificial intelligence. The book focuses on trustworthy deep learning under various types of imperfect data, including noisy labels, adversarial examples, and out-of-distribution data. It covers trustworthy machine learning algorithms, theories, and systems.
The main goal of the book is to provide students and researchers in academia with an unbiased and comprehensive literature review. More importantly, it aims to stimulate insightful discussions about the future of trustworthy machine learning. By engaging the audience in more in-depth conversations, the book intends to spark ideas for addressing core problems in this topic. For example, it will explore how to build up benchmark datasets in noisy-supervised learning, how to tackle the emerging adversarial learning, and how to tackle out-of-distribution detection.
For practitioners in the industry, this book will present state-of-the-art trustworthy machine learning methods to help them solve real-world problems in different scenarios, such as online recommendation and web search. While the book will introduce the basics of knowledge required, readers will benefit from having some familiarity with linear algebra, probability, machine learning, and artificial intelligence. The emphasis will be on conveying the intuition behind all formal concepts, theories, and methodologies, ensuring the book remains self-contained at a high level.
 

List of contents

"Chapter1-Introduction".- "Chapter-2,Trustworthy Machine Learning with Noisy Labels".- "Chapter-3,Trustworthy Machine Learning with Adversarial Examples".- "Chapter-4,Trustworthy Machine Learning with Out-of-distribution Data".- "Chapter-5,Advance Topics in Trustworthy Machine Learning".

About the author

Prof. Bo Han is an Assistant Professor in Machine Learning at Hong Kong Baptist University and a BAIHO Visiting Scientist at RIKEN AIP, where his research focuses on machine learning, deep learning, foundation models and their applications. He was a Visiting Faculty Researcher at Microsoft Research and a Postdoc Fellow at RIKEN AIP. He has co authored a machine learning monograph by MIT Press. He has served as Area Chairs of NeurIPS, ICML, ICLR and UAI. He has also served as Action Editors and Editorial Board Members of JMLR, MLJ, JAIR, TMLR and IEEE TNNLS. He received the Outstanding Paper Award at NeurIPS and Outstanding Area Chair at ICLR. He received the RIKEN BAIHO Award (2019), RGC Early CAREER Scheme (2020), Microsoft Research StarTrack Program (2021), and Tencent AI Faculty Research Award (2022). 

Prof. Tongliang Liu is the Director of Sydney AI Centre at University of Sydney, Australia; a Visiting Professor of University of Science and Technology of China, Hefei, China; a Visiting Scientist of RIKEN AIP, Tokyo, Japan; and a Visiting Associate Professor at Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates. He has published more than 100 papers at leading ML/AI conferences and journals. He is regularly the meta reviewer of ICML, NeurIPS, ICLR, UAI, IJCAI, and AAAI. He is the Action Editor of Transactions on Machine Learning Research, Associate Editor of ACM Computing Surveys, and in the Editorial Board of Journal of Machine Learning Research and the Machine Learning journal. He received the ARC DECRA Award in 2018, ARC Future Fellowship Award in 2022, and IEEE AI's 10 to Watch Award in 2023. He also received multiple faculty awards, e.g., from OPPO and Meituan.

Summary

The subject of this book centres around trustworthy machine learning under imperfect data. It is primarily designed for scientists, researchers, practitioners, professionals, postgraduates and undergraduates in the field of machine learning and artificial intelligence. The book focuses on trustworthy deep learning under various types of imperfect data, including noisy labels, adversarial examples, and out-of-distribution data. It covers trustworthy machine learning algorithms, theories, and systems.
The main goal of the book is to provide students and researchers in academia with an unbiased and comprehensive literature review. More importantly, it aims to stimulate insightful discussions about the future of trustworthy machine learning. By engaging the audience in more in-depth conversations, the book intends to spark ideas for addressing core problems in this topic. For example, it will explore how to build up benchmark datasets in noisy-supervised learning, how to tackle the emerging adversarial learning, and how to tackle out-of-distribution detection.
For practitioners in the industry, this book will present state-of-the-art trustworthy machine learning methods to help them solve real-world problems in different scenarios, such as online recommendation and web search. While the book will introduce the basics of knowledge required, readers will benefit from having some familiarity with linear algebra, probability, machine learning, and artificial intelligence. The emphasis will be on conveying the intuition behind all formal concepts, theories, and methodologies, ensuring the book remains self-contained at a high level.
 

Product details

• Authors: Bo Han, Tongliang Liu
• Publisher: Springer, Berlin
• Languages: English
• Product format: Hardback
• Released: 03.10.2025
• EAN: 9789819693955
• ISBN: 978-981-9693-95-5
• No. of pages: 292
• Illustrations: VIII, 292 p. 92 illus., 90 illus. in color.
• Subjects: Natural sciences, medicine, IT, technology > IT, data processing > IT; Künstliche Intelligenz, machine learning, Artificial Intelligence, Out Of Distribution, Trustworthy Machine Learning, Label Noise, Adversarial Noise