Robust Federated Learning for Imperfect Decentralised Data

针对不完美的去中心化数据的鲁棒联邦学习

• 批准号: DP220100768
• 负责人: Prof Chengqi Zhang
• 金额: $ 24.82万
• 依托单位: University of Technology Sydney
• 依托单位国家: 澳大利亚
• 项目类别: Discovery Projects
• 财政年份: 2022
• 资助国家: 澳大利亚
• 起止时间: 2022-01-01 至 2024-12-31
• 项目状态: 已结题
• 来源: https://dataportal.arc.gov.au/RGS/Web/Grants/DP220100768
• 关键词: Robust; Federated; Learning; Imperfect; Decentralised

This project aims to develop a next-generation robust federated learning framework to tackle the challenging scenarios of imperfect decentralised data in real applications, e.g. mobile phones and the Internet of Things (IoT) devices. The outcomes will bring great benefits to a broad range of industry sectors by providing novel large-scale intelligent applications with privacy preservation. The proposed method will advance the development of a cutting-edge technique to develop new intelligent applications in a decentralised and privacy-sensitive scenario. This game-changing research will advance current data mining and artificial intelligence research from centralised intelligence to decentralised intelligence with a collaboration network.

该项目旨在开发下一代强大的联邦学习框架，以解决真实的应用程序中不完美的分散数据的挑战性场景，例如移动的电话和物联网（IoT）设备。这些成果将通过提供具有隐私保护的新型大规模智能应用，为广泛的行业领域带来巨大利益。该方法将推动尖端技术的发展，以在分散和隐私敏感的场景中开发新的智能应用程序。这项改变游戏规则的研究将推动当前的数据挖掘和人工智能研究从集中式智能到具有协作网络的分散式智能。