Technology Category
Machine Learning: Transfer, Domain Adaptation, Multi-Task LearningPhilosophy and Ethics of AI: Safety, Robustness & TrustworthinessGame Theory and Economic Paradigms: Adversarial Learning
Trustworthy Transfer Learning: A Survey
🤖 AI Summary
This study addresses two core challenges in transfer learning: quantitative assessment of knowledge transferability and assurance of trustworthiness. First, it systematically formalizes transfer learning from a trustworthiness perspective, proposing a novel “transferability–trustworthiness” co-evaluation framework; theoretically characterizes transferability bounds under non-IID settings; and develops a new transfer paradigm incorporating multi-dimensional trust constraints—privacy, robustness, and fairness. Methodologically, it integrates statistical learning theory, adversarial robustness analysis, fairness metrics, differential privacy mechanisms, and mainstream transfer approaches (e.g., domain adaptation, meta-transfer learning, federated transfer learning). Key contributions include: (1) establishing the first holistic framework spanning theoretical modeling, quantitative trust attribute measurement, and empirical validation; and (2) identifying three open research directions—trustworthy non-IID transfer, standardized trustworthiness benchmarks, and cross-domain causal generalization.
Technology Category
Application Category
📝 Abstract
Transfer learning aims to transfer knowledge or information from a source domain to a relevant target domain. In this paper, we understand transfer learning from the perspectives of knowledge transferability and trustworthiness. This involves two research questions: How is knowledge transferability quantitatively measured and enhanced across domains? Can we trust the transferred knowledge in the transfer learning process? To answer these questions, this paper provides a comprehensive review of trustworthy transfer learning from various aspects, including problem definitions, theoretical analysis, empirical algorithms, and real-world applications. Specifically, we summarize recent theories and algorithms for understanding knowledge transferability under (within-domain) IID and non-IID assumptions. In addition to knowledge transferability, we review the impact of trustworthiness on transfer learning, e.g., whether the transferred knowledge is adversarially robust or algorithmically fair, how to transfer the knowledge under privacy-preserving constraints, etc. Beyond discussing the current advancements, we highlight the open questions and future directions for understanding transfer learning in a reliable and trustworthy manner.
Problem
Research questions and friction points this paper is trying to address.
Quantitatively measuring and enhancing knowledge transferability across domains
Ensuring transferred knowledge is trustworthy and reliable in practice
Addressing adversarial robustness and fairness in transfer learning processes
Innovation
Methods, ideas, or system contributions that make the work stand out.
Quantifying knowledge transferability across domains
Ensuring adversarial robustness in transferred knowledge
Transferring knowledge under privacy-preserving constraints
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
Michigan State University | University of Illinois Urbana-Champaign
