检索结果-内蒙古大学图书馆

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Zehao Li Jiachun Liao Jinhao Yu Lei Zhang Department of Computer Science and Engineering Shanghai Jiao Tong University China Big Data Research Center Nanhu Laboratory Jiaxing China

ISBN: (数字)9798331506209

ISBN: (纸本)9798331506216

The transformer has profoundly driven the development of natural language processing and computer vision tasks. However, their widespread deployment has raised concerns about the potential leakage of data privacy. To address the issue, homomorphic encryption (HE) is employed as a secure technique to process user private inputs over ciphertexts. As HE only supports linear operations, non-linear functions are required to be approximated into polynomials, which leads to heavy communication and computation overhead. In this paper, we propose THEF (Tee-And-HE-based Framework), an efficient and secure inference framework for transformer inference, which uses HE to ensure data security and leverages Trusted Execution Environment (TEE) to reduce communication and computation cost. We also design a number of optimization methods, including expanding encoding matrix multiplication scheme, batch acceleration and adaptive scheme, to improve performances of the THEF. Finally, we compare the performances of THEF and the state-of-the-art methods. The experimental results demonstrate that THEF maintains a level of accuracy close to that of plaintext model, reduces end-to-end communication cost by 80% and achieves significant improvement in end-to-end run-time.

关键词： Privacy Costs Accuracy Noise Optimization methods Transformers Encoding Polynomials Safety Homomorphic encryption

来源：评论

学校读者我要写书评

暂无评论

CLDG: Contrastive Learning on Dynamic Graphs 39

CLDG: Contrastive Learning on Dynamic Graphs

引用

39th IEEE International Conference on data engineering, ICDE 2023

作者： Xu, Yiming Shi, Bin Ma, Teng Dong, Bo Zhou, Haoyi Zheng, Qinghua Xi'an Jiaotong University Department of Computer Science and Technology China Xi'an Jiaotong University Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering China Xi'an Jiaotong University Department of Distance Education China Beihang University School of Software China Beihang University Advanced Innovation Center for Big Data and Brain Computing China

ISBN: (纸本)9798350322279

The graph with complex annotations is the most potent data type, whose constantly evolving motivates further exploration of the unsupervised dynamic graph representation. One of the representative paradigms is graph contrastive learning. It constructs self-supervised signals by maximizing the mutual information between the statistic graph's augmentation views. However, the semantics and labels may change within the augmentation process, causing a significant performance drop in downstream tasks. This drawback becomes greatly magnified on dynamic graphs. To address this problem, we designed a simple yet effective framework named CLDG. Firstly, we elaborate that dynamic graphs have temporal translation invariance at different levels. Then, we proposed a sampling layer to extract the temporally-persistent signals. It will encourage the node to maintain consistent local and global representations, i.e., temporal translation invariance under the timespan views. The extensive experiments demonstrate the effectiveness and efficiency of the method on seven datasets by outperforming eight unsupervised state-of-the-art baselines and showing competitiveness against four semi-supervised methods. Compared with the existing dynamic graph method, the number of model parameters and training time is reduced by an average of 2,001.86 times and 130.31 times on seven datasets, respectively. The code and data are available at: https://***/yimingxu24/CLDG. © 2023 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Class-Incremental Semantic Segmentation via Pseudo-Labeling and Knowledge Distillation 4

Few-Shot Class-Incremental Semantic Segmentation via Pseudo-...

引用

4th International Conference on Information Science, Parallel and Distributed Systems, ISPDS 2023

作者： Jiang, Chengjia Wang, Tao Li, Sien Wang, Jinyang Wang, Shirui Antoniou, Antonios Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou China Fujian Education Institutions Wuyi University The Key Laboratory of Cognitive Computing and Intelligent Information Processing Wuyishan China College of Computer and Data Science Fuzhou University Fuzhou China European University Cyprus Department of Computer Science and Engineering Nicosia Cyprus

ISBN: (纸本)9798350337181

We address the problem of learning new classes for semantic segmentation models from few examples, which is challenging because of the following two reasons. Firstly, it is difficult to learn from limited novel data to capture the underlying class distribution. Secondly, it is challenging to retain knowledge for existing classes and to avoid catastrophic forgetting. For learning from limited data, we propose a pseudo-labeling strategy to augment the few-shot training annotations in order to learn novel classes more effectively. Given only one or a few images labeled with the novel classes and a much larger set of unlabeled images, we transfer the knowledge from labeled images to unlabeled images with a coarse-to-fine pseudo-labeling approach in two steps. Specifically, we first match each labeled image to its nearest neighbors in the unlabeled image set at the scene level, in order to obtain images with a similar scene layout. This is followed by obtaining pseudo-labels within this neighborhood by applying classifiers learned on the few-shot annotations. In addition, we use knowledge distillation on both labeled and unlabeled data to retain knowledge on existing classes. We integrate the above steps into a single convolutional neural network with a unified learning objective. Extensive experiments on the Cityscapes and KITTI datasets validate the efficacy of the proposed approach in the self-driving domain. Code is available from https://***/ChasonJiang/FSCILSS. © 2023 IEEE.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

A Novel Under-sampling Method with Gaussian Mixture and Jensen-Shannon Divergence 2022

A Novel Under-sampling Method with Gaussian Mixture and Jens...

