Zobrazeno 1 - 10
of 366
pro vyhledávání: '"Guan Haibing"'
Publikováno v:
中国工程科学, Vol 23, Iss 2, Pp 104-111 (2021)
As the industrial Internet deeply integrated with manufacturing, the drive capability of industrial intelligence becomes prominent regarding the digitization and informatization of the manufacturing industry. Meanwhile, new applications propose highe
Externí odkaz:
https://doaj.org/article/d6732fef6bbe4bf3b5a877904774a4e4
Without direct access to the client's data, federated learning (FL) is well-known for its unique strength in data privacy protection among existing distributed machine learning techniques. However, its distributive and iterative nature makes FL inher
Externí odkaz:
http://arxiv.org/abs/2407.15389
Few-shot fine-tuning of Diffusion Models (DMs) is a key advancement, significantly reducing training costs and enabling personalized AI applications. However, we explore the training dynamics of DMs and observe an unanticipated phenomenon: during the
Externí odkaz:
http://arxiv.org/abs/2405.19931
Diffusion Models (DMs) have evolved into advanced image generation tools, especially for few-shot generation where a pretrained model is fine-tuned on a small set of images to capture a specific style or object. Despite their success, concerns exist
Externí odkaz:
http://arxiv.org/abs/2403.11162
Autor:
Yan, Peishen, Wang, Hao, Song, Tao, Hua, Yang, Ma, Ruhui, Hu, Ningxin, Haghighat, Mohammad R., Guan, Haibing
Federated Learning (FL) is becoming a popular paradigm for leveraging distributed data and preserving data privacy. However, due to the distributed characteristic, FL systems are vulnerable to Byzantine attacks that compromised clients attack the glo
Externí odkaz:
http://arxiv.org/abs/2312.12484
Autor:
Zhang, Jianqing, Hua, Yang, Wang, Hao, Song, Tao, Xue, Zhengui, Ma, Ruhui, Cao, Jian, Guan, Haibing
Federated Learning (FL) is popular for its privacy-preserving and collaborative learning capabilities. Recently, personalized FL (pFL) has received attention for its ability to address statistical heterogeneity and achieve personalization in FL. Howe
Externí odkaz:
http://arxiv.org/abs/2308.10279
Deploying deep learning models in cloud clusters provides efficient and prompt inference services to accommodate the widespread application of deep learning. These clusters are usually equipped with host CPUs and accelerators with distinct responsibi
Externí odkaz:
http://arxiv.org/abs/2307.11339
Recently, personalized federated learning (pFL) has attracted increasing attention in privacy protection, collaborative learning, and tackling statistical heterogeneity among clients, e.g., hospitals, mobile smartphones, etc. Most existing pFL method
Externí odkaz:
http://arxiv.org/abs/2307.01217
Autor:
Liang, Chumeng, Wu, Xiaoyu, Hua, Yang, Zhang, Jiaru, Xue, Yiming, Song, Tao, Xue, Zhengui, Ma, Ruhui, Guan, Haibing
Recently, Diffusion Models (DMs) boost a wave in AI for Art yet raise new copyright concerns, where infringers benefit from using unauthorized paintings to train DMs to generate novel paintings in a similar style. To address these emerging copyright
Externí odkaz:
http://arxiv.org/abs/2302.04578
A key challenge in federated learning (FL) is the statistical heterogeneity that impairs the generalization of the global model on each client. To address this, we propose a method Federated learning with Adaptive Local Aggregation (FedALA) by captur
Externí odkaz:
http://arxiv.org/abs/2212.01197