检索结果-内蒙古大学图书馆

Ensemble Kalman Filtering Meets Gaussian Process SSM for Non-Mean-Field and Online inference

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2024年 72卷 4286-4301页

作者： Lin, Zhidi Sun, Yiyong Yin, Feng Thiery, Alexandre Hoang Chinese Univ Hong Kong Sch Sci & Engn Future Network Intelligence Inst Shenzhen 518172 Peoples R China Shenzhen Res Inst Big Data Shenzhen 518172 Peoples R China Natl Univ Singapore Dept Stat & Data Sci Singapore 117546 Singapore Chinese Univ Hong Kong Sch Sci & Engn Shenzhen Peoples R China

The Gaussian process state-space models (GPSSMs) represent a versatile class of data-driven nonlinear dynamical system models. However, the presence of numerous latent variables in GPSSM incurs unresolved issues for existing variational inference approaches, particularly under the more realistic non-mean-field (NMF) assumption, including extensive training effort, compromised inference accuracy, and infeasibility for online applications, among others. In this paper, we tackle these challenges by incorporating the ensemble Kalman filter (EnKF), a well-established model-based filtering technique, into the NMF variational inference framework to approximate the posterior distribution of the latent states. This novel marriage between EnKF and GPSSM not only eliminates the need for extensive parameterization in learning variational distributions, but also enables an interpretable, closed-form approximation of the evidence lower bound (ELBO). Moreover, owing to the streamlined parameterization via the EnKF, the new GPSSM model can be easily accommodated in online learning applications. We demonstrate that the resulting EnKF-aided online algorithm embodies a principled objective function by ensuring data-fitting accuracy while incorporating model regularizations to mitigate overfitting. We also provide detailed analysis and fresh insights for the proposed algorithms. Comprehensive evaluation across diverse real and synthetic datasets corroborates the superior learning and inference performance of our EnKF-aided variational inference algorithms compared to existing methods.

关键词： Heuristic algorithms Signal processing algorithms inference algorithms Gaussian processes Computational modeling Kalman filters Approximation algorithms Gaussian process state-space model ensemble Kalman filter online learning variational inference

来源：评论

学校读者我要写书评

暂无评论

MoEI: Mobility-Aware Edge inference Based on Model Partition and Service Migration

引用

IEEE TRANSACTIONS ON MOBILE COMPUTING 2024年第10期23卷 9437-9450页

作者： Liu, Zhicheng Tian, Meng Dong, Mianxiong Wang, Xiaofei Qiu, Chao Zhang, Cheng Tianjin Univ Coll Intelligence & Comp Tianjin Key Lab Adv Networking Tianjin 300350 Peoples R China Muroran Inst Technol Dept Sci & Informat Muroran Hokkaido 0508585 Japan Tianjin Univ Finance & Econ Inst Technol Tianjin 300222 Peoples R China

Deep neural networks are the cornerstone of many mobile intelligent systems, and their inference processes bring about computation-intensive tasks. Device-edge cooperative inference in mobile edge computing provides a fine-grained processing method to migrate the burden of inference computation. However, the geographical dispersion of resources and the mobility pattern of devices pose scheduling issues to be considered. In this paper, we propose a task scheduling framework for such device-edge systems to improve the pipeline time of model inference. First, we consider the resource provisioning strategy with a pre-fetching service migration setting in the environment of multiple mobile devices and edge nodes. Then, we leverage game theory to analyze the property of the decision-making process and propose an offline algorithm under complete information. Next, we propose an algorithm based on proximal policy optimization to enable mobile devices to make decisions in a distributed online manner. Further, we adopt a memory mechanism into the online algorithm to improve the decision-makers' understanding of the system environment. Experiments demonstrate the effectiveness of the two algorithms. The average pipeline time of the proposed online algorithm is only 61.44% of that of local processing, which is 1.196 times that of the proposed offline algorithm.

