Zobrazeno 1 - 10
of 1 509
pro vyhledávání: '"Guan, Hui"'
The rapid adoption of machine learning (ML) has underscored the importance of serving ML models with high throughput and resource efficiency. Traditional approaches to managing increasing query demands have predominantly focused on hardware scaling,
Externí odkaz:
http://arxiv.org/abs/2407.03583
It is extremely memory-hungry to train Large Language Models (LLM). To solve this problem, existing work exploits the combination of CPU and GPU for the training process, such as ZeRO-Offload. Such a technique largely democratizes billion-scale model
Externí odkaz:
http://arxiv.org/abs/2406.08334
Graph Neural Networks (GNNs) have gained significant attention in recent years due to their ability to learn representations of graph structured data. Two common methods for training GNNs are mini-batch training and full-graph training. Since these t
Externí odkaz:
http://arxiv.org/abs/2406.00552
Finetuning large language models (LLMs) in federated learning (FL) settings has become important as it allows resource-constrained devices to finetune a model using private data. However, finetuning LLMs using backpropagation requires excessive memor
Externí odkaz:
http://arxiv.org/abs/2405.15551
Graph pattern matching is a fundamental problem encountered by many common graph mining tasks and the basic building block of several graph mining systems. This paper explores for the first time how to proactively prune graphs to speed up graph patte
Externí odkaz:
http://arxiv.org/abs/2403.01050
Autor:
Zhang, Lijun, Liu, Xiao, Martin, Antoni Viros, Bearfield, Cindy Xiong, Brun, Yuriy, Guan, Hui
Watermarking images is critical for tracking image provenance and claiming ownership. With the advent of generative models, such as stable diffusion, able to create fake but realistic images, watermarking has become particularly important, e.g., to m
Externí odkaz:
http://arxiv.org/abs/2401.04247
While existing strategies to execute deep learning-based classification on low-power platforms assume the models are trained on all classes of interest, this paper posits that adopting context-awareness i.e. narrowing down a classification task to th
Externí odkaz:
http://arxiv.org/abs/2310.19112
Multi-Task Learning (MTL) involves developing a singular model, known as a multi-task model, to concurrently perform multiple tasks. While the security of single-task models has been thoroughly studied, multi-task models pose several critical securit
Externí odkaz:
http://arxiv.org/abs/2305.12066
Publikováno v:
Chengshi guidao jiaotong yanjiu, Vol 27, Iss 6, Pp 95-99 (2024)
Objective The large section tunnel, due to flat shape and large span, usually adopts multiple steps and staged excavation. In the process of construction, the surrounding rock and the temporary support are repeatedly disturbed, affecting the stabilit
Externí odkaz:
https://doaj.org/article/5c5b53bf0878443bb56474d6b3520f40
Although multi-task deep neural network (DNN) models have computation and storage benefits over individual single-task DNN models, they can be further optimized via model compression. Numerous structured pruning methods are already developed that can
Externí odkaz:
http://arxiv.org/abs/2304.06840