检索结果-内蒙古大学图书馆

The Journal of Machine Learning Research 2022年第1期23卷 13101-13161页

作者： Laura Forastiere Fabrizia Mealli Albert Wu Edoardo M. Airoldi Yale Institute for Network Science Yale University New Haven CT Department of Statistics Computer Science Applications University of Florence Florence Italy Department of Statistics Harvard University Cambridge MA Department of Statistics Operations and Data Science Fox School of Business Data Science Institute Temple University Philadelphia PA

Real-world systems are often comprised of interconnected units, and can be represented as networks, with nodes and edges. In a social system, for instance, individuals may have social ties and financial relationships. In these settings, when a node (the unit analysis) is exposed to a treatment, its effects may spill over to connected units; then estimating both the direct effect of the treatment and its spillover effects presents several challenges. First, assumptions about the mechanism through which spillover effects occur along the observed network are required. Second, in observational studies, where the treatment assignment has not been randomized, confounding and homophily are further potential threats to the identification and to the estimation of causal effects, on networks. Here, we make two structural assumptions: (i) neighborhood interference, which assumes interference operates only through a function of the immediate neighbors' treatments, and (ii) unconfoundedness of the individual and neighborhood treatment, which rules out the presence of unmeasured confounding variables, including those driving homophily. Under these assumptions we develop a new covariate-adjustment estimator for direct treatment and spillover effects in observational studies on networks. We proposed an estimation strategy based on a generalized propensity score that balances individual and neighborhood covariates across units under different levels of individual treatment and of exposure to neighbors' treatment. Adjustment for propensity score is performed using a penalized spline regression. Our inference strategy capitalizes on a three-step Bayesian procedure, which allows to take account for the uncertainty in the propensity score estimation, and avoids model feedback. The correlation among connected units is taken into account using a community detection algorithm, and incorporating random effects in the outcome model. All these sources of variability, including variability of

关键词： causal inference interference spillover effect Bayesian inference network data

来源：评论

学校读者我要写书评

暂无评论

Boosting Automatic Modulation Recognition in Wireless Communications with Frequency Encoder

引用

IEEE Transactions on Cognitive Communications and Networking 2024年

作者： Zhao, Yuhang Ying, Zuobin Wang, Yajie Zhang, Chuan Zheng, Jun Xiong, Zehui Zhu, Liehuang The School of Cyberspace Science and Technology Beijing Institute of Technology Beijing100081 China The Faculty of Data Science City University of Macau Macau999078 China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore487372 Singapore

Automatic modulation recognition (AMR) plays a crucial role in wireless communications. Deep learning-based AMR methods have garnered significant attention due to their high accuracy. Among these, transformer-based models hold great promise but often underperform in noisy environments. To address this problem, we propose a specific transformer model tailored for signal data, named radio transformer (RaT), which aims to extract frequency-domain features to achieve higher classification accuracy. We design a frequency encoder that contains an adaptive filter to assign weights to each frequency component. Additionally, we introduce global average pooling (GAP) in the classification stage to reduce the impact of noise. Furthermore, we analyze the model’s representational capability with varying slice lengths and encoder layers, identifying the optimal configurations for both parameters. Experimental results on the RML 2018.01A dataset demonstrate that our proposed RaT model achieves superior performance, particularly on low signal-to-noise (SNR) conditions. The accuracy is improved by up to 15.79% when the SNR is 4 dB, underscoring its effectiveness and potential for real-time communication applications. © 2015 IEEE.

关键词： Signal modulation

来源：评论

学校读者我要写书评

暂无评论

DAPO-QAOA: An algorithm for solving combinatorial optimization problems by dynamically constructing phase operators

arXiv

引用

arXiv 2025年

作者： Wang, Yukun Li, ZeYang Wan, Linchun Beijing Key Laboratory of Petroleum Data Mining China University of Petroleum Beijing102249 China State Key Lab of Processors Institute of Computing Technology CAS Beijing100190 China School of Computer and Information Science Southwest University Chongqing400715 China

The Quantum Approximate Optimization Algorithm (QAOA) is a well-known hybrid quantum-classical algorithm for combinatorial optimization problems. Improving QAOA involves enhancing its approximation ratio while addressing practical constraints of Noisy Intermediate Scale Quantum (NISQ) devices, such as minimizing the number of two-qubit gates and reducing circuit depth. Although existing research has optimized designs for phase and mixer operators to improve performance, challenges remain, particularly concerning the excessive use of two-qubit gates in the construction of phase operators. To address these issues, we introduce a Dynamic Adaptive Phase Operator (DAPO) algorithm, which dynamically constructs phase operators based on the output of previous layers and neighborhood search approach, optimizing the problem Hamiltonian more efficiently. By using solutions generated by QAOA itself to simplify the problem Hamiltonian at each layer, the algorithm captures the problem’s structural properties more effectively, progressively steering the solution closer to the optimal target. Experimental results on MaxCut and NAE3SAT problems show that DAPO achieves higher approximation ratios and significantly reduces two-qubit RZZ gates, especially in dense graphs. Compared to vanilla QAOA, DAPO uses only 66% of RZZ gates at the same depth while delivering better results, demonstrating its potential for efficient combinatorial optimization in the NISQ era. © 2025, CC BY.