关键词： Mobile handsets Task analysis Computational modeling inference algorithms Pipelines Partitioning algorithms Multi-access edge computing Collaborative inference deep reinforcement learning mobile edge computing model partition service migration

来源：评论

学校读者我要写书评

暂无评论

Mobility and Cost Aware inference Accelerating Algorithm for Edge Intelligence

引用

IEEE TRANSACTIONS ON MOBILE COMPUTING 2025年第3期24卷 1530-1549页

作者： Yuan, Xin Li, Ning Wei, Kang Xu, Wenchao Chen, Quan Chen, Hao Guo, Song Harbin Inst Technol Sch Ocean Engn Harbin 150001 Peoples R China Harbin Inst Technol Sch Comp Sci & Technol Harbin 150001 Peoples R China TheHong Kong Polytech Univ Dept Comp Hong Kong 999077 Peoples R China Guangdong Univ Technol Sch Comp Sci & Technol Guangzhou 510006 Peoples R China Hong Kong Univ Sci & Technol Dept Comp Sci & Engn Hong Kong Peoples R China

The edge intelligence (EI) has been widely applied recently. Splitting the model between device, edge server, and cloud can significantly improve the performance of EI. The model segmentation without user mobility has been investigated in detail in previous studies. However, in most EI use cases, the end devices are mobile. Few studies have been conducted on this topic. These works still have many issues, such as ignoring the energy consumption of mobile device, inappropriate network assumption, and low effectiveness on adapting user mobility, etc. Therefore, to address the disadvantages of model segmentation and resource allocation in previous studies, we propose mobility and cost aware model segmentation and resource allocation algorithm for accelerating the inference at edge (MCSA). Specifically, in the scenario without user mobility, the loop iteration gradient descent (Li-GD) algorithm is provided. When the mobile user has a large model inference task that needs to be calculated, it will take the energy consumption of mobile user, the communication and computing resource renting cost, and the inference delay into account to find the optimal model segmentation and resource allocation strategy. In the scenario with user mobility, the mobility aware Li-GD (MLi-GD) algorithm is proposed to calculate the optimal strategy. Then, the properties of the proposed algorithms are investigated, including convergence, complexity, and approximation ratio. The experimental results demonstrate the effectiveness of the proposed algorithms.

关键词： Servers Computational modeling inference algorithms Resource management Delays Costs Energy consumption Complexity theory Partitioning algorithms Mobile handsets Edge intelligence model segmentation inference accelerating mobility

来源：评论

学校读者我要写书评

暂无评论

Stable Knowledge Tracing Using Causal inference

引用

IEEE TRANSACTIONS ON LEARNING TECHNOLOGIES 2024年 17卷 124-134页

作者： Zhu, Jia Ma, Xiaodong Huang, Changqin Zhejiang Normal Univ Key Lab Intelligent Educ Technol & Applicat Zhejia Jinhua 321004 Peoples R China

Knowledge tracing (KT) for evaluating students' knowledge is an essential task in personalized education. More and more researchers have devoted themselves to solving KT tasks, e.g., deep knowledge tracing (DKT), which can capture more sophisticated representations of student knowledge. Nonetheless, these techniques ignore the reconstruction of the observed input information. Therefore, this leads to poor predictions of students' knowledge, even if the student performed well in the past knowledge state. In this article, we first employ causal inference for explanatory analysis of KT, then propose a learning algorithm for stable KT based on the analysis outcomes. The proposed approach aims to achieve stable KT by constructing global balanced weights that facilitate estimating feature influence and assessing causal relationships between individual variables and outcome variables. We have proved the approach has effective in accuracy and interpretability through extensive experimentation on real-world datasets. In conclusion, this article has methodological implications for the stable assessment of students' knowledge and provides a reference for personalization and use of intelligence in the educational teaching process.

关键词： Analytical models Education Predictive models Prediction algorithms inference algorithms Stability analysis Robustness Causal inference deep knowledge tracing (DKT) learning sciences stable knowledge tracing (KT)

来源：评论

学校读者我要写书评

暂无评论

CANET: Quantized Neural Network inference With 8-bit Carry-Aware Accumulator

引用

IEEE ACCESS 2024年 12卷 38765-38772页

作者： Yang, Jingxuan Wang, Xiaoqin Jiang, Yiying Inst Microelect Chinese Acad Sci Chaoyang Beijing 100029 Peoples R China Univ Chinese Acad Sci Sch Integrated Circuits Huairou Beijing 101408 Peoples R China

Neural network quantization represents weights and activations with few bits, greatly reducing the overhead of multiplications. However, due to the recursive accumulation operations, high-precision accumulators are still required in multiply-accumulate (MAC) units to avoid overflow, incurring significant computational overhead. This constraint limits the efficient deployment of quantized NNs on resource-constrained platforms. To address this problem, we present a novel framework named CANET, which adapts the 8-bit quantized model to execute MAC operations with 8-bit accumulators. CANET not only employs 8-bit carry-aware accumulators to represent overflow data correctly, but also adaptively learns the optimal format per layer to minimize truncation errors. Meanwhile, a weight-oriented reordering method is developed to reduce the transfer length of the carry. CANET is evaluated on three networks in the ImageNet classification task, where comparable performance with state-of-the-art methods is realized. Finally, we implement the proposed architecture on a custom hardware platform, demonstrating a reduction of 40% in power and 49% in area compared with the MAC unit with 32-bit accumulators.

