检索结果-内蒙古大学图书馆

Integrating Conjugate Gradients Into Evolutionary Algorithms for Large-Scale Continuous Multi-Objective Optimization

引用

IEEE/CAA Journal of Automatica Sinica 2022年第10期9卷 1801-1817页

作者： Ye Tian Haowen Chen Haiping Ma Xingyi Zhang Kay Chen Tan Yaochu Jin the Information Materials and Intelligent Sensing Laboratory of Anhui Province Institutes of Physical Science and Information TechnologyAnhui UniversityHefei 230601China the Institute of Artificial Intelligence Hefei Comprehensive National Science CenterHefei 230601China IEEE the Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Artificial IntelligenceAnhui UniversityHefei 230601China the Department of Computing The Hong Kong Polytechnic UniversityHong Kong SARChina the Faculty of Technology Bielefeld UniversityBielefeld 33619Germany

Large-scale multi-objective optimization problems(LSMOPs)pose challenges to existing optimizers since a set of well-converged and diverse solutions should be found in huge search *** evolutionary algorithms are good at solving small-scale multi-objective optimization problems,they are criticized for low efficiency in converging to the optimums of *** contrast,mathematical programming methods offer fast convergence speed on large-scale single-objective optimization problems,but they have difficulties in finding diverse solutions for ***,how to integrate evolutionary algorithms with mathematical programming methods to solve LSMOPs remains *** this paper,a hybrid algorithm is tailored for LSMOPs by coupling differential evolution and a conjugate gradient *** the one hand,conjugate gradients and differential evolution are used to update different decision variables of a set of solutions,where the former drives the solutions to quickly converge towards the Pareto front and the latter promotes the diversity of the solutions to cover the whole Pareto *** the other hand,objective decomposition strategy of evolutionary multi-objective optimization is used to differentiate the conjugate gradients of solutions,and the line search strategy of mathematical programming is used to ensure the higher quality of each offspring than its *** comparison with state-of-the-art evolutionary algorithms,mathematical programming methods,and hybrid algorithms,the proposed algorithm exhibits better convergence and diversity performance on a variety of benchmark and real-world LSMOPs.

关键词： Conjugate gradient differential evolution evolutionary computation large-scale multi-objective optimization mathematical programming

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal Context Modeling for Road Obstacle Detection 1

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Wu, Xiuen Wang, Tao Liang, Lingyu Li, Zuoyong Ching, Fum Yew College of Computer and Data Science Fuzhou University Fuzhou350108 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350108 China The Key Laboratory of Cognitive Computing and Intelligent Information Processing of Fujian Education Institutions Wuyi University Wuyishan354300 China School of Electronic and Information Engineering South China University of Technology Guangzhou510641 China Ministry of Education Key Laboratory of Computer Network and Information Integration Southeast University Nanjing211189 China Guangzhou510320 China Penang11800 Malaysia

ISBN: (数字)9783031200960

ISBN: (纸本)9783031200953

Road obstacle detection is an important problem for vehicle driving safety. In this paper, we aim to obtain robust road obstacle detection based on spatio-temporal context modeling. Firstly, a data-driven spatial context model of the driving scene is constructed with the layouts of the training data. Then, obstacles in the input image are detected via the state-of-the-art object detection algorithms, and the results are combined with the generated scene layout. In addition, to further improve the performance and robustness, temporal information in the image sequence is taken into consideration, and the optical flow is obtained in the vicinity of the detected objects to track the obstacles across neighboring frames. Qualitative and quantitative experiments were conducted on the Small Obstacle Detection (SOD) dataset and the Lost and Found dataset. The results indicate that our method with spatio-temporal context modeling is superior to existing methods for road obstacle detection. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Extracting Variable-Depth Logical Document Hierarchy from Long Documents:Method,Evaluation,and Application

引用

Journal of Computer Science & Technology 2022年第3期37卷 699-718页

作者： Rong-Yu Cao Yi-Xuan Cao Gan-Bin Zhou Ping Luo Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China WeChat Search Application Department Tencent Holdings Ltd.Beijing 100080China Peng Cheng Laboratory Shenzhen 518066China