引用

4th International Conference on Image, Video and Signal Processing, IVSP 2022

作者： Pan, Xueling Li, Guohe Liu, Shunxin Yu, Qiuyue Li, Ying Beijing Key Lab of Data Mining for Petroleum Data China University of Petroleum Beijing102249 China College of Information Science and Engineering China University of Petroleum Beijing102249 China Department of Computer Science and Technology China University of Petroleum-Beijing at Keramay China

ISBN: (纸本)9781450387415

Due to bias towards major class samples, the traditional classifier cannot obtain excellent performance in imbalanced data. The under-sampling approach is one of the effective methods in imbalance classification. Nowadays, most of the under-sampling methods do not consider the global and local distribution of samples and the intra-class imbalance problem simultaneously. In addition, the sampling quantity cannot be adjusted adaptively in the practical application. To handle the above problems, in this paper, we propose a novel under-sampling approach with the Gaussian mixture model and Jensen-Shannon divergence, called GD-US. Firstly, it utilizes a Gaussian mixture model to cluster the majority class samples. And then, it calculates the number of sampling in each cluster according to its sparsity. In addition, GD-US adopts the global and local distribution of samples to decide the probability of deleting samples. Eventually, the Jensen-Shannon divergence is used to control the number of sampling. The experimental results show that the proposal can help solve the imbalance problem and enhance the classification accuracy. © 2022 ACM.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

Adaptive Fourier Decomposition of the First Three SARS-CoV-2 Infection Waves with Epidemic Intervention—London,UK,2020-2022

引用

China CDC weekly 2024年第21期6卷 478-486,I0006-I0008页

作者： Zige Liu Guibin Lu Cheokieng Vong Zhiqi Zeng Wei He Zhijie Lin Cuiyun Lin Kaichin Hsieh Zifeng Yang Arlindo L.Oliveira Chitin Hon Department of Engineering Science Faculty of Innovation EngineeringMacao University of Science and TechnologyMacao SARChina Queen Ethelburga’s Collegiate Thorpe Underwood EstateYorkUK State Key Laboratory of Respiratory Disease National Clinical Research Center for Respiratory DiseaseGuangzhou Institute of Respiratory HealthThe First Affiliated Hospital of Guangzhou Medical UniversityGuangzhou CityGuangdong ProvinceChina Respiratory Disease AI Laboratory on Epidemic and Medical Big Data Instrument Applications Department of Engineering ScienceFaculty of Innovation EngineeringMacao University of Science and TechnologyMacao SARChina Guangzhou Key Laboratory for Clinical Rapid Diagnosis and Early Warning of Infectious Diseases KingMed School of Laboratory MedicineGuangzhou Medical UniversityGuangzhou CityGuangdong ProvinceChina Faculty of Innovation Engineering School of Computer Science and EngineeringMacao University of Science and TechnologyMacao SARChina University College London UCL Faculty of Engineering SciencesLondonUK Guangzhou Laboratory Guangzhou CityGuangdong ProvinceChina Instituto de Engenharia de Sistemas e Computadores:Investigação e Desenvolvimento em Lisboa LisboaPortugal Instituto Superior Técnico Universidade de LisboaLisboaPortugal

Background:This study provides a detailed analysis of the daily fluctuations in coronavirus disease 2019(COVID-19)case numbers in London from January 31,2020 to February 24,*** primary objective was to enhance understanding of the interactions among government pandemic responses,viral mutations,and the subsequent changes in COVID-19 case ***:We employed the adaptive Fourier decomposition(AFD)method to analyze diurnal changes and further segmented the AFD into novel multi-component groups consisting of one to three *** restructured components were rigorously evaluated using Pearson correlation,and their effectiveness was compared with other signal analysis *** study introduced a novel approach to differentiate individual components across various time-frequency scales using basis decomposition ***:Analysis of London’s daily COVID-19 data using AFD revealed a strong correlation between the“stay at home”directive and high-frequency components during the first epidemic *** indicates the need for sustained implementation of vaccination policies to maintain their ***:The AFD component method provides a comprehensive analysis of the immediate and prolonged impact of governmental policies on the spread of severe acute respiratory syndrome coronavirus 2(SARS-CoV-2).This robust tool has proven invaluable for analyzing COVID-19 pandemic data,offering critical insights that guide the formulation of future preventive and public health strategies.

