检索结果-内蒙古大学图书馆

A computationally-efficient sandbox algorithm for multifractal analysis of large-scale complex networks with tens of millions of nodes

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Ding, Yuemin Liu, Jin-Long Li, Xiaohui Tian, Yu-Chu Yu, Zu-Guo School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China School of Computer Science Queensland University of Technology BrisbaneQLD4000 Australia Key Laboratory of Intelligent Computing and Information Processing Ministry of Education Hunan Key Laboratory for Computation and Simulation in Science and Engineering Xiangtan University Xiangtan Hunan411105 China School of Information Science and Engineering Wuhan University of Science and Technology Wuhan Hubei430081 China

The fractality of complex networks has attracted much attention with extensive investigations over the last 15 years. As a generalization of fractal analysis, multifractal analysis (MFA) is a useful tool to systematically describe the spatial heterogeneity of both theoretical and experimental fractal patterns. One of the widely used methods for fractal analysis is box-covering. It uses the minimum number of covering boxes to calculate the fractal dimension of complex networks, and is known to be NP-hard. More severely, in comparison with fractal analysis algorithms, MFA algorithms have much higher computational complexity. Among various MFA algorithms for complex networks, the sandbox MFA algorithm behaves with the best computational efficiency. However, the existing sandbox algorithm is still computationally expensive. Thus, so far it has only been applied to small-scale complex networks of the size of about tens of thousands of nodes. It becomes challenging to implement the MFA for large-scale networks with tens of millions of nodes. It is also not clear whether or not MFA results can be improved by a largely increased size of a theoretical network. To tackle these challenges, a computationally-efficient sandbox algorithm (CESA) is presented in this paper for MFA of large-scale networks. Distinct from the existing sandbox algorithm that uses the shortest-path distance matrix to obtain the required information for MFA of complex networks, our CESA employs the breadth-first search (BFS) technique to directly search the neighbor nodes of each layer of center nodes, and then to retrieve the required information. Our CESA's input is a sparse data structure derived from the compressed sparse row (CSR) format designed for compressed storage of the adjacency matrix of large-scale network. A theoretical analysis reveals that the CESA reduces the time complexity of the existing sandbox algorithm from cubic to quadratic, and also improves the space complexity from quadratic

关键词： Computational efficiency

Incremental Online Learning of Randomized Neural Network with Forward Regularization

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Junda Hu, Minghui Li, Ning Al-Ali, Abdulaziz Suganthan, Ponnuthurai Nagaratnam The Key Laboratory of System Control and Information Processing Ministry of Education of China China The Department of Automation Shanghai Jiao Tong University Shanghai200240 China The Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China The School of Electrical and Electronic Nanyang Technological University Singapore The KINDI Computing Research Center College of Engineering Qatar University Qatar

Online learning of deep neural networks suffers from challenges such as hysteretic non-incremental updating, increasing memory usage, past retrospective retraining, and catastrophic forgetting. To alleviate these drawbacks and achieve progressive immediate decision-making, we propose a novel Incremental Online Learning (IOL) process of Randomized Neural Networks (Randomized NN), a framework facilitating continuous improvements to Randomized NN performance in restrictive online scenarios. Within the framework, we further introduce IOL with ridge regularization (-R) and IOL with forward regularization (-F). -R generates stepwise incremental updates without retrospective retraining and avoids catastrophic forgetting. Moreover, we substituted -R with -F as it enhanced precognition learning ability using semi-supervision and realized better online regrets to offline global experts compared to -R during IOL. The algorithms of IOL for Randomized NN with -R/-F on non-stationary batch stream were derived respectively, featuring recursive weight updates and variable learning rates. Additionally, we conducted a detailed analysis and theoretically derived relative cumulative regret bounds of the Randomized NN learners with -R/-F in IOL under adversarial assumptions using a novel methodology and presented several corollaries, from which we observed the superiority on online learning acceleration and regret bounds of employing -F in IOL. Finally, our proposed methods were rigorously examined across regression and classification tasks on diverse datasets, which distinctly validated the efficacy of IOL frameworks of Randomized NN and the advantages of forward regularization. Copyright © 2024, The Authors. All rights reserved.