In this paper,we study the problem of extracting variable-depth"logical document hierarchy"from long documents,namely organizing the recognized"physical document objects"into hierarchical *** discovery of logical document hierarchy is the vital step to support many downstream applications(e.g.,passage-based retrieval and high-quality information extraction).However,long documents,containing hundreds or even thousands of pages and a variable-depth hierarchy,challenge the existing *** address these challenges,we develop a framework,namely Hierarchy Extraction from Long Document(HELD),where we"sequentially"insert each physical object at the proper position on the current *** whether each possible position is proper or not can be formulated as a binary classification *** further improve its effectiveness and efficiency,we study the design variants in HELD,including traversal orders of the insertion positions,heading extraction explicitly or implicitly,tolerance to insertion errors in predecessor steps,and so *** for evaluations,we find that previous studies ignore the error that the depth of a node is correct while its path to the root is *** such mistakes may worsen the downstream applications seriously,a new measure is developed for a more careful *** empirical experiments based on thousands of long documents from Chinese financial market,English financial market and English scientific publication show that the HELD model with the"root-to-leaf"traversal order and explicit heading extraction is the best choice to achieve the tradeoff between effectiveness and efficiency with the accuracy of 0.972,6,0.729,1 and 0.957,8 in the Chinese financial,English financial and arXiv datasets,***,we show that the logical document hierarchy can be employed to significantly improve the performance of the downstream passage retrieval *** summary,we conduct a systematic study on this task in terms of methods

关键词： logical document hierarchy long documents passage retrieval

来源：评论

学校读者我要写书评

暂无评论

Trajectory diffusion for objectgoal navigation 24

Trajectory diffusion for objectgoal navigation

引用

Proceedings of the 38th International Conference on Neural information processing Systems

作者： Xinyao Yu Sixian Zhang Xinhang Song Xiaorong Qin Shuqiang Jiang Key Lab of Intelligent Information Processing Laboratory of the Chinese Academy of Sciences (CAS) Institute of Computing Technology Beijing and University of Chinese Academy of Sciences Beijing Key Lab of Intelligent Information Processing Laboratory of the Chinese Academy of Sciences (CAS) Institute of Computing Technology Beijing and University of Chinese Academy of Sciences Beijing and Institute of Intelligent Computing Technology Suzhou CAS

ISBN: (纸本)9798331314385

Object goal navigation requires an agent to navigate to a specified object in an unseen environment based on visual observations and user-specified goals. Human decision-making in navigation is sequential, planning a most likely sequence of actions toward the goal. However, existing ObjectNav methods, both end-to-end learning methods and modular methods, rely on single-step planning. They output the next action based on the current model input, which easily overlooks temporal consistency and leads to myopic planning. To this end, we aim to learn sequence planning for ObjectNav. Specifically, we propose trajectory diffusion to learn the distribution of trajectory sequences conditioned on the current observation and the goal. We utilize DDPM and automatically collected optimal trajectory segments to train the trajectory diffusion. Once the trajectory diffusion model is trained, it can generate a temporally coherent sequence of future trajectory for agent based on its current observations. Experimental results on the Gibson and MP3D datasets demonstrate that the generated trajectories effectively guide the agent, resulting in more accurate and efficient navigation. The code is available at https://***/sx-zhang/***.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Meta-path and Meta-schema Hierarchical Aggregation for Heterogeneous Graph Neural Networks

Meta-path and Meta-schema Hierarchical Aggregation for Heter...

引用

Smart World Congress (SWC), IEEE

作者： Ling Wu Pingping Gao Kun Guo Fujian Key Laboratory of Network Computing and Intelligent Information Processing College of Computer and Data Sciencen (Fuzhou University) China

ISBN: (数字)9798331520861

ISBN: (纸本)9798331520878

With deep learning’s advancement in recent years, heterogeneous graph neural networks (HGNNs) have drawn a lot of interest. They are a group of deep learning models specifically designed for handling heterogeneous graph data, in which nodes and edges are of various types and all nodes are assumed to have either direct or indirect associations. A metaschema, which serves as a thorough and unified blueprint for the heterogeneous graph, elegantly connects varied node types to other heterogeneous nodes via multiple heterogeneous edges with rich sematincs. However, many existing methods that utilize meta-schema to mine heterogeneous information often focus on the different meta-relationships inside the schema, limiting the meta-schema to describing only the local relational semantics. To better utilize meta-schema for efficiently integrating different heterogeneous information, we organize them into a hierarchical structure(i.e., hierarchical meta-schema), with all types of nodes distributed across different layers. The layers are interconnected through heterogeneous relationships. The target type is placed at the final layer and others are arranged hierarchically in the front according to the heterogeneous relationships defined in the meta-schema. During information aggregation, according to the hierarchical meta-schema, the information of each layer is gradually aggregated to the target type on the final layer from far to near via the attention mechanism. Moreover, metapaths regularly begin and end with the same type and help to define complex structures and semantic. Therefore, we also consider the semantic information of neighbors based on metapaths within the proposed hierarchical meta-schema to enhance the complex semantics among nodes of the same-type that may be lacking in the meta-schema. Finally, we proposed a meta-path and meta-schema hierarchical aggregation for heterogeneous graph neural network model, named HGNN-MMHA. And we may allow the meta-schema to not

