检索结果-内蒙古大学图书馆

QoS-Aware and Cost-Efficient Dynamic Resource Allocation for Serverless ML Workflows

学校读者我要写书评

暂无评论

QoS-Aware and Cost-Efficient Dynamic Resource Allocation for...

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： Hao Wu Junxiao Deng Hao Fan Shadi Ibrahim Song Wu Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Inria Univ. Rennes CNRS IRISA France

Machine Learning (ML) workflows are increasingly deployed on serverless computing platforms to benefit from their elasticity and fine-grain pricing. Proper resource allocation is crucial to achieve fast and cost-efficient execution of serverless ML workflows (specially for hyperparameter tuning and model training). Unfortunately, existing resource allocation methods are static, treat functions equally, and rely on offline prediction, which limit their efficiency. In this paper, we introduce CE-scaling – a Cost-Efficient autoscaling framework for serverless ML work-flows. During the hyperparameter tuning, CE-scaling partitions resources across stages according to their exact usage to minimize resource waste. Moreover, it incorporates an online prediction method to dynamically adjust resources during model training. We implement and evaluate CE-scaling on AWS Lambda using various ML models. Evaluation results show that compared to state-of-the-art static resource allocation methods, CE-scaling can reduce the job completion time and the monetary cost by up to 63% and 41% for hyperparameter tuning, respectively; and by up to 58% and 38% for model training.

关键词：

Breath of Life: A Biofeedback Game with Diverse Breathing Techniques for Enhanced Real-Life Emotion Regulation

学校读者我要写书评

暂无评论

Breath of Life: A Biofeedback Game with Diverse Breathing Te...

2025 CHI Conference on Human Factors in Computing Systems, CHI EA 2025

作者： Chen, Qi Du, Jiachen Yao, Zhihao Feng, Yuanling Liu, Guanhong Ni, Ning Wu, Zhenyu Liu, Haoran Chen, Xijing Mi, Haipeng Wuhan Textile University Wuhan China Tsinghua University Beijing China The Future Laboratory Tsinghua University Beijing China College of Design and Innovation Intelligent Big Data Visualization Lab. Tongji University Shanghai China Department of Psychology University of Chinese Academy of Sciences Beijing China Key Laboratory of Cognitive Science and Mental Health Institute of Psychology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798400713958

Mental health is a critical public health concern, with emotion regulation (ER) playing a pivotal role in maintaining and improving psychological well-being. While respiratory biofeedback games have emerged as effective tools for ER training, existing research predominantly focuses on single-session interventions with limited techniques, emphasizing short-term skill transfer in simulated environments. This approach has led to a significant gap in understanding the long-term application of these techniques in real-life contexts, which is essential for designing effective ER training games. To address this gap, we developed a biofeedback game incorporating four distinct breathing techniques and conducted a 10-week longitudinal study with 25 participants. After one week of training, the majority of participants demonstrated successful transfer of breathing techniques to real-life scenarios. Our findings provide actionable design insights for promoting long-term skill transfer and highlight the potential of respiratory biofeedback games as sustainable tools for emotion regulation training. © 2025 Copyright held by the owner/author(s).

关键词： Affective Communication Breath Breath Sharing Collocated Interaction Pneumatic Display Self-Expression Social Wearable

UWAT-GAN: Fundus Fluorescein Angiography Synthesis via Ultra-wide-angle Transformation Multi-scale GAN

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Fang, Zhaojie Chen, Zhanghao Wei, Pengxue Li, Wangting Zhang, Shaochong Elazab, Ahmed Jia, Gangyong Ge, Ruiquan Wang, Changmiao HDU-ITMO Joint Institute Hangzhou Dianzi University Hangzhou310018 China School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China Shenzhen Eye Hospital Jinan University Shenzhen518040 China School of Biomedical Engineering Shenzhen University Shenzhen518060 China Medical Big Data Lab Shenzhen Research Institure of Big Data Shenzhen518172 China

Fundus photography is an essential examination for clinical and differential diagnosis of fundus diseases. Recently, Ultra-Wide-angle Fundus (UWF) techniques, UWF Fluorescein Angiography (UWF-FA) and UWF Scanning Laser Ophthalmoscopy (UWF-SLO) have been gradually put into use. However, Fluorescein Angiography (FA) and UWF-FA require injecting sodium fluorescein which may have detrimental influences. To avoid negative impacts, cross-modality medical image generation algorithms have been proposed. Nevertheless, current methods in fundus imaging could not produce high-resolution images and are unable to capture tiny vascular lesion areas. This paper proposes a novel conditional generative adversarial network (UWAT-GAN) to synthesize UWF-FA from UWF-SLO. Using multi-scale generators and a fusion module patch to better extract global and local information, our model can generate high-resolution images. Moreover, an attention transmit module is proposed to help the decoder learn effectively. Besides, a supervised approach is used to train the network using multiple new weighted losses on different scales of data. Experiments on an in-house UWF image dataset demonstrate the superiority of the UWAT-GAN over the state-of-the-art methods. The source code is available at: https://***/Tinysqua/UWAT-GAN. Copyright © 2023, The Authors. All rights reserved.