关键词：

A Dynamic Multi-Objective Evolutionary Algorithm Based on Niche Prediction Strategy

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Zheng, Jinhua Zhang, Bo Zou, Juan Yang, Shengxiang Hu, Yaru Hunan Engineering Research Center of Intelligent System Optimization and Security Xiangtan University Hunan Province Xiangtan411105 China Key Laboratory of Intelligent Computing and Information Processing Ministry of Education of China Xiangtan University Hunan Province Xiangtan411105 China Key Laboratory of Hunan Province for Internet of Things and Information Security Xiangtan University Hunan Province Xiangtan411105 China School of Computer Science and Informatics De Montfort University LeicesterLE1 9BH United Kingdom

In reality, many multi-objective optimization problems are dynamic. The Pareto optimal front (PF) or Pareto optimal solution (PS) of these dynamic multi-objective problems (DMOPs) changes as the environment change. Therefore, solving such problems requires an optimization algorithm that can quickly track the PF or PS after an environment change. Prediction-based response mechanism is a common method used to deal with environmental changes, which is commonly known as center point-based prediction. However, if the predicted direction of the center point is inaccurate, the predicted population will be biased towards one side. In this paper, we propose a niche prediction strategy based on center and boundary points (PCPB) to solve the dynamic multi-objective optimization problems, which consists of three steps. After environmental changes are detected, the first step is to divide the niche, dividing different individuals in the PS into different niche populations. The second step is to independently predict different niches, and select individuals with good convergence and distribution in the niche to predict the individuals that will produce the next generation. Finally, some different individuals are randomly generated in the next possible PS area to ensure the diversity of the population. To verify whether our proposed strategy is effective and competitive, PCPB was compared with five state-of-the-art strategies. The experimental results show that PCPB performed competitively in solving dynamic multi-objective optimization problems, which proves that our algorithm has good competitiveness. © 2022, The Authors. All rights reserved.

关键词： Forecasting

ESNet: evolution and succession network for high-resolution salient object detection 24

学校读者我要写书评

暂无评论

ESNet: evolution and succession network for high-resolution ...

Proceedings of the 41st International Conference on Machine Learning

作者： Hongyu Liu Runmin Cong Hua Li Qianqian Xu Qingming Huang Wei Zhang Institute of Information Science Beijing Jiaotong University & Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing China School of Control Science and Engineering Shandong University & Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Computer Science and Technology Hainan University Hainan China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

Preserving details and avoiding high computational costs are the two main challenges for the High-Resolution Salient Object Detection (HRSOD) task. In this paper, we propose a two-stage HRSOD model from the perspective of evolution and succession, including an evolution stage with Low-resolution Location Model (LrLM) and a succession stage with High-resolution Refinement Model (HrRM). The evolution stage achieves detail-preserving salient objects localization on the low-resolution image through the evolution mechanisms on supervision and feature; the succession stage utilizes the shallow high-resolution features to complement and enhance the features inherited from the first stage in a lightweight manner and generate the final high-resolution saliency prediction. Besides, a new metric named Boundary-Detail-aware Mean Absolute Error (MAEBD) is designed to evaluate the ability to detect details in high-resolution scenes. Extensive experiments on five datasets demonstrate that our network achieves superior performance at real-time speed (49 FPS) compared to state-of-the-art methods. Our code is publicly available at: https://***/rmcong/ESNet_ICML24.

关键词：

Constructions of optimal LCD codes over large finite fields

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Sok, Lin Shi, Minjia Solé, Patrick School of Mathematical Sciences Anhui University Hefei Anhui230601 Department of Mathematics Royal University of Phnom Penh Cambodia Key Laboratory of Intelligent Computing Signal Processing Ministry of Education Anhui University No.3 Feixi Road Hefei Anhui230039 China School of Mathematical Sciences Anhui University HefeiAnhui230601 China National Mobile Communications Research Laboratory Southeast University China CNRS/LAGA University of Paris 8 Saint-Denis93 526 France

In this paper, we prove existence of optimal complementary dual codes (LCD codes) over large finite fields. We also give methods to generate orthogonal matrices over finite fields and then apply them to construct LCD codes. Construction methods include random sampling in the orthogonal group, code extension, matrix product codes and projection over a self-dual basis. Copyright © 2017, The Authors. All rights reserved.

关键词： Matrix algebra

学校读者我要写书评

暂无评论

Pisano period codes

arXiv 2017年

作者： Shi, Minjia Zhang, Zhongyi Solé, Patrick Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University No. 3 Feixi Road Hefei Anhui Province230039 China School of Mathematical Sciences Anhui University Hefei230601 China National Mobile Communications Research Laboratory Southeast University Nanjing210096 China School of Wendian Anhui University Hefei Anhui230601 China CNRS/LAGA University of Paris 8 2 rue de la Liberté Saint-Denis93 526 France

The cyclic codes with parity check polynomial the reciprocal of the characteristic polynomial of the Fibonacci recurrence over a prime finite field are shown to have either one weight or two weights. When these codes are irreducible cyclic we obtain many counterexamples to the conjectural classification of two-weight irreducible cyclic codes of Schmidt and White (2002). When they are reducible and projective their duals are uniformly packed. Copyright © 2017, The Authors. All rights reserved.

