arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2307.07146cs.DCcs.AI
收藏

无线网络中联邦学习赋能的人工智能生成内容

Federated Learning-Empowered AI-Generated Content in Wireless Networks

University of Macau(澳门大学);Nanyang Technological University(南洋理工大学);Guangdong University of Technology(广东工业大学);Sungkyunkwan University(成均馆大学)

Xumin Huang, Peichun Li, Hongyang Du, Jiawen Kang, Dusit Niyato, Dong In Kim, Yuan Wu

AI总结:

针对无线网络中AIGC集中训练与隐私保护难题,本文提出基于联邦学习的AIGC赋能框架,并通过Stable Diffusion微调案例验证其在通信成本、延迟和隐私方面的优势。

摘要:

人工智能生成内容(AIGC)已成为一项颇具前景的技术,可通过采用多种生成式AI模型来提升内容创作过程的效率、质量、多样性和灵活性。在无线网络中部署AIGC服务有望增强用户体验。然而,现有的AIGC服务提供存在若干局限,例如预训练、微调和推理过程中的集中式训练,尤其是其在具有隐私保护需求的无线网络中的实现。联邦学习(FL)是一种协作学习框架,其中模型训练被分发至协作的数据所有者,而无需共享数据;可利用该框架同时提高AIGC的学习效率并实现隐私保护。为此,我们提出了基于FL的技术以赋能AIGC,旨在使用户能够生成多样化、个性化和高质量的内容。此外,我们使用最先进的AIGC模型(即Stable Diffusion模型)开展了FL辅助AIGC微调的案例研究。数值结果表明,我们的方案在有效降低通信成本和训练延迟以及隐私保护方面具有优势。最后,我们强调了FL与AIGC融合的若干主要研究方向和开放问题。

英文摘要:

Artificial intelligence generated content (AIGC) has emerged as a promising technology to improve the efficiency, quality, diversity and flexibility of the content creation process by adopting a variety of generative AI models. Deploying AIGC services in wireless networks has been expected to enhance the user experience. However, the existing AIGC service provision suffers from several limitations, e.g., the centralized training in the pre-training, fine-tuning and inference processes, especially their implementations in wireless networks with privacy preservation. Federated learning (FL), as a collaborative learning framework where the model training is distributed to cooperative data owners without the need for data sharing, can be leveraged to simultaneously improve learning efficiency and achieve privacy protection for AIGC. To this end, we present FL-based techniques for empowering AIGC, and aim to enable users to generate diverse, personalized, and high-quality content. Furthermore, we conduct a case study of FL-aided AIGC fine-tuning by using the state-of-the-art AIGC model, i.e., stable diffusion model. Numerical results show that our scheme achieves advantages in effectively reducing the communication cost and training latency and privacy protection. Finally, we highlight several major research directions and open issues for the convergence of FL and AIGC.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