关键词： Generative adversarial networks

MULTIPLE HEADS ARE BETTER THAN ONE: MIXTURE OF MODALITY KNOWLEDGE EXPERTS FOR ENTITY REPRESENTATION LEARNING

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Yichi Chen, Zhuo Guo, Lingbing Xu, Yajing Hu, Binbin Liu, Ziqi Zhang, Wen Chen, Huajun College of Computer Science and Technology Zhejiang University China ZJU-Ant Group Joint Lab of Knowledge Graph China Ant Group China School of Software Technology Zhejiang University China Zhejiang Key Laboratory of Big Data Intelligent Computing China

Learning high-quality multi-modal entity representations is an important goal of multi-modal knowledge graph (MMKG) representation learning, which can enhance reasoning tasks within the MMKGs, such as MMKG completion (MMKGC). The main challenge is to collaboratively model the structural information concealed in massive triples and the multi-modal features of the entities. Existing methods focus on crafting elegant entity-wise multi-modal fusion strategies, yet they overlook the utilization of multi-perspective features concealed within the modalities under diverse relational contexts. To address this issue, we introduce a novel framework with Mixture of Modality Knowledge experts (MOMOK for short) to learn adaptive multi-modal entity representations for better MMKGC. We design relation-guided modality knowledge experts to acquire relation-aware modality embeddings and integrate the predictions from multi-modalities to achieve joint decisions. Additionally, we disentangle the experts by minimizing their mutual information. Experiments on four public MMKG benchmarks demonstrate the outstanding performance of MOMOK under complex scenarios. Our code and data are available at https://***/zjukg/MoMoK. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

SpirDet: Towards Efficient, Accurate and Lightweight Infrared Small Target Detector

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Mao, Qianchen Li, Qiang Wang, Bingshu Zhang, Yongjun Dai, Tao Chen, C.L. Philip The School of Software Northwestern Polytechnical University Taicang Campus Suzhou215400 China The School of Software Northwestern Polytechnical University Xi’an710129 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China The State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China The College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China The School of Computer Science and Engineering South China University of Technology and Pazhou Lab Guangzhou510641 China

In recent years, the detection of infrared small targets using deep learning methods has garnered substantial attention due to notable advancements. To improve the detection capability of small targets, these methods commonly maintain a pathway that preserves high-resolution features of sparse and tiny targets. However, it can result in redundant and expensive computations. To tackle this challenge, we propose SpirDet, a novel approach for efficient detection of infrared small targets. Specifically, to cope with the computational redundancy issue, we employ a new dual-branch sparse decoder to restore the feature map. Firstly, the fast branch directly predicts a sparse map indicating potential small target locations (occupying only 0.5% area of the map). Secondly, the slow branch conducts fine-grained adjustments at the positions indicated by the sparse map. Additionally, we design an lightweight DO-RepEncoder based on reparameterization with the Downsampling Orthogonality, which can effectively reduce memory consumption and inference latency. Extensive experiments show that the proposed SpirDet significantly outperforms state-of-the-art models while achieving faster inference speed and fewer parameters. For example, on the IRSTD-1K dataset, SpirDet improves MIoU by 4.7 and has a 7× FPS acceleration compared to the previous state-of-the-art model. The code will be open to the public. © 2024, CC BY.

关键词： Deep learning

FedAA: A Reinforcement Learning Perspective on Adaptive Aggregation for Fair and Robust Federated Learning 39

学校读者我要写书评

暂无评论

FedAA: A Reinforcement Learning Perspective on Adaptive Aggr...

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： He, Jialuo Chen, Wei Zhang, Xiaojin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan 430074 China School of Microelectronics and Communication Engineering Chongqing University Chongqing 400044 China School of Software Engineering Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)157735897X

Federated Learning (FL) has emerged as a promising approach for privacy-preserving model training across decentralized devices. However, it faces challenges such as statistical heterogeneity and susceptibility to adversarial attacks, which can impact model robustness and fairness. Personalized FL attempts to provide some relief by customizing models for individual clients. However, it falls short in addressing server-side aggregation vulnerabilities. We introduce a novel method called FedAA, which optimizes client contributions via Adaptive Aggregation to enhance model robustness against malicious clients and ensure fairness across participants in non-identically distributed settings. To achieve this goal, we propose an approach involving a Deep Deterministic Policy Gradient-based algorithm for continuous control of aggregation weights, an innovative client selection method based on model parameter distances, and a reward mechanism guided by validation set performance. Empirically, extensive experiments demonstrate that, in terms of robustness, FedAA outperforms the state-of-the-art methods, while maintaining comparable levels of fairness, offering a promising solution to build resilient and fair federated systems. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Reinforcement learning

