检索结果-内蒙古大学图书馆

Multi-task representation learning with multi-view graph convolutional networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Huang, Hong Song, Yu Wu, Yao Shi, Jia Xie, Xia Jin, Hai National Engineering Research Center for Big Data Technology Service Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

Link prediction and node classification are two important downstream tasks of network representation learning. Existing methods have achieved acceptable results but they perform these two tasks separately, which requires a lot of duplication of work and ignores the correlations between tasks. Besides, conventional models suffer from the identical treatment of information of multiple views, thus they fail to learn robust representation for downstream tasks. To this end, we tackle link prediction and node classification problems simultaneously via multi-task multi-view learning in this paper. We first explain the feasibility and advantages of multi-task multi-view learning for these two tasks. Then we propose a novel model named as MT-MVGCN to perform link prediction and node classification tasks simultaneously. More specifically, we design a multi-view graph convolutional network to extract abundant information of multiple views in a network, which is shared by different tasks. We further apply two attention mechanisms: view attention mechanism and task attention mechanism to make views and tasks adjust the view fusion process. Moreover, view reconstruction can be introduced as an auxiliary task to boost the performance of the proposed model. Experiments on real-world network datasets demonstrate that our model is efficient yet effective, and outperforms advanced baselines in these two tasks. © 2021, CC BY.

关键词： data mining

Grace: An Efficient Parallel SPARQL Query System over Large-Scale RDF data

学校读者我要写书评

暂无评论

Grace: An Efficient Parallel SPARQL Query System over Large-...

International Conference on Computer Supported Cooperative Work in Design

作者： Xiang Kang Yuying Zhao Pingpeng Yuan 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 Wuhan China

As a markup language for describing web resources, RDF is often used to represent graph data. SPARQL is a standard query language for RDF data, which is convenient in querying RDF. As RDF data grows rapidly, how to deal with complex queries over large-scale data in a reasonable time still remains many challenges. The existing RDF query systems often fail to respond within a reasonable time when dealing with complex SPARQL queries. Therefore, we propose an efficient parallel SPARQL query system and novel in three aspects. First, the proposed design provides a dynamic selectivity estimation strategy and generates an optimal query plan for parallel query processing. Second, the new design proposes a parallel processing model to maximize the parallelism of the system. Finally, chunk-based task distribution strategy is implemented to assist the parallel processing model. Based on the proposed design, we implement an efficient parallel query system (Grace). Extensive experiments on LUBM and BTC benchmarks show that Grace outperforms RDF-3X, Virtuoso, TripleBit and achieves a good performance of scalability on the number of threads.

关键词： Distribution strategy Scalability Query processing Markup languages Instruction sets Estimation Parallel processing

TCSloT: Text Guided 3D Context and Slope Aware Triple Network for Dental Implant Position Prediction

学校读者我要写书评

暂无评论

TCSloT: Text Guided 3D Context and Slope Aware Triple Networ...

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Xinquan Yang Jinheng Xie Xuechen Li Xuguang Li Linlin Shen Yongqiang Deng College of Computer Science and Software Engineering Shenzhen University Shenzhen China Show Lab National University of Singapore Singapore National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Stomatology Shenzhen University General Hospital Shenzhen China

In implant prosthesis treatment, the surgical guide of implant is used to ensure accurate implantation. However, such design heavily relies on the manual location of the implant position. When deep neural network has been proposed to assist the dentist in locating the implant position, most of them take a single slice as input, which do not fully explore 3D contextual information and ignores the influence of implant slope. In this paper, we design a Text Guided 3D Context and Slope Aware Triple Network (TCSloT) to integrate the perception of contextual information from multiple adjacent slices and awareness of variation of implant slopes. A Texture Variation Perception (TVP) module is correspondingly design to process the multiple slices and capture the texture variation among slices and a Slope-Aware Loss (SAL) is proposed to dynamically assign adaptive weights for the regression head. Additionally, we design a conditional text guidance (CTG) module to integrate the text condition (i.e., left, middle and right) from the CLIP to assist the implant position prediction. Extensive experiments on a dental implant dataset through five-fold cross-validation, demonstrated that the proposed TCSloT achieves superior performance than existing methods.