关键词： Quantization (signal) Arithmetic Hardware Finite wordlength effects inference algorithms Costs Training Convolutional neural networks quantization efficient inference low-precision accumulator

来源：评论

学校读者我要写书评

暂无评论

QoS-Aware inference Acceleration Using Adaptive Depth Neural Networks

引用

IEEE ACCESS 2024年 12卷 49329-49340页

作者： Kang, Woochul Incheon Natl Univ Dept Embedded Syst Engn Incheon 22012 South Korea

While deep neural networks (DNNs) have brought revolutions to many intelligent services and systems, the deployment of high-performing models for real-world applications faces challenges posed by resource constraints and diverse operating environments. While existing methods such as model compression combined with inference accelerators have enhanced the efficiency of deep neural networks, they are not dynamically adaptable to dynamically changing resource conditions since they provide static accuracy-efficiency trade-offs. Further, since they are not aware of performance requirements, such as desired inference latency, they are not able to provide robust and effective performance under unpredictable workloads. This paper introduces a holistic solution to address this challenge, consisting of two key components: adaptive depth neural networks and the Quality of Service (QoS)-aware inference accelerator. The adaptive depth neural networks exhibit the ability to scale computation instantly with minimal impact on accuracy, utilizing a novel architectural pattern and training algorithm. Complementing this, the QoS-aware inference accelerator employs a feedback control loop, adapting network depth dynamically to meet desired inference latency. Experimental results demonstrate that the proposed adaptive depth networks outperform non-adaptive counterparts, achieving up to 38% dynamic acceleration via depth adaption, with a marginal accuracy loss of 1.5%. Furthermore, the QoS-aware inference accelerator successfully controls network depth at runtime, ensuring robust performance in unpredictable environments.

关键词： Adaptive systems Quality of service Task analysis Deep learning Adaptation models Training inference algorithms Artificial neural networks Feedback control Real-time systems Energy efficiency inference acceleration deep neural networks feedback control real-time energy efficiency quality-of-service QoS

来源：评论

学校读者我要写书评

暂无评论

Taming Serverless Cold Start of Cloud Model inference With Edge Computing

引用

IEEE TRANSACTIONS ON MOBILE COMPUTING 2024年第8期23卷 8111-8128页

作者： Zhao, Kongyange Zhou, Zhi Jiao, Lei Cai, Shen Xu, Fei Chen, Xu Sun Yat Sen Univ SYSU Sch Comp Sci & Engn Guangzhou 510006 Peoples R China Univ Oregon Dept Comp & Informat Sci Eugene OR 97403 USA East China Normal Univ Shanghai Key Lab Multidimens Informat Proc Sch Comp Sci & Technol Shanghai 200062 Peoples R China

Serverless computing is envisioned as the de-facto standard for next-generation cloud computing. However, the cold start dilemma has impeded its adoption by delay-sensitive and burst applications. In this paper, we propose to tame serverless cold start in a cloud inference system with edge computing. Specifically, the proposed solution smooths the serverless cloud workload with user-owned edge computing, reducing the number of cold starts. Leveraging the configurability of requests and serverless functions, the proposed solution further reduces the transmission latency and serverless cost by adapting request configuration (e.g., image resolution) and function configuration (e.g., memory). To alleviate the potential inference accuracy degradation incurred by configuration adaption, we aim to strike a nice balance between inference latency, cost, and accuracy. However, achieving this goal is non-trivial since the underlying optimization is non-convex and involves future uncertain information. To simultaneously address dual challenges, the presented cold-start-aware online algorithms apply the regularization technique to decompose the problem into separate convex subproblems. Then, it applies lazy switching to smooth the number of provisioned functions and thus reduces the cold start. Through rigorous theoretical analysis, realistic prototype evaluations on AWS Lambda, and trace-driven simulations, we comprehensively validate the theoretical and empirical performance of our proposed solution.