关键词： Deep learning Correlation Limiting Attention mechanisms Semantics Graph neural networks Heterogeneous networks Data models

来源：评论

学校读者我要写书评

暂无评论

Speculative decoding with CTC-based draft model for LLM inference acceleration 24

Speculative decoding with CTC-based draft model for LLM infe...

引用

Proceedings of the 38th International Conference on Neural information processing Systems

作者： Zhuofan Wen Shangtong Gui Yang Feng Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences and State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences and Key Laboratory of Al Safety Chinese Academy of Sciences and University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798331314385

Inference acceleration of large language models (LLMs) has been put forward in many application scenarios and speculative decoding has shown its advantage in addressing inference acceleration. Speculative decoding usually introduces a draft model to assist the base LLM where the draft model produces drafts and the base LLM verifies the draft for acceptance or rejection. In this framework, the final inference speed is decided by the decoding speed of the draft model and the acceptance rate of the draft provided by the draft model. Currently the widely used draft models usually generate draft tokens for the next several positions in a non-autoregressive way without considering the correlations between draft tokens. Therefore, it has a high decoding speed but an unsatisfactory acceptance rate. In this paper, we focus on how to improve the performance of the draft model and aim to accelerate inference via a high acceptance rate. To this end, we propose a CTC-based draft model which strengthens the correlations between draft tokens during the draft phase, thereby generating higher-quality draft candidate sequences. Experiment results show that compared to strong baselines, the proposed method can achieve a higher acceptance rate and hence a faster inference speed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fusion recommendation algorithm based on DeepWalk and Item-Based collaborative filtering 3

Fusion recommendation algorithm based on DeepWalk and Item-B...

引用

3rd International Conference on Computer Science and Management Technology, ICCSMT 2022

作者： Yu, Yicheng Li, Rongbin Yin, Jun Qinghai Normal University School of Computing Xi'Ning China The State Key Laboratory of Tibetan Intelligent Information Processing and Application Xi'Ning China

ISBN: (纸本)9798350320404

Collaborative filtering techniques have been applied to personalised recommendation systems in recommender systems. However, with the gradual increase in the number of platform users and goods, the user rating data on the entire project matrix is extremely sparse, resulting in the inaccuracy of the prediction results. DeepWalk, on the other hand, still performs well when the data is sparse. Therefore, DeepWalk is introduced into collaborative filtering, and a fusion recommendation algorithm based on DeepWalk and collaborative filtering is proposed to reduce the impact of cold start and sparsity on the recommendation results. Experiments show that the proposed fusion recommendation algorithm has higher recommendation accuracy when the data is sparse compared with other traditional algorithms, which improves the recommendation quality to a certain extent. © 2022 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Structure-constrain Source Free Domain Adaptation with Regularized Knowledge Distillation of Source Model 13

Structure-constrain Source Free Domain Adaptation with Regul...

引用

13th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2024

作者： Yang, Dan Peng, Xin Su, Cheng Tan, Dayu Chen, Chaoyang Zhong, Weimin Ministry of Education East China University of Science and Technology Key Laboratory of Smart Manufacturing in Energy Chemical Process Shanghai200237 China Ministry of Education Anhui University Key Laboratory of Intelligent Computing and Signal Processing Anhui Hefei230601 China School of Information and Electrical Engineering Hunan University of Science and Technology Xiangtan China

