检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Ye, Fei Bors, Adrian G. Zhang, Kun School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China Department of Computer Science University of York York YO10 5GH United Kingdom MBZUAI Abu Dhabi United Arab Emirates Carnegie Mellon University Pittsburgh PA United States

ISBN: (纸本)157735897X

Lately, deep generative models have achieved excellent results after learning pre-defined and static data distribution. Meanwhile, their performance on continual learning suffers from degeneration, caused by catastrophic forgetting. In this paper, we study the unsupervised generative modelling in a more realistic continual learning scenario, where class and task information are absent during both training and inference learning phases. To implement this goal, the proposed memory approach consists of a temporary memory system, which stores data examples while a dynamic expansion memory system would gradually preserve those samples that are crucial for long-term memorization. A novel memory expansion mechanism is then proposed, by employing optimal transport distances between the statistics of memorized samples and each newly seen datum. This paper proposes the Sinkhorn-based Dual Dynamic Memory (SDDM) method, by considering Sinkhorn distance as an optimal transport measure, for evaluating the significance of the data to be stored in the memory buffer. The Sinkhorn transport algorithm leads to preserving a diversity of samples within a compact memory capacity. The memory buffering approach does not interact with the model’s training process and can be optimized independently in both supervised and unsupervised learning without any modifications. Moreover, we also propose a novel dynamic model expansion mechanism to automatically increase the model’s capacity whenever necessary, which can deal with infinite data streams and further improve the model’s performance. Experimental results show that the proposed approach achieves state-of-the-art performance in both supervised and unsupervised learning. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Asynchronous Fractional Multi-Agent Deep Reinforcement Learning for Age-Minimal Mobile Edge Computing

arXiv

引用

arXiv 2024年

作者： Jin, Lyudong Tang, Ming Pan, Jiayu Zhang, Meng Wang, Hao Zhejiang University University of Illinois at Urbana–Champaign Institute Zhejiang University Haining314400 China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518000 China School of Software Technology Zhejiang University Ningbo315048 China Department of Data Science and AI Faculty of Information Technology Monash University MelbourneVIC3800 Australia

In the realm of emerging real-time networked applications such as industrial cyber-physical systems (CPS), the Age of Information (AoI) has emerged as a pivotal metric for evaluating the timeliness. To meet the high computational demands, such as those in smart manufacturing within CPS, mobile edge computing (MEC) presents a promising solution for optimizing computing and reducing AoI. In this work, we study the timeliness of computational-intensive updates and explore jointly optimizing the task updating (when to generate a task) and offloading (where to process a task) policies to minimize AoI. Specifically, we consider edge load dynamics and formulate a task scheduling problem to minimize the expected time-average AoI. Solving this problem is challenging due to the fractional objective introduced by AoI and asynchronous decision-making of the semi-Markov game (SMG). To this end, we propose a fractional reinforcement learning (RL) framework. We first introduce a fractional single-agent RL framework and further propose a fractional multi-agent RL framework, including convergence analysis for both scenarios. To tackle the challenge of asynchronous decision-making in SMG, we further design an asynchronous model-free fractional multi-agent RL algorithm, where each mobile device can determine the task updating and offloading decisions without knowing the real-time system dynamics and decisions of other devices. Experimental results show that when compared with the best baseline algorithm, our proposed algorithms reduce the average AoI by up to 52.6%. Copyright © 2024, The Authors. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

DeepLV: Suggesting Log Levels Using Ordinal Based Neural Networks

DeepLV: Suggesting Log Levels Using Ordinal Based Neural Net...

引用

International Conference on software engineering (ICSE)

作者： Zhenhao Li Heng Li Tse-Hsun Chen Weiyi Shang Department of Computer Science and Software Engineering Concordia University Montreal Canada Department of Computer Engineering and Software Engineering Polytechnique Montréal Montreal Canada Concordia University Canada

Developers write logging statements to generate logs that provide valuable runtime information for debugging and maintenance of software systems. Log level is an important component of a logging statement, which enables developers to control the information to be generated at system runtime. However, due to the complexity of software systems and their runtime behaviors, deciding a proper log level for a logging statement is a challenging task. For example, choosing a higher level (e.g., error) for a trivial event may confuse end users and increase system maintenance overhead, while choosing a lower level (e.g., trace) for a critical event may prevent the important execution information to be conveyed opportunely. In this paper, we tackle the challenge by first conducting a preliminary manual study on the characteristics of log levels. We find that the syntactic context of the logging statement and the message to be logged might be related to the decision of log levels, and log levels that are further apart in order (e.g., trace and error) tend to have more differences in their characteristics. Based on this, we then propose a deep-learning based approach that can leverage the ordinal nature of log levels to make suggestions on choosing log levels, by using the syntactic context and message features of the logging statements extracted from the source code. Through an evaluation on nine large-scale open source projects, we find that: 1) our approach outperforms the state-of-the-art baseline approaches; 2) we can further improve the performance of our approach by enlarging the training data obtained from other systems; 3) our approach also achieves promising results on cross-system suggestions that are even better than the baseline approaches on within-system suggestions. Our study highlights the potentials in suggesting log levels to help developers make informed logging decisions.