关键词： offering sustained London

来源：评论

学校读者我要写书评

暂无评论

Gap minimization for knowledge sharing and transfer

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2023年第1期24卷 1282-1338页

作者： Boyu Wang Jorge A. Mendez Changjian Shui Fan Zhou Di Wu Gezheng Xu Christian Gagné Eric Eaton Department of Computer Science University of Western Ontario Computer Science & Artificial Intelligence Laboratory Massachusetts Institute of Technology Institute Intelligence and Data Université Laval School of Transportation Science and Engineering Beihang University Department of Electrical and Computer Engineering McGill University Department of Computer and Information Science University of Pennsylvania

Learning from multiple related tasks by knowledge sharing and transfer has become increasingly relevant over the last two decades. In order to successfully transfer information from one task to another, it is critical to understand the similarities and differences between the domains. In this paper, we introduce the notion of performance gap, an intuitive and novel measure of the distance between learning tasks. Unlike existing measures which are used as tools to bound the difference of expected risks between tasks (e.g., H-divergence or discrepancy distance), we theoretically show that the performance gap can be viewed as a data- and algorithm-dependent regularizer, which controls the model complexity and leads to finer guarantees. More importantly, it also provides new insights and motivates a novel principle for designing strategies for knowledge sharing and transfer: gap minimization. We instantiate this principle with two algorithms: 1. gapBoost, a novel and principled boosting algorithm that explicitly minimizes the performance gap between source and target domains for transfer learning; and 2. gapMTNN, a representation learning algorithm that reformulates gap minimization as semantic conditional matching for multitask learning. Our extensive evaluation on both transfer learning and multitask learning benchmark data sets shows that our methods outperform existing baselines.

关键词： performance gap transfer learning multitask learning regularization algorithmic stability

来源：评论

学校读者我要写书评

暂无评论

Using Lock-Free Design for Throughput-Optimized Cache Eviction

引用

Proceedings of the ACM on Measurement and Analysis of Computing Systems 2025年第2期9卷 1-28页

作者： Dong, Chao Wang, Fang Jiang, Hong Feng, Dan Huazhong University of Science and Technology Key Laboratory of Information Storage System Wuhan National Laboratory for Optoelectronics Engineering Research Center of data storage systems and Technology School of Computer Science and Technology Ministry of Education of China Hubei Wuhan China University of Texas at Arlington Department of Computer Science and Engineering ArlingtonTX United States

In large-scale information systems, storage device performance continues to improve while workloads expand in size and access characteristics. This growth puts tremendous pressure on caches and storage hierarchy in terms of concurrent throughput. However, existing cache eviction policies often struggle to provide adequate concurrent throughput due to their reliance on coarse-grained locking mechanisms and complex data structures. This paper presents a practical approach to cache eviction algorithm design, called Mobius, that optimizes the concurrent throughput of caches and reduces cache operation latency by utilizing lock-free data structures, while maintaining comparable hit ratios. Mobius includes two key designs. First, Mobius employs two lock-free FIFO queues to manage cache items, ensuring that all cache operations are executed efficiently in parallel. Second, Mobius integrates a consecutive detection mechanism that merges multiple modifications during eviction into a single operation, thereby reducing data races. Extensive evaluations using both synthetic and real-world workloads from high-concurrency clusters demonstrate that Mobius achieves a concurrent-throughput improvement ranging from 1.2× to 8.5× over state-of-the-art methods, while also maintaining lower latency and comparable cache hit ratios. The implementation of Mobius in CacheLib and RocksDB highlights its effectiveness in enhancing cache performance in practical scenarios. © 2025 ACM.

关键词： Keyways

来源：评论

学校读者我要写书评

暂无评论

Large Language Models as Evolutionary Optimizers 13

Large Language Models as Evolutionary Optimizers

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Liu, Shengcai Chen, Caishun Qu, Xinghua Tang, Ke Ong, Yew-Soon Southern University of Science and Technology Centre for Frontier Ai Research A∗star Department of Computer Science and Engineering China Centre for Frontier Ai Research A∗star Singapore Tianqiao & Chrissy Chen Institute China Southern University of Science and Technology Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering China Nanyang Technological University Centre for Frontier Ai Research A∗star College of Computing and Data Science Singapore