关键词： Number theory

Lecture Notes in Control and Information Sciences

学校读者我要写书评

暂无评论

Preface

Lecture Notes in Control and Information Sciences 2023年 492卷 v-vi页

作者： Luan, Xiaoli He, Shuping Liu, Fei Key Laboratory of Advanced Process Control for Light Industry [Ministry of Education Institute of Automation Jiangnan University Jiangsu Wuxi China Key Laboratory of Intelligent Computing and Signal Processing [Ministry of Education School of Electrical Engineering and Automation Anhui University Anhui Hefei China

Computationally Expensive High-Dimensional Multiobjective Optimization via Surrogate-Assisted Reformulation and Decomposition

学校读者我要写书评

暂无评论

IEEE Transactions on Evolutionary Computation 2024年 1-1页

作者： Pan, Linqiang Lin, Jianqing Wang, Handing He, Cheng Tan, Kay Chen Jin, Yaochu School of Artificial Intelligence and Automation Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan China School of Artificial Intelligence Xidian University Xi’an China School of Electrical and Electronic Engineering Huazhong University of Science and Technology Wuhan China Department of Computing The Hong Kong Polytechnic University Hong Kong Hong Kong School of Engineering Trustworth and General Artificial Intelligence Laboratory Westlake University Hangzhou China

In recent decades, various surrogate-assisted evolutionary algorithms (SAEAs) have been proposed to solve computationally expensive multiobjective optimization problems (EMOPs). Nevertheless, designing an SAEA to handle high-dimensional EMOPs and balance convergence, diversity, and computational complexity remains challenging. Here, we propose a two-phase SAEA (TP-SAEA), which follows the idea of convergence first and diversity second, for solving high-dimensional EMOPs. In Phase I, a surrogate-assisted problem reformulation method is proposed to fast-track the Pareto optimal set in association with some reference solutions. Specifically, the high-dimensional EMOP is reformulated into an expensive single-objective one with low-dimensional decision space. Then, the surrogate-assisted optimization is utilized to obtain well-converged solutions. In Phase II, the high-dimensional EMOP is decomposed into two subproblems to explore subregions of the decision space that can effectively promote the diversity of the solutions. The two subproblems are optimized independently via surrogate-assisted optimization, aiming to push the population towards different regions of the Pareto optimal front. Experiments are conducted on EMOPs with 100 to 500 decision variables compared with four state-of-the-art SAEAs. The proposed TP-SAEA obtains well-converged and diverse solutions with only 509 real function evaluations. Moreover, its superiority is examined in six real-world instances with up to 12,000 decision variables. IEEE

关键词： Iron

Dual-State Personalized Knowledge Tracing with Emotional Incorporation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Shanshan Yuan, Fangzheng Wang, keyang Yang, Xun Zhang, Xingyi Wang, Meng Information Materials and Intelligent Sensing Laboratory of Anhui Province Institute of Physical Science and Information Technology Anhui University Hefei230601 China Zhejiang Dahua Technology Co. Ltd China Department of Electronic Engineering and Information Science School of information Science and Technology University of Science and Technology of China Hefei230026 China Key Laboratory of intelligent computing and Signal Processing Ministry of Education school of Computer Science and Technology Anhui University Hefei230601 China School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China

Knowledge tracing has been widely used in online learning systems to guide the students' future learning. However, most existing KT models primarily focus on extracting abundant information from the question sets and explore the relationships between them, but ignore the personalized student behavioral information in the learning process. This will limit the model's ability to accurately capture the personalized knowledge states of students and reasonably predict their performances. To alleviate this limitation, we explicitly models the personalized learning process by incorporating the emotions, a representative personalized behavior in the learning process, into KT framework. Specifically, we present a novel Dual-State Personalized Knowledge Tracing with Emotional Incorporation model to achieve this goal: Firstly, we incorporate emotional information into the modeling process of knowledge state, resulting in the Knowledge State Boosting Module. Secondly, we design an Emotional State Tracing Module to monitor students' personalized emotional states, and propose an emotion prediction method based on personalized emotional states. Finally, we apply the predicted emotions to enhance students' response prediction. Furthermore, to extend the generalization capability of our model across different datasets, we design a transferred version of DEKT, named Transfer Learningbased Self-loop model (T-DEKT). Extensive experiments show our method achieves the state-of-the-art performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Students