关键词： Hamiltonians

来源：评论

学校读者我要写书评

暂无评论

Large Language Models, Computational Chemistry, and Digital Reticular Chemistry: A Perspective and Proposed Workflow

引用

Molecular Frontiers Journal 2024年第01N02期08卷 3-6页

作者： Abdullah A. AlGhamdi Department of Chemistry and Kavli Energy Nanoscience Institute and Bakar Institute of Digital Materials for the Planet Division of Computing Data Science and Society University of California Berkeley CA USA UC Berkeley-KACST Joint Center of Excellence for Nanomaterials for Clean Energy Applications King Abdulaziz City for Science and Technology Riyadh 11442 Saudi Arabia

In this article, I explore the synergy between Large Language Models (LLMs) and computational chemistry in the context of digital reticular chemistry and propose a workflow leveraging these technologies to advance research and discovery in the field. I argue that understanding the intricacies of new tools is imperative before integrating them into applications, and that the proposed workflow, though robust, merely offers a glimpse into the expansive potential and applications of this field.

关键词： Reticular Chemistry Digital Chemistry Computational Chemistry Large Language Models Generative Pretrained Transformer Artificial Intelligence Machine Learning data science

来源：评论

学校读者我要写书评

暂无评论

Matching Knowledge Graphs in Entity Embedding Spaces: An Experimental Study [Extended Abstract]

Matching Knowledge Graphs in Entity Embedding Spaces: An Exp...

引用

International Conference on data Engineering

作者： Weixin Zeng Xiang Zhao Zhen Tan Jiuyang Tang Xueqi Cheng Laboratory for Big Data and Decision National University of Defense Technology China Science and Technology on Information Systems Engineering Laboratory National University of Defense Technology China Institute of Computing Technology CAS China

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Entity alignment (EA) identifies equivalent entities that locate in different knowledge graphs (KGs), and has attracted growing research interests over the last few years with the advancement of KG embedding techniques. Although a pile of embedding-based EA frameworks have been developed, they mainly focus on improving the performance of entity representation learning, while largely overlook the subsequent stage that matches $KGs$ in entity embedding spaces. Nevertheless, accurately matching entities based on learned entity representations is crucial to the overall alignment performance, as it coordinates individual alignment decisions and determines the global matching result. Hence, it is essential to understand how well existing solutions for matching KGs in entity embedding spaces perform on present benchmarks, as well as their strengths and weaknesses. To this end, in this article we provide a comprehensive survey and evaluation of matching algorithms for KGs in entity embedding spaces in terms of effectiveness and efficiency on both classic settings and new scenarios that better mirror real-life challenges. Based on in-depth analysis, we provide useful insights into the design trade-offs and good paradigms of existing works, and suggest promising directions for future development.

关键词： Surveys Representation learning Knowledge graphs Benchmark testing data engineering Mirrors

来源：评论

学校读者我要写书评

暂无评论

Unified Guidance for Geometry-Conditioned Molecular Generation

arXiv

引用

arXiv 2025年

作者： Ayadi, Sirine Hetzel, Leon Sommer, Johanna Theis, Fabian Günnemann, Stephan School of Computation Information and Technology Technical University of Munich Germany Munich Data Science Institute Technical University of Munich Germany Center for Computation Health Helmholtz Munich Germany

Effectively designing molecular geometries is essential to advancing pharmaceutical innovations, a domain, which has experienced great attention through the success of generative models and, in particular, diffusion models. However, current molecular diffusion models are tailored towards a specific downstream task and lack adaptability. We introduce UniGuide, a framework for controlled geometric guidance of unconditional diffusion models that allows flexible conditioning during inference without the requirement of extra training or networks. We show how applications such as structure-based, fragment-based, and ligand-based drug design are formulated in the UniGuide framework and demonstrate on-par or superior performance compared to specialised models. Offering a more versatile approach, UniGuide has the potential to streamline the development of molecular generative models, allowing them to be readily used in diverse application scenarios. © 2025, CC BY.

关键词： Molecular docking

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Intrusion Detection System for IoT Networks Using Deep Learning

An Adaptive Intrusion Detection System for IoT Networks Usin...