Individual tree detection and counting based on high-resolution imagery and the canopy height model data

学校读者我要写书评

暂无评论

地球空间信息科学学报（英文版） 2024年第6期27卷中插23,2162-2178页

作者： Ye Zhang Moyang Wang Joseph Mango Liang Xin Chen Meng Xiang Li Key Laboratory of Geographic Information Science(Ministry of Education)and School of Geographic Sciences East China Normal UniversityShanghaiChina Department of Transportation and Geotechnical Engineering University of Dar es SalaamDar es salaamTanzania College of Surveying and Geographic Informatics Tongji UniversityShanghaiChina Cadre School of Shanghai Municipal Bureau of Planning and Natural Resources ShanghaiChina School of Ecology and Environmental Sciences East China Normal UniversityShanghaiChina Key Laboratory of Geographic Information Science(Ministry of Education)and School of Geographic Sciences East China Normal UniversityShanghaiChina Shanghai Key Lab for Urban Ecological Processes and Eco-Restoration East China Normal UniversityShanghaiChina Key Laboratory of Spatial-Temporal Big Data Analysis and Application of Natural Resources in Megacities(Ministry of Natural Resources) East China Normal UniversityShanghaiChina

Individual Tree Detection-and-Counting(ITDC)is among the important tasks in town areas,and numerous methods are proposed in this *** their many advantages,still,the proposed methods are inadequate to provide robust results because they mostly rely on the direct field *** paper presents a novel approach involving high-resolution imagery and the Canopy-Height-Model(CHM)data to solve the ITDC *** new approach is studied in six urban scenes:farmland,woodland,park,industrial land,road and residential ***,it identifies tree canopy regions using a deep learning network from high-resolution *** then deploys the CHM-data to detect treetops of the canopy regions using a local maximum algorithm and individual tree canopies using the region ***,it calculates and describes the number of individual trees and tree *** proposed approach is experimented with the data from Shanghai,*** results show that the individual tree detection method had an average overall accuracy of 0.953,with a precision of 0.987 for woodland ***,the R2 value for canopy segmentation in different urban scenes is greater than 0.780 and 0.779 for canopy area and diameter size,*** results confirm that the proposed method is robust enough for urban tree planning and management.

关键词： Individual tree detection-and-counting(ITDC) deep learning high-resolution imagery Canopy Height Model data(CHM)

Tokenization, Fusion, and Augmentation: Towards Fine-grained Multi-modal Entity Representation

学校读者我要写书评

暂无评论

arXiv 2024年

Multi-modal knowledge graph completion (MMKGC) aims to discover unobserved knowledge from given knowledge graphs, collaboratively leveraging structural information from the triples and multi-modal information of the entities to overcome the inherent incompleteness. Existing MMKGC methods usually extract multi-modal features with pre-trained models, resulting in coarse handling of multi-modal entity information, overlooking the nuanced, fine-grained semantic details and their complex interactions. To tackle this shortfall, we introduce a novel framework MYGO to tokenize, fuse, and augment the fine-grained multi-modal representations of entities and enhance the MMKGC performance. Motivated by the tokenization technology, MYGO tokenizes multi-modal entity information as fine-grained discrete tokens and learns entity representations with a cross-modal entity encoder. To further augment the multi-modal representations, MYGO incorporates fine-grained contrastive learning to highlight the specificity of the entity representations. Experiments on standard MMKGC benchmarks reveal that our method surpasses 19 of the latest models, underlining its superior performance. Code and data can be found in https://***/zjukg/MyGO. Copyright © 2024, The Authors. All rights reserved.

关键词： Knowledge graph

Random noise defense against query-based black-box attacks 21

学校读者我要写书评

暂无评论

Random noise defense against query-based black-box attacks

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Zeyu Qin Yanbo Fan Hongyuan Zha Baoyuan Wu School of Data Science Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen Tencent AI Lab

ISBN: (纸本)9781713845393

The query-based black-box attacks have raised serious threats to machine learning models in many real applications. In this work, we study a lightweight defense method, dubbed Random Noise Defense (RND), which adds proper Gaussian noise to each query. We conduct the theoretical analysis about the effectiveness of RND against query-based black-box attacks and the corresponding adaptive attacks. Our theoretical results reveal that the defense performance of RND is determined by the magnitude ratio between the noise induced by RND and the noise added by the attackers for gradient estimation or local search. The large magnitude ratio leads to the stronger defense performance of RND, and it's also critical for mitigating adaptive attacks. Based on our analysis, we further propose to combine RND with a plausible Gaussian augmentation Fine-tuning (RND-GF). It enables RND to add larger noise to each query while maintaining the clean accuracy to obtain a better trade-off between clean accuracy and defense performance. Additionally, RND can be flexibly combined with the existing defense methods to further boost the adversarial robustness, such as adversarial training (AT). Extensive experiments on CIFAR-10 and ImageNet verify our theoretical findings and the effectiveness of RND and RND-GF.

关键词：