Zobrazeno 1 - 10
of 139
pro vyhledávání: '"Sun, Guangzhong"'
The integration of large language models (LLMs) with external content has enabled more up-to-date and wide-ranging applications of LLMs, such as Microsoft Copilot. However, this integration has also exposed LLMs to the risk of indirect prompt injecti
Externí odkaz:
http://arxiv.org/abs/2312.14197
Federated learning is an emerging distributed machine learning method, enables a large number of clients to train a model without exchanging their local data. The time cost of communication is an essential bottleneck in federated learning, especially
Externí odkaz:
http://arxiv.org/abs/2309.09719
Autor:
Peng, Wenjun, Yi, Jingwei, Wu, Fangzhao, Wu, Shangxi, Zhu, Bin, Lyu, Lingjuan, Jiao, Binxing, Xu, Tong, Sun, Guangzhong, Xie, Xing
Large language models (LLMs) have demonstrated powerful capabilities in both text understanding and generation. Companies have begun to offer Embedding as a Service (EaaS) based on these LLMs, which can benefit various natural language processing (NL
Externí odkaz:
http://arxiv.org/abs/2305.10036
Autor:
Sun, Hao, Shen, Li, Zhong, Qihuang, Ding, Liang, Chen, Shixiang, Sun, Jingwei, Li, Jing, Sun, Guangzhong, Tao, Dacheng
Sharpness aware minimization (SAM) optimizer has been extensively explored as it can generalize better for training deep neural networks via introducing extra perturbation steps to flatten the landscape of deep learning models. Integrating SAM with a
Externí odkaz:
http://arxiv.org/abs/2303.00565
Proxy applications (proxy-apps) are basic tools for evaluating the performance of specific workloads on high-performance computing (HPC) systems.Since the development of high-fidelity proxy-apps, which exhibit similar performance characteristics as c
Externí odkaz:
http://arxiv.org/abs/2301.06062
Autor:
Yi, Jingwei, Wu, Fangzhao, Wu, Chuhan, Huang, Xiaolong, Jiao, Binxing, Sun, Guangzhong, Xie, Xing
Query-aware webpage snippet extraction is widely used in search engines to help users better understand the content of the returned webpages before clicking. Although important, it is very rarely studied. In this paper, we propose an effective query-
Externí odkaz:
http://arxiv.org/abs/2210.08809
Federated learning (FL) enables multiple clients to collaboratively train models without sharing their local data, and becomes an important privacy-preserving machine learning framework. However, classical FL faces serious security and robustness pro
Externí odkaz:
http://arxiv.org/abs/2205.10848
Autor:
Yang, Junhan, Liu, Zheng, Xiao, Shitao, Lian, Jianxun, Wu, Lijun, Lian, Defu, Sun, Guangzhong, Xie, Xing
The lack of labeled data is a major obstacle to learning high-quality sentence embeddings. Recently, self-supervised contrastive learning (SCL) is regarded as a promising way to address this problem. However, the existing works mainly rely on hand-cr
Externí odkaz:
http://arxiv.org/abs/2202.13802
News recommendation is critical for personalized news distribution. Federated news recommendation enables collaborative model learning from many clients without sharing their raw data. It is promising for privacy-preserving news recommendation. Howev
Externí odkaz:
http://arxiv.org/abs/2202.06701
Publikováno v:
EMNLP 2021;page 2814-2824
News recommendation is critical for personalized news access. Most existing news recommendation methods rely on centralized storage of users' historical news click behavior data, which may lead to privacy concerns and hazards. Federated Learning is a
Externí odkaz:
http://arxiv.org/abs/2109.05446