Zobrazeno 1 - 10
of 592
pro vyhledávání: '"Rajasekaran, Sanguthevar"'
Autor:
Jin, Can, Peng, Hongwu, Zhao, Shiyu, Wang, Zhenting, Xu, Wujiang, Han, Ligong, Zhao, Jiahui, Zhong, Kai, Rajasekaran, Sanguthevar, Metaxas, Dimitris N.
Large Language Models (LLMs) have significantly enhanced Information Retrieval (IR) across various modules, such as reranking. Despite impressive performance, current zero-shot relevance ranking with LLMs heavily relies on human prompt engineering. E
Externí odkaz:
http://arxiv.org/abs/2406.14449
Autor:
Deng, Jieren, Wang, Chenghong, Meng, Xianrui, Wang, Yijue, Li, Ji, Lin, Sheng, Han, Shuo, Miao, Fei, Rajasekaran, Sanguthevar, Ding, Caiwen
In this work, we consider the problem of designing secure and efficient federated learning (FL) frameworks. Existing solutions either involve a trusted aggregator or require heavyweight cryptographic primitives, which degrades performance significant
Externí odkaz:
http://arxiv.org/abs/2201.11934
Autor:
Huang, Shaoyi, Xu, Dongkuan, Yen, Ian E. H., Wang, Yijue, Chang, Sung-en, Li, Bingbing, Chen, Shiyang, Xie, Mimi, Rajasekaran, Sanguthevar, Liu, Hang, Ding, Caiwen
Conventional wisdom in pruning Transformer-based language models is that pruning reduces the model expressiveness and thus is more likely to underfit rather than overfit. However, under the trending pretrain-and-finetune paradigm, we postulate a coun
Externí odkaz:
http://arxiv.org/abs/2110.08190
Autor:
Deng, Jieren, Wang, Yijue, Li, Ji, Shang, Chao, Liu, Hang, Rajasekaran, Sanguthevar, Ding, Caiwen
Although federated learning has increasingly gained attention in terms of effectively utilizing local devices for data privacy enhancement, recent studies show that publicly shared gradients in the training process can reveal the private training ima
Externí odkaz:
http://arxiv.org/abs/2103.06819
Autor:
Wang, Yijue, Deng, Jieren, Guo, Dan, Wang, Chenghong, Meng, Xianrui, Liu, Hang, Ding, Caiwen, Rajasekaran, Sanguthevar
Distributed learning such as federated learning or collaborative learning enables model training on decentralized data from users and only collects local gradients, where data is processed close to its sources for data privacy. The nature of not cent
Externí odkaz:
http://arxiv.org/abs/2009.06228
Autor:
Wang, Yijue, Wang, Chenghong, Wang, Zigeng, Zhou, Shanglin, Liu, Hang, Bi, Jinbo, Ding, Caiwen, Rajasekaran, Sanguthevar
Publikováno v:
IJCAI, 2021
The large model size, high computational operations, and vulnerability against membership inference attack (MIA) have impeded deep learning or deep neural networks (DNNs) popularity, especially on mobile devices. To address the challenge, we envision
Externí odkaz:
http://arxiv.org/abs/2008.13578
The closest pair of points problem or closest pair problem (CPP) is an important problem in computational geometry where we have to find a pair of points from a set of points in metric space with the smallest distance between them. This problem arise
Externí odkaz:
http://arxiv.org/abs/2007.16111
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Polyspectral estimation is a problem of great importance in the analysis of nonlinear time series that has applications in biomedical signal processing, communications, geophysics, image, radar, sonar and speech processing, etc. Higher order spectra
Externí odkaz:
http://arxiv.org/abs/1805.11775