关键词： Runtime Manuals Syntactics Maintenance engineering software systems Feature extraction Task analysis

来源：评论

学校读者我要写书评

暂无评论

Analytic Correlation Penalty with Variable Window in Multi-task Learning Disease Progression Model

Analytic Correlation Penalty with Variable Window in Multi-t...

引用

International Conference on Mobile Ad-hoc and Sensor Networks, MSN

作者： Xiangchao Chang Menghui Zhou Fengtao Nan Yun Yang Po Yang School of Software Yunnan University Kunming China School of Information Science and Engineering Yunnan University Kunming China Department of Computer Science University of Sheffield Sheffield UK

Alzheimer's Disease (AD) is the most common reason of dementia that causes serious problems in patients' congnitive functions. Multi-task learning (MTL) has performed well in studies of longitudinal processes in Alzheimer's disease for revealing the progression of AD. Combined with prior knowl-edges in disease progression or medical science, regularization MTL framework could introduce empirical constraints more flexibly. Meanwhile, it brings higher cost during optimization. While it shown that most of formulations could not define the disease progression precisely. Existing regression methods with temporal smoothness method eliminated abnormal fluctuation of cognitive scores, and neglected the sophisticated progression in disease. In this article, we proposed an analytic method to define the progression of AD, and a flexible bandwidth method to encourage the points of disease time sequence temporal smoothness in an appropriate way. To solve three non-smooth penalties in our method, we proposed an optimization method combined accelerated gradient descent (AGD) and alternating direction method of multipliers (ADMM).

关键词： Analytical models Statistical analysis Optimization methods Information sharing Bandwidth Predictive models Multitasking

来源：评论

学校读者我要写书评

暂无评论

A Survey on Learnable Evolutionary Algorithms for Scalable Multiobjective Optimization

arXiv

引用

arXiv 2022年

作者： Liu, Songbai Lin, Qiuzhen Li, Jianqiang Tan, Kay Chen The College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China The Department of Computing The Hong Kong Polytechnic University Hong Kong

Recent decades have witnessed great advancements in multiobjective evolutionary algorithms (MOEAs) for multiobjective optimization problems (MOPs). However, these progressively improved MOEAs have not necessarily been equipped with scalable and learnable problem-solving strategies for new and grand challenges brought by the scaling-up MOPs with continuously increasing complexity from diverse aspects, mainly including expensive cost of function evaluations, many objectives, large-scale search space, time-varying environments, and multitask. Under different scenarios, divergent thinking is required in designing new powerful MOEAs for solving them effectively. In this context, research studies on learnable MOEAs with machine learning techniques have received extensive attention in the field of evolutionary computation. This paper begins with a general taxonomy of scaling-up MOPs and learnable MOEAs, followed by an analysis of the challenges that these MOPs pose to traditional MOEAs. Then, we synthetically overview recent advances of learnable MOEAs in solving various scaling-up MOPs, focusing primarily on four attractive directions (i.e., learnable evolutionary discriminators for environmental selection, learnable evolutionary generators for reproduction, learnable evolutionary evaluators for function evaluations, and learnable evolutionary transfer modules for sharing or reusing optimization experience). The insight of learnable MOEAs is offered to readers as a reference to the general track of the efforts in this field. Copyright © 2022, The Authors. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Microvision: Static analysis-based approach to visualizing microservices in augmented reality

arXiv

引用

arXiv 2022年

作者： Cerny, Tomas Abdelfattah, Amr S. Bushong, Vincent Maruf, Abdullah Al Taibi, Davide Department of Computer Science Baylor University WacoTX United States Software Engineering Group Tampere University TampereFI-33720 Finland

Microservices are supporting digital transformation;however, fundamental tools and system perspectives are missing to better observe, understand, and manage these systems, their properties, and their dependencies. Microservices architecture leans toward decentralization, which yields many advantages to system operation;it, however, brings challenges to their development. Microservices lack a system-centric perspective to better cope with system evolution and quality assessment. In this work, we explore microservice-specific architecture reconstruction based on static analysis. Such reconstruction typically results in system models to visualize selected system-centric perspectives. Conventional models are limited in utility when the service cardinality is high. We consider an alternative data visualization using 3D space using augmented reality. To begin testing the feasibility of deriving such perspectives from microservice systems, we developed and implemented prototype tools for software architecture reconstruction and visualization of compared perspectives. © 2022, CC BY-NC-ND.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Linking network- and neuron-level correlations by renormalized field theory

引用

Physical Review Research 2024年第3期6卷 033264页

作者： Michael Dick Alexander van Meegen Moritz Helias Institute of Neuroscience and Medicine (INM-6) and Institute for Advanced Simulation (IAS-6) and JARA-Institute Brain Structure-Function Relationships (INM-10) Department of Computer Science 3 - Software Engineering Peter Grünberg Institut (PGI-1) and Institute for Advanced Simulation (IAS-1) Institute of Zoology Department of Physics Faculty 1

It is frequently hypothesized that cortical networks operate close to a critical point. Advantages of criticality include rich dynamics well suited for computation and critical slowing down, which may offer a mechanism for dynamic memory. However, mean-field approximations, while versatile and popular, inherently neglect the fluctuations responsible for such critical dynamics. Thus, a renormalized theory is necessary. We consider the Sompolinsky-Crisanti-Sommers model which displays a well studied chaotic as well as a magnetic transition. Based on the analog of a quantum effective action, we derive self-consistency equations for the first two renormalized Greens functions. Their self-consistent solution reveals a coupling between the population level activity and single neuron heterogeneity. The quantitative theory explains the population autocorrelation function, the single-unit autocorrelation function with its multiple temporal scales, and cross correlations.