引用

International Conference on Advances in Electronics, Computers and Communications (ICAECC)

作者： Pon Harshavardhanan V Muneeswaran D. Saravanan P. Vijayakarthik R Natchadalingam Pundru Chandra Shaker Reddy School of Computing Science and Engineering VIT Bhopal University Kothrikalan Madhya Pradesh India Computer Science and Engineering R.L Jalappa Institute of Technology Doddaballapur Karnataka India CSE-Data Science R.L. Jalappa Institute of Technology Bengaluru Karnataka India School of Computer Science and Engineering Lovely Professional University Phagwara Punjab India

ISBN: (数字)9798350305449

ISBN: (纸本)9798350305456

The rapid expansion of the Internet-of-Things (IoT) has never before attracted the attention of cybercriminals. The increasing prevalence of cyberattacks against IoT devices and intermediary communication channels lends credence to this assertion. If an IoT attack goes unnoticed for too long, it might disrupt services severely, costing money. In addition, it poses the risk of having one's identity stolen. For IoT-enabled services to be dependable, secure and financially fruitful, real-time intrusion detection on IoT devices is a must. A new intrusion detection design for IoT devices based on Deep Learning (DL) is presented in this research. In order to identify potentially harmful traffic that could lead to assaults on Internet of Things (IoT) gadgets, this smart framework employs a 4layer deep Fully-Connected (FC) network architecture. To simplify deployment, the suggested system was designed to work with any available communication protocol. During experimental performance evaluation, the suggested system has proven to be effective against both simulated and real invasions. According to the data, the proposed model is more accurate than existing methods. This novel deep learning-based IDS has highest detection rate of 95.7 percent, making it suitable for bolstering the safety of IoT networks.

关键词： Deep learning Accuracy Computer hacking Intrusion detection Training data Real-time systems Safety

来源：评论

学校读者我要写书评

暂无评论

The acyclic coloring of the Direct product and Semi-strong product of special graphs

The acyclic coloring of the Direct product and Semi-strong p...

引用

2021 International Conference on Big data Analysis and Computer science, BDACS 2021

作者： Lu, Qiqi Tian, Shuangliang Peng, Lizhen Northwest for Minzu University Key Laboratory of Streaming Data Computing Technologies and Applications Northwest Minzu University School of Mathematics and Computer Science Lanzhou China

ISBN: (纸本)9781665425612

An acyclic coloring of a graph is a proper vertex coloring without dichromatic cycles. The acyclic chromatic number of G, denoted a(G), is the minimum number of colors required for acyclic coloring of a graph G. We study the acyclic coloring of the direct product, semi-strong product of paths and stars, and the corresponding acyclic chromatic number are determined. © 2021 IEEE.

关键词： Coloring

来源：评论

学校读者我要写书评

暂无评论

Rethink Video Retrieval Representation for Video Captioning

SSRN

引用

SSRN 2024年

作者： Tian, Mingkai Li, Guorong Qi, Yuankai Wang, Shuhui Sheng, Quan Z. Huang, Qingming School of Computer Science and Technology Key Lab of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences China School of Computing Macquarie University Australia Key Laboratory of Intelligent Information Processing Institute of Computer Technology Chinese Academy of Sciences China

Video captioning, a challenging task targeting the automatic generation of accurate and comprehensive descriptions based on video content, has witnessed substantial success recently driven by bridging video representations and textual semantics. Inspired by the nature of the video retrieval task, which learns visual features strongly related to text queries, we propose to take advantage of visual representation learning from the video retrieval framework to tackle video captioning tasks. However, a simple direct application of video retrieval models performs poorly due to the weak ability to capture sufficient video details and temporal information required for video captioning. To increase the attention on details, we propose a learnable token shift module, which flexibly captures subtle movements in local regions across the temporal sequence. Furthermore, we devise a Refineformer, which learns to integrate local video tokens strongly related to desired captions via a cross-attention mechanism. Extensive experiments on MSVD, MSR-VTT and VATEX demonstrate the favorable performance of our method. © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Understanding the impact of disease and vaccine mechanisms on the importance of optimal vaccine allocation

引用

Infectious Disease Modelling 2023年第2期8卷 539-550页

作者： Isobel R.Abell James M.McCaw Christopher M.Baker School of Mathematics and Statistics The University of MelbourneMelbourneAustralia Melbourne Centre for Data Science The University of MelbourneMelbourneAustralia Centre for Epidemiology and Biostatistics Melbourne School of Population and Global HealthThe University of MelbourneMelbourneAustralia Peter Doherty Institute for Infection and Immunity The Royal Melbourne Hospital and the University of MelbourneMelbourneAustralia Centre of Excellence for Biosecurity Risk Analysis The University of MelbourneMelbourneAustralia

Vaccination is an important epidemic intervention ***,it is generally unclear how the outcomes of different vaccine strategies change depending on population characteristics,vaccine mechanisms and allocation *** this paper we develop a conceptual mathematical model to simulate strategies for pre-epidemic *** extend the SEIR model to incorporate a range of vaccine mechanisms and disease *** then compare the outcomes of optimal and suboptimal vaccination strategies for three public health objectives(total infections,total symptomatic infections and total deaths)using numerical *** comparison shows that the difference in outcomes between vaccinating optimally and suboptimally depends on vaccine mechanisms,disease characteristics,and objective *** modelling finds vaccines that impact transmission produce better outcomes as transmission is reduced for all *** vaccines that impact the likelihood of symptomatic disease or dying due to infection,the improvement in outcome as we decrease these variables is dependent on the strategy *** a principled model-based process,this work highlights the importance of designing effective vaccine allocation *** conclude that efficient allocation of resources can be just as crucial to the success of a vaccination strategy as the vaccine effectiveness and/or amount of vaccines available.

关键词： Mathematical modelling Epidemiology

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：