Algebraic Structures in Weakly Supervised Disentangled Representation Learning

弱监督解缠表示学习中的代数结构

• 批准号: 22KJ0880
• 负责人: 張 一凡
• 金额: $ 1.09万
• 依托单位: The University of Tokyo
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for JSPS Fellows
• 财政年份: 2023
• 资助国家: 日本
• 起止时间: 2023-03-08 至 2024-03-31
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-22KJ0880/
• 关键词: 機械学習; 圏論; machine learning; disentanglement; category theory

In this project, "Algebraic Structures in Weakly Supervised Disentangled Representation Learning", we aimed to develop theoretical tools and practical algorithms for learning abstract and meaningful representations. As the first step, we conducted a meta-analysis of various definitions of disentanglement in machine learning. Using category theory as a unifying framework, we revealed the similarities and differences between different definitions. We also introduced tools to analyze disentanglement in different settings, including equivariant maps and stochastic maps. Our findings can help researchers choose the most appropriate definition of disentanglement for their specific task and discover better metrics, models, and algorithms.

在这个项目“弱监督解缠表示学习中的代数结构”中，我们的目标是开发用于学习抽象和有意义的表示的理论工具和实用算法。作为第一步，我们对机器学习中解缠的各种定义进行了元分析。以范畴理论为统一框架，揭示了不同定义之间的异同。我们还介绍了在不同环境下分析解缠的工具，包括等变映射和随机映射。我们的发现可以帮助研究人员为他们的特定任务选择最合适的解缠定义，并发现更好的度量、模型和算法。

项目成果

A Category-theoretical Meta-analysis of Definitions of Disentanglement

解开定义的范畴论元分析

• 发表时间: 2023
• 作者: Yivan Zhang;Masashi Sugiyama
• 通讯作者: Masashi Sugiyama

Neural Information Processing Systems 2022

神经信息处理系统 2022

• 发表时间: 2022