ISBN: (纸本)9798350308365

Evolutionary algorithms (EAs) have achieved remarkable success in tackling complex combinatorial optimization problems. However, EAs often demand carefully-designed operators with the aid of domain expertise to achieve satisfactory performance. In this work, we present the first study on large language models (LLMs) as evolutionary combinatorial optimizers. The main advantage is that it requires minimal domain knowledge and human efforts, as well as no additional training of the model. This approach is referred to as LLM-driven EA (LMEA). Specifically, in each generation of the evolutionary search, LMEA instructs the LLM to select parent solutions from current population, and perform crossover and mutation to generate offspring solutions. Then, LMEA evaluates these new solutions and include them into the population for the next generation. LMEA is equipped with a self-adaptation mechanism that controls the temperature of the LLM. This enables it to balance between exploration and exploitation and prevents the search from getting stuck in local optima. We investigate the power of LMEA on the classical traveling salesman problems (TSPs) widely used in combinatorial optimization research. Notably, the results show that LMEA performs competitively to traditional heuristics in finding high-quality solutions on TSP instances with up to 20 nodes. Additionally, we also study the effectiveness of LLM-driven crossover/mutation and the self- adaptation mechanism in evolutionary search. In summary, our results reveal the great potentials of LLMs as evolutionary optimizers for solving combinatorial problems. We hope our research shall inspire future explorations on LLM-driven EAs for complex optimization challenges. © 2024 IEEE.

关键词： Traveling salesman problem

来源：评论

学校读者我要写书评

暂无评论

Cyclic Refiner: Object-Aware Temporal Representation Learning for Multi-View 3D Detection and Tracking

arXiv

引用

arXiv 2024年

作者： Guo, Mingzhe Zhang, Zhipeng Jing, Liping He, Yuan Wang, Ke Fan, Heng Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University China KargoBot China Department of Computer Science and Engineering University of North Texas United States

We propose a unified object-aware temporal learning framework for multi-view 3D detection and tracking tasks. Having observed that the efficacy of the temporal fusion strategy in recent multi-view perception methods may be weakened by distractors and background clutters in historical frames, we propose a cyclic learning mechanism to improve the robustness of multi-view representation learning. The essence is constructing a backward bridge to propagate information from model predictions (e.g., object locations and sizes) to image and BEV features, which forms a circle with regular inference. After backward refinement, the responses of target-irrelevant regions in historical frames would be suppressed, decreasing the risk of polluting future frames and improving the object awareness ability of temporal fusion. We further tailor an object-aware association strategy for tracking based on the cyclic learning model. The cyclic learning model not only provides refined features, but also delivers finer clues (e.g., scale level) for tracklet association. The proposed cycle learning method and association module together contribute a novel and unified multi-task framework. Experiments on nuScenes show that the proposed model achieves consistent performance gains over baselines of different designs (i.e., dense query-based BEVFormer, sparse query-based SparseBEV and LSS-based BEVDet4D) on both detection and tracking evaluation. © 2024, CC BY.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Empirical Analysis of Nature-Inspired Algorithms for Autism Spectrum Disorder Detection Using 3D Video dataset

arXiv

引用

arXiv 2025年

作者： Panchal, Aneesh Khan, Kainat Katarya, Rahul Department of Computational and Data Sciences Indian Institute of Science Karnataka Bangalore560012 India Big Data Analytics and Web Intelligence Laboratory Department of Computer Science & Engineering Delhi Technological University Delhi110042 India

Autism Spectrum Disorder (ASD) is a chronic neurodevelopmental disorder symptoms of which includes repetitive behaviour and lack of social and communication skills. Even though these symptoms can be seen very clearly in social but a large number of individuals with ASD remains undiagnosed. In this paper, we worked on a methodology for detection of ASD from 3-dimensional walking video dataset, utilizing supervised machine learning (ML) classification algorithms and using nature-inspired optimization algorithms for feature extraction from dataset. The proposed methodology involve the classification of ASD using supervised ML classification algorithm and extracting important and relevant features from the dataset using nature-inspired optimization algorithms. We also included the ranking coefficients for finding the initial leading particle. This selection of particle significantly reduces the computation time and hence, improving the total efficiency and accuracy for the ASD detection. To evaluate the efficiency of the proposed methodology, we deployed various combination of classification algorithm and nature-inspired algorithms resulting in an outstanding classification accuracy of 100% using random forest classification algorithm and gravitational search algorithm for feature selection. The application of the proposed methodology with different datasets would enhance the robustness and generalizability of the proposed methodology. Due to high accuracy and less total computation time, the proposed methodology will offer a significant contribution to the medical and academia fields, providing a foundation for future research and advancements in ASD diagnosis. Copyright © 2025, The Authors. All rights reserved.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：