AI Fairness for Responsible Intelligence

Erscheinungsjahr 2027
ISBN: 978-981-9251-33-9
Verlag: Springer

Buch, Englisch, 334 Seiten, Format (B × H): 155 mm x 235 mm

Fairness in artificial intelligence is no longer an abstract concern—it shapes decisions in healthcare, education, housing, and beyond. treats fairness not as an isolated algorithmic objective, but as the organizing principle of responsible intelligence, integrating technical foundations with privacy, security, governance, and societal impact throughout the AI lifecycle.

Beginning with the foundations of responsible AI and machine learning, the book examines formal fairness definitions, sources of bias in data and algorithms, and algorithmic approaches for mitigating unfairness. It then explores fairness in natural language processing, computer vision, graph learning, and foundation models, while addressing researcher bias, scientific rigor, and real-world case studies that highlight current challenges and emerging research directions.

Written for advanced undergraduate and graduate students, researchers, instructors, and practitioners across AI, machine learning, data science, healthcare, public policy, and related disciplines, the book equips readers to critically evaluate, design, deploy, and govern fair and trustworthy AI in real-world settings.

Zielgruppe

Research

Autoren/Hrsg.

Zhang, Wenbin

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz

Inhaltsverzeichnis

.- Part I: Foundations of Responsible AI.

.- Chapter 1. Introduction to Fairness in Artificial Intelligence.

.- Chapter 2. Foundations of Machine Learning.

.- Part II: Defining and Measuring Fairness.

.- Chapter 3. Formal Definitions of Fairness.

.- Chapter 4. Bias in Data and Representation.

.- Part III: Fairness Across Modalities.

.- Chapter 5. Fairness in Computer Vision.

.- Chapter 6. Fairness in Natural Language Processing.

.- Chapter 7. Fairness in Networked and Graph Data.

.- Part IV: Mitigation and Robustness.

.- Chapter 8. Debiasing Methods in Machine Learning.

.- Chapter 9. Privacy, Security, and Fairness.

.- Chapter 10. Feedback Loops and Long-Term Impacts.

.- Part V: Human and Societal Perspectives.

.- Chapter 11. Researcher Bias and Human Factors.

.- Chapter 12. Case Studies and Emerging Directions.

Über Autor(innen)

Dr. Wenbin Zhang is an Assistant Professor in the Knight Foundation School of Computing and Information Sciences at Florida International University and an Associate Member of the Te Ipu o Te Mahara Artificial Intelligence Institute. His research focuses on the theoretical foundations of machine learning, with an emphasis on responsible and socially beneficial AI. He has applied his work across multiple domains, including healthcare, digital forensics, energy, transportation, and finance. Dr. Zhang has received several honors, including the NSF CRII Award, the Leibniz Fellowship, the Distinguished Area Chair Award for ECML PKDD 2025, the Outstanding Senior Program Committee Member Award for ECAI 2025, the Distinguished Senior Program Committee Member Award for IJCAI 2023, Data Mining and Knowledge Discovery Editorial Contribution Award, and recognition in the Stanford/Elsevier Top 2% Scientists List. His research has also earned best paper awards/candidates at ECML PKDD 2025, FAccT 2023, ICDM 2023, DAMI, and ICDM 2021, and he was featured in the AAAI 2024 New Faculty Highlights. He actively contributes to the AI and interdisciplinary communities through leadership roles on organizing committees and editorial boards of leading venues, including as Sponsorship Chair for AAAI 2026, Volunteer Chair for WSDM 2024, Associate Editor for ACM Computing Surveys, and Action Editor for Data Mining and Knowledge Discovery.