关键词：

A hardware-based multi-factor authentication - An initiative to secure web applications

学校读者我要写书评

暂无评论

AIP Conference Proceedings 2024年第1期3075卷

作者： K. Sornalakshmi Revathi Venkataraman V. Kavitha P. Shamunesh Ashwin Raja Charu Khemka Department of Computing Technologies School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamilnadu India School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamilnadu India Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamilnadu India

Hardware-based multi-factor authentication is a broad and extensive security solution approach to overcome the impact of cyber data compromises that are happening these days in applications using cutting-edge technologies. Our proposed work handles the high-end security modules by developing frameworks in parallel to the IoT-based security visualization to make the system’s security an unbreakable unit. This work depicts the idea of prototyping a hardware key, termed in this paper as “AppSec Key” that handles the MFA/2FA checkpoints into a hardware level making it impossible for hackers to bypass it online using the tools. The visualization of IoT setup to the software security is a new revolution to the complication of mishandling data online. This work proposes sequence-based authentication that adds an extra protection layer. The overall approaches to tackle the existing cyber threats are been discussed with many real-world instances.

关键词：

Refining Fast Calorimeter Simulations with a Schrödinger Bridge

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Diefenbacher, Sascha Mikuni, Vinicius Nachman, Benjamin Physics Division Lawrence Berkeley National Laboratory BerkeleyCA94720 United States National Energy Research Scientific Computing Center Berkeley Lab BerkeleyCA94720 United States Berkeley Institute for Data Science University of California BerkeleyCA94720 United States

Machine learning-based simulations, especially calorimeter simulations, are promising tools for approximating the precision of classical high energy physics simulations with a fraction of the generation time. Nearly all methods proposed so far learn neural networks that map a random variable with a known probability density, like a Gaussian, to realistic-looking events. In many cases, physics events are not close to Gaussian and so these neural networks have to learn a highly complex function. We study an alternative approach: Schrödinger bridge Quality Improvement via Refinement of Existing Lightweight Simulations (SQuIRELS). SQuIRELS leverages the power of diffusion-based neural networks and Schrödinger bridges to map between samples where the probability density is not known explicitly. We apply SQuIRELS to the task of refining a classical fast simulation to approximate a full classical simulation. On simulated calorimeter events, we find that SQuIRELS is able to reproduce highly non-trivial features of the full simulation with a fraction of the generation time. Copyright © 2023, The Authors. All rights reserved.

关键词： Calorimeters

On identifying statistical redundancy at the level of amino acid subsequences

学校读者我要写书评

暂无评论

On identifying statistical redundancy at the level of amino ...

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Rajapaksa, Sandun Sumanaweera, DInithi De La Banda, Maria Garcia Stuckey, Peter Abramson, David Allison, Lloyd Lesk, Arthur Konagurthu, Arun Monash University Department of Data Science and Artificial Intelligence ClaytonVIC3800 Australia University of Queensland Research Computing Centre BrisbaneQLD4072 Australia Pennsylvania State University University Park Department of Biochemistry and Molecular Biology PA16802 United States

ISBN: (纸本)9781665401265

This paper presents a framework to characterize and identify local sequences of proteins that are statistically redundant under the measure of Shannon information content while accounting for variations in their occurrences over evolutionary insertions, deletions, and substitutions of amino acids. The identification of such local sequences provides insights for downstream studies on proteins. Here, we have applied our methods to amino acid sequence data sets derived from a database corresponding to 935,552 substructural regions of varying sizes, covering 113,724 proteins from the protein data bank. The results identify, among others, a surjective mapping between 110,598 local sequences (with an average length of 82 amino acids per sequence) and 1,493 topological shapes. The C++ source code and supporting material are available from https://***/bibm2021. © 2021 IEEE.

关键词： Amino acids

Energy-Efficient Dynamic Asynchronous Federated Learning in Mobile Edge computing Networks

学校读者我要写书评

暂无评论

Energy-Efficient Dynamic Asynchronous Federated Learning in ...