关键词： Neuronal network activity Statistical field theory Cortical networks Critical phenomena Dynamical mean field theory

来源：评论

学校读者我要写书评

暂无评论

Microservice Architecture Reconstruction and Visualization Techniques: A Review

arXiv

引用

arXiv 2022年

作者： Cerny, Tomas Abdelfattah, Amr Elsayed S. Bushong, Vincent Maruf, Abdullah Al Taibi, Davide Department of Computer Science Baylor University WacoTX United States Software Engineering Group Tampere University TampereFI-33720 Finland

Microservice system solutions are now mainstream. The older microservices-based systems are not more than 15 years old, and their architecture is by far different than the one originally designed because of several changes applied to the systems due to the implementation of new features and bug fixing. The evolution of these legacy systems is therefore subjected to degradation. One of the most important methods to identify degradation is being able to reconstruct the software architecture of a system based on the current system running in production. Different methods have been proposed in the past: methods based on the static analysis of the source code of the microservices and methods based on the analysis of the log traces collected at runtime. Both static and dynamic analysis-based methods have their pros ad cons. In this work, we review the existing technologies for static and dynamic architectural reconstruction and related tools adopted to visualize the reconstructed architecture. The result of this work can be useful both to practitioners and researchers that can further develop these methods to provide better support for architectural degradation. © 2022, CC BY-NC-ND.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

A Data Completion Algorithm Based on Low-Rank Prior Knowledge for Data-Driven Applications

引用

IEEE Transactions on Network and Service Management 2024年

作者： Tang, Jun Guo, Bing Shen, Yan Garg, Sahil Kaddoum, Georges Hossain, M. Shamim Sichuan University College of Computer Science Chengdu China Chengdu University of Information Technology School of Computer Science Chengdu China École de Technologie Supérieure Electrical Engineering Department MontréalQCH3C 1K3 Canada Chitkara University Institute of Engineering and Technology Chitkara University Centre for Research Impact and Outcome Punjab Rajpura140401 India Lebanese American University Artificial Intelligence and Cyber Systems Research Center Beirut03797751 Lebanon King Saud University College of Computer and Information Sciences Department of Software Engineering Riyadh12372 Saudi Arabia

Low rank tensor ring based data recovery algorithms have been widely used in data-driven consumer electronics to recover missing data entries in the collecting data pre-processing stage for providing stable and reliable service. However, traditional recovery methods often fail to utilize the abundant prior knowledge of data and the non-local self-similarity of the data, thus leading to the failure to effectively capture the spatial relationships within high-dimensional data to recover them accurately. To address these problems, we present a novel Non-local Self-similarity and Low-rank Prior Knowledge based tensor ring completion method. Firstly, we incorporate the BM3D denoising operator within a Plug-and-Play framework to exploit the self-similarity in the data. Then a logarithmic determinant function is integrated to distinguish singular values in the cyclic unfolding matrix of the tensor and adopts a tensor ring completion approach based on weighted nuclear norms. Finally, in order to evaluate the effectiveness of our proposed method, we conducted a series of experiments by using the missing image dataset and the missing traffic data dataset respectively, and the experimental results show that our method achieves the highest level in terms of data recovery accuracy. © 2024 IEEE.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Dynamic Expansion Diffusion Learning for Lifelong Generative Modelling 39

Dynamic Expansion Diffusion Learning for Lifelong Generative...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

ISBN: (纸本)157735897X

The diffusion model has lately been shown to achieve remarkable performances through its ability of generating high quality images. However, current diffusion model studies consider only learning from a single data distribution, resulting in catastrophic forgetting when attempting to learn new data. In this paper, we explore a more realistic learning scenario where training data is continuously acquired. We propose the Dynamic Expansion Diffusion Model (DEDM) for addressing catastrophic forgetting and data distribution shifts under Online Task-Free Continual Learning (OTFCL) paradigm. New diffusion components are added to a mixture model following the evaluation of a criterion which compares the probabilistic representation of the new data with the existing knowledge of the DEDM model. In addition, to maintain an optimal architecture, we propose a component discovery approach that ensures the diversity of knowledge while minimizing the total number of parameters in the DEDM. Furthermore, we show how the proposed DEDM can be implemented as a teacher module in a unified framework for representation learning. In this approach, knowledge distillation is proposed for training a student module aiming to compress the teacher’s knowledge into the latent space of the student. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

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：