Trustworthy Hypothesis Transfer Learning

可信假设迁移学习

• 批准号: DE240101089
• 负责人: Dr Feng Liu
• 金额: $ 30.28万
• 依托单位: The University of Melbourne
• 依托单位国家: 澳大利亚
• 项目类别: Discovery Early Career Researcher Award
• 财政年份: 2024
• 资助国家: 澳大利亚
• 起止时间: 2024-01-01 至 2026-12-31
• 项目状态: 未结题
• 来源: https://dataportal.arc.gov.au/RGS/Web/Grants/DE240101089
• 关键词: Trustworthy; Hypothesis; Transfer; Learning; Trustworthy; Hypothesis; Transfer; Learning

It is urgent to develop a new hypothesis transfer learning scheme that can overcome potential risks when finetuning unreliable large-scale pre-trained models. This project aims to develop an advanced and reliable scheme of hypothesis transfer learning, called Trustworthy Hypothesis Transfer Learning (TrustHTL). A new theoretically guaranteed heterogeneous hypothesis transfer learning framework will be developed to handle heterogeneous situations; a methodology to disinherit risks of pre-trained models and a new fuzzy relation based distributional discrepancy in heterogeneous transfer learning scenarios. The outcomes should significantly improve the reliability of machine learning with benefits for safety learning in data analytics.

迫切需要制定一种新的假设转移学习计划，该方案在鉴定不可靠的大规模预训练模型时可以克服潜在的风险。该项目旨在制定一个高级可靠的假设转移学习方案，称为可信赖的假设转移学习（TRUSTHTL）。将开发一个新的理论保证的异质假设转移学习框架来处理异质情况。在异质转移学习方案中，使用预训练模型的风险和基于模糊关系的新分布差异的方法。结果应显着提高机器学习的可靠性，并在数据分析中获得安全学习的好处。