IEEE International Conference on Communications (ICC)

作者： Guozeng Xu Xiuhua Li Hui Li Qilin Fan Xiaofei Wang Victor C. M. Leung School of Big Data & Software Engineering Chongqing University Chongqing China TKLAN College of Intelligence & Computing Tianjin University Tianjin China College of Computer Science & Software Engineering Shenzhen University Shenzhen China Department of Electrical & Computer Engineering The University of British Columbia Vancouver Canada

To break data silos and address the challenge of green communication, federated learning (FL) is widely used at network edges to train deep learning models in mobile edge computing (MEC) networks. However, many existing FL algorithms do not fully consider the dynamic environment, resulting in slower convergence of the model and larger training energy consumption. In this paper, we design a dynamic asynchronous federated learning (DAFL) model to improve the efficiency of FL in MEC networks. Specifically, we dynamically choose a certain number of mobile devices (MDs) by their arrival order to participate in the global aggregation at each epoch. Meanwhile, we analyze the energy consumption model of local update and upload update, and formulate the problem as a dynamic sequential decision problem to minimize the energy consumption, which is NP-hard. To address it, we propose an energy-efficient algorithm based on deep reinforcement learning named DDAFL, to intelligently determine the number of MDs participating in global aggregation according to the state of MEC networks at each epoch. Compared with baseline schemes, the proposed algorithm can significantly reduce energy consumption and accelerate model convergence.

关键词：

Exploring the Role of Diversity in Example Selection for In-Context Learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Kapuriya, Janak Kaushik, Manit Ganguly, Debasis Bhatia, Sumit Data Science Institute University of Galway Galway Ireland Computer Science and Engineering IIIT Delhi New Delhi India School of Computing University of Glasgow Glasgow United Kingdom Media and Data Science Research Lab Adobe Systems Noida India

In-Context Learning (ICL) has gained prominence due to its ability to perform tasks without requiring extensive training data and its robustness to noisy labels. A typical ICL workflow involves selecting localized examples relevant to a given input using sparse or dense embedding-based similarity functions. However, relying solely on similarity-based selection may introduce topical biases in the retrieved contexts, potentially leading to suboptimal downstream performance. We posit that reranking the retrieved context to enhance topical diversity can improve downstream task performance. To achieve this, we leverage maximum marginal relevance (MMR) which balances topical similarity with inter-example diversity. Our experimental results demonstrate that diversifying the selected examples leads to consistent improvements in downstream performance across various context sizes and similarity functions. The implementation of our approach is made available at https://***/janak11111/Diverse-ICL. © 2025, CC BY.

关键词：

Demystifying the vulnerability propagation and its evolution via dependency trees in the NPM ecosystem

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Liu, Chengwei Chen, Sen Fan, Lingling Chen, Bihuan Liu, Yang Peng, Xin College of Intelligence and Computing Tianjin University Tianjin China College of Cyber Science Nankai University Tianjin China School of Computer Science Shanghai Key Laboratory of Data Science Fudan University Shanghai China School of Computer Science and Engineering Nanyang Technological University Singapore Singapore Nanyang Technological University Singapore

Third-party libraries with rich functionalities facilitate the fast development of JavaScript software, leading to the explosive growth of the NPM ecosystem. However, it also brings new security threats that vulnerabilities could be introduced through dependencies from third-party libraries. In particular, the threats could be excessively amplified by transitive dependencies. Existing research only considers direct dependencies or reasoning transitive dependencies based on reachability analysis, which neglects the NPM-specific dependency resolution rules as adapted during real installation, resulting in wrongly resolved dependencies. Consequently, further fine-grained analysis, such as precise vulnerability propagation and their evolution over time in dependencies, cannot be carried out precisely at a large scale, as well as deriving ecosystem-wide solutions for vulnerabilities in dependencies. To fill this gap, we propose a knowledge graph-based dependency resolution, which resolves the inner dependency relations of dependencies as trees (i.e., dependency trees), and investigates the security threats from vulnerabilities in dependency trees at a large scale. Specifically, we first construct a complete dependencyvulnerability knowledge graph (DVGraph) that captures the whole NPM ecosystem (over 10 million library versions and 60 million well-resolved dependency relations). Based on it, we propose a novel algorithm (DTResolver) to statically and precisely resolve dependency trees, as well as transitive vulnerability propagation paths, for each package by taking the official dependency resolution rules into account. Based on that, we carry out an ecosystem-wide empirical study on vulnerability propagation and its evolution in dependency trees. Our study unveils lots of useful findings, and we further discuss the lessons learned and solutions for different stakeholders to mitigate the vulnerability impact in NPM based on our findings. For example, we implement a depend

关键词： Libraries