关键词： Computational modeling Edge computing Serverless computing inference algorithms Optimization Costs Adaptation models cold start model inference edge computing online optimization

来源：评论

学校读者我要写书评

暂无评论

SecBNN: Efficient Secure inference on Binary Neural Networks

引用

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2024年 19卷 10273-10286页

作者： Chen, Hanxiao Li, Hongwei Hao, Meng Hu, Jia Xu, Guowen Zhang, Xilin Zhang, Tianwei Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 610056 Peoples R China Nanyang Technol Univ Coll Comp & Data Sci Singapore 639798 Singapore

This work studies secure inference on Binary Neural Networks (BNNs), which have binary weights and activations as a desirable feature. Although previous works have developed secure methodologies for BNNs, they still have performance limitations and significant gaps in efficiency when applied in practice. We present SecBNN, an efficient secure two-party inference framework on BNNs. SecBNN exploits appropriate underlying primitives and contributes efficient protocols for the non-linear and linear layers of BNNs. Specifically, for non-linear layers, we introduce a secure sign protocol with an innovative adder logic and customized evaluation algorithms. For linear layers, we propose a new binary matrix multiplication protocol, where a divide-and-conquer strategy is provided to recursively break down the matrix multiplication problem into multiple sub-problems. Building on top of these efficient ingredients, we implement and evaluate SecBNN over two real-world datasets and various model architectures under LAN and WAN. Experimental results show that SecBNN substantially improves the communication and computation performance of existing secure BNN inference works by up to 29 x and 14 x, respectively.

关键词： Wide area networks Protocols Accuracy Quantization (signal) Neural networks Buildings Computer architecture inference algorithms Logic Adders Binary neural networks private inference secure two-party computation

来源：评论

学校读者我要写书评

暂无评论

Scene inference Using Saliency Graphs With Trust-Theoretic Semantic Information Encoding

引用

IEEE SIGNAL PROCESSING LETTERS 2025年 32卷 256-260页

作者： Meena, Preeti Kumar, Himanshu Yadav, Sandeep Indian Inst Technol Jodhpur Discipline Elect Engn Jodhpur 342030 India

Scene inference refers to the identification of the scene from a given set of scene representations such as images. A saliency graph of a scene contains scene-defining objects along with semantic information between them in the graph representation. Existing methods consider the entire scene with uniform weighting to all semantic information for scene inference, resulting in a suboptimal performance. This letter presents an optimal edge weight estimation using the trust theoretic framework to encode semantic information effectively in saliency graphs. We have utilized the notion of converged global absolute trust in saliency scores of salient objects to compute the weighting of semantic information. Experimental results highlight the efficacy of the proposed method.

关键词： Peer-to-peer computing Semantics Estimation Symmetric matrices Image edge detection Signal processing algorithms inference algorithms Eigenvalues and eigenfunctions Visualization Accuracy Scene inference saliency graph semantic information trust graph P2P

来源：评论

学校读者我要写书评

暂无评论

Joint Network Topology inference in the Presence of Hidden Nodes

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2024年 72卷 2710-2725页

作者： Navarro, Madeline Rey, Samuel Buciulea, Andrei Marques, Antonio G. Segarra, Santiago Rice Univ Dept ECE Houston TX 77005 USA King Juan Carlos Univ Dept Signal Theory & Commun Madrid 28933 Spain

We investigate the increasingly prominent task of jointly inferring multiple networks from nodal observations. While most joint inference methods assume that observations are available at all nodes, we consider the realistic and more difficult scenario where a subset of nodes are hidden and cannot be measured. Under the assumptions that the partially observed nodal signals are graph stationary and the networks have similar connectivity patterns, we derive structural characteristics of the connectivity between hidden and observed nodes. This allows us to formulate an optimization problem for estimating networks while accounting for the influence of hidden nodes. We identify conditions under which a convex relaxation yields the sparsest solution, and we formalize the performance of our proposed optimization problem with respect to the effect of the hidden nodes. Finally, synthetic and real-world simulations provide evaluations of our method in comparison with other baselines.

关键词： Network topology Topology Task analysis Signal processing Signal processing algorithms inference algorithms Symmetric matrices Graph learning network topology inference hidden nodes graph signal processing graph stationarity multi-layer graphs

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：