Trustworthy Transfer Learning:
Transferability and Trustworthiness
Jun Wu, Jingrui He
Location: 202A, Long Beach Convention & Entertainment Center, Long Beach, CA
Time and Date: 9 AM - 12 PM, August 6th, 2023.
ABSTRACT
Deep transfer learning investigates the transfer of knowledge or information from a source domain to a relevant target domain via deep neural networks. In this tutorial, we dive into understanding deep transfer learning from the perspective of knowledge transferability and trustworthiness (e.g., privacy, robustness, fairness, transparency, etc.). To this end, we provide a comprehensive review of state-of-the-art theoretical analysis and algorithms for deep transfer learning. To be specific, we start by introducing the concepts of transferability and trustworthiness in the context of deep transfer learning. Then we summarize recent theories and algorithms for understanding knowledge transferability from two aspects: (1) IID transferability: the samples within each domain are independent and identically distributed (e.g., individual images), and (2) non-IID transferability: The samples within each domain are interdependent (e.g., connected nodes within a graph). In addition to knowledge transferability, we also review the impact of trustworthiness on deep transfer learning, e.g., whether the transferred knowledge is adversarially robust or algorithmically fair, how to transfer the knowledge under privacy-preserving constraints, etc. Finally, we highlight the open questions and future directions for understanding deep transfer learning in real-world applications. We believe this tutorial can benefit researchers and practitioners by rethinking the trade-off between knowledge transferability and trustworthiness in developing trustworthy transfer learning systems.
TUTORIAL SLIDES
OUTLINE
Introduction
Part I: Knowledge Transferability
Part I-1: IID Transferability
Domain Discrepancy (Data-level)
Task Diversity (Task-level)
Transferability Measures (Model-level)
Part I-2: Non-IID Transferability
Graph Transferability
Text Transferability
Time-series Transferability
Part II: Knowledge Trustworthiness
Part II-1: Adversarial Robustness
Attack
Defense
Part II-2: Privacy
Source-free Hypothesis Transfer
Federated Learning
Part II-3: Fairness
Individual Fairness
Group Fairness
Part II-4: Transparency and Explainability
Feature-level Explainability
Prediction-level Uncertainty
Part III: Open Questions and Future Trends
Multi-dimensional Distribution Shifts
Universal Trustworthiness
Tradeoff between Transferability and Trustworthiness
SPEAKERS
Jun Wu is currently a Ph.D. candidate at the Department of Computer Science, University of Illinois at Urbana-Champaign. His research interests focus on statistical machine learning and trustworthy transfer learning, adversarial learning, with applications in image recognition, graph mining, recommender system, and agriculture analysis. He has published multiple articles in the top peer-reviewed conferences and journals (e.g., NeurIPS, KDD, CIKM, AAAI, IJCAI, TKDE, etc.). He has also served as a program committee member in major machine learning and artificial intelligence conferences (e.g., ICML, NeurIPS, KDD, AAAI, IJCAI, etc.). For more information, please refer to his personal website at https://publish.illinois.edu/junwu3/.
Jingrui He is an associate professor in the School of Information Sciences at the University of Illinois Urbana-Champaign. She received her PhD from Carnegie Mellon University in 2010. Her research focuses on heterogeneous machine learning, rare category analysis, active learning and semi-supervised learning, with applications in security, social network analysis, healthcare, and manufacturing processes. Dr. He is the recipient of the 2016 NSF CAREER Award, the 2020 OAT Award, three-time recipient of the IBM Faculty Award in 2018, 2015, and 2014, and was selected as IJCAI 2017 Early Career Spotlight. Dr. He has more than 100 publications at major conferences (e.g., IJCAI, AAAI, KDD, ICML, NeurIPS) and journals (e.g., TKDE, TKDD, DMKD), and is the author of two books. Her papers have received the Distinguished Paper Award at FAccT 2022, as well as Bests of the Conference at ICDM 2016, ICDM 2010, and SDM 2010. For more information, please refer to her personal website at https://www.hejingrui.org/.