Zobrazeno 1 - 10
of 237
pro vyhledávání: '"Zhao, Tianli"'
Recently, graph-based models designed for downstream tasks have significantly advanced research on graph neural networks (GNNs). GNN baselines based on neural message-passing mechanisms such as GCN and GAT perform worse as the network deepens. Theref
Externí odkaz:
http://arxiv.org/abs/2301.10536
Large neural networks are difficult to deploy on mobile devices because of intensive computation and storage. To alleviate it, we study ternarization, a balance between efficiency and accuracy that quantizes both weights and activations into ternary
Externí odkaz:
http://arxiv.org/abs/2204.01234
Federated learning frameworks typically require collaborators to share their local gradient updates of a common model instead of sharing training data to preserve privacy. However, prior works on Gradient Leakage Attacks showed that private training
Externí odkaz:
http://arxiv.org/abs/2112.14087
For practical deep neural network design on mobile devices, it is essential to consider the constraints incurred by the computational resources and the inference latency in various applications. Among deep network acceleration related approaches, pru
Externí odkaz:
http://arxiv.org/abs/2110.08013
Publikováno v:
In Engineering Failure Analysis August 2024 162
Autor:
Zhao, Tianli, Zhang, Bing, Zhang, Zhijuan, Zhao, Jie, Zhan, Shancheng, Dang, Longjie, Zhang, Zengwen, Cai, Jun, Wang, Kuaishe
Publikováno v:
In Materials Characterization June 2024 212
Acceleration of deep neural networks to meet a specific latency constraint is essential for their deployment on mobile devices. In this paper, we design an architecture aware latency constrained sparse (ALCS) framework to prune and accelerate CNN mod
Externí odkaz:
http://arxiv.org/abs/2109.00170
Autor:
Gao, Huan, Zhang, Bing, Fan, Yu, Zhang, Zhijuan, Nan, Hongqiang, Zhao, Tianli, Lei, Zhiqiang, Cai, Jun, Wang, Kuaishe
Publikováno v:
In Journal of Materials Research and Technology May-June 2024 30:197-209
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Zhang, Zhijuan, Zhang, Bing, Dang, Xiaohan, Zhao, Tianli, Xie, Yingchun, Cai, Jun, Wang, Kuaishe
Publikováno v:
In Journal of Materials Research and Technology September-October 2023 26:2941-2956