ISBN: (纸本)9798350361674

Transfer learning aims to leverage the knowledge of the source domain to help the learning of unlabeled target domain models. However, all conventional transfer learning methods assume that samples from source and target domains are always freely accessible. However, this assumption is rarely plausible in real-world due to data privacy. To combat this challenge, we introduce Structure-constrain Source Free Domain Adaptation with regularized Knowledge Distillation of source model (SSFDA-KD). Our method is based on the observations that a deterministic classification result can be obtained when the target data distribution aligns with the source data distribution, and a well-trained model not only yields a deterministic classification for a sample but also has clear category boundaries, which implies samples that are close together belong to the same category. From those, we first generate the source model with labeled source data, which is regarded as a well-trained model. Then, we identify target prototypes with lower self-entropy and assign the pseudo-labels to other samples according to the neighborhood structure. Finally, we refine the target model by minimizing prediction loss, constraining internal structure via triplet loss, and reducing knowledge distillation loss. Experiments of fault diagnosis based on WWTPs are conducted to validate its effectiveness. © 2024 IEEE.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

CHIME: A Cache-Efficient and High-Performance Hybrid Index on Disaggregated Memory 24

CHIME: A Cache-Efficient and High-Performance Hybrid Index o...

引用

30th ACM Symposium on Operating Systems Principles, SOSP 2024

作者： Luo, Xuchuan Shen, Jiacheng Zuo, Pengfei Wang, Xin Lyu, Michael R. Zhou, Yangfan National Key Laboratory of Parallel and Distributed Computing Changsha China School of Computer Science Fudan University Shanghai China Duke Kunshan University Kunshan China Huawei Cloud Shenzhen China Shanghai Key Laboratory of Intelligent Information Processing Shanghai China The Chinese University of Hong Kong Hong Kong Hong Kong

ISBN: (纸本)9798400712517

Disaggregated memory (DM) is a widely discussed datacenter architecture in academia and industry. It decouples computing and memory resources from monolithic servers into two network-connected resource pools. Range indexes are widely adopted by storage systems on DM to efficiently locate and query remote data. However, existing range indexes on DM suffer from either high computing-side cache consumption or high memory-side read amplifications. In this paper, we propose CHIME, a hybrid index combining B+ trees with hopscotch hashing, to achieve low cache consumption and low read amplifications simultaneously. There are three challenges in constructing CHIME on DM, i.e., the complicated optimistic synchronization, the extra metadata access, and the read amplifications introduced by hopscotch hashing. CHIME leverages 1) a three-level optimistic synchronization scheme to synchronize read and write operations with various granularities, 2) an access-aggregated metadata management technique to eliminate extra metadata accesses by piggybacking and replicating metadata, and 3) an effective hotness-aware speculative read mechanism to mitigate the read amplifications of hopscotch hashing. Experimental results show that CHIME outperforms the state-of-the-art range indexes on DM by up to 5.1× with the same cache size and achieves similar performance with up to 8.7× lower cache consumption. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Memory architecture

来源：评论

学校读者我要写书评

暂无评论

The Mean Time to Absorption on Horizontal Partitioned Sierpinski Gasket Networks

引用

Analysis in Theory and Applications 2024年第1期40卷 1-21页

作者： Zhizhuo Zhang Bo Wu Zuguo Yu School of Mathematics Southeast UniversityNanjingJianagsu 211189China School of Applied Mathematics Nanjing University of Finance and EconomicsNanjingJiangsu 210023China Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education and Hunan Key Laboratory for Computation and Simulation in Science and Engineering Xiangtan UniversityXiangtanHunan 411105China

The random walk is one of the most basic dynamic properties of complex networks,which has gradually become a research hotspot in recent years due to its many applications in actual *** important characteristic of the random walk is the mean time to absorption,which plays an extremely important role in the study of topology,dynamics and practical application of complex *** the mean time to absorption on the regular iterative self-similar network models is an important way to explore the inﬂuence of self-similarity on the properties of random walks on the *** existing literatures have proved that even local self-similar structures can greatly affect the properties of random walks on the global network,but they have failed to prove whether these effects are related to the scale of these self-similar *** this article,we construct and study a class of Horizontal Par-titioned Sierpinski Gasket network model based on the classic Sierpinski gasket net-work,which is composed of local self-similar structures,and the scale of these structures will be controlled by the partition coefﬁcient ***,the analytical expressions and approximate expressions of the mean time to absorption on the network model are obtained,which prove that the size of the self-similar structure in the network will directly restrict the inﬂuence of the self-similar structure on the properties of random walks on the ***,we also analyzed the mean time to absorption of different absorption nodes on the network toﬁnd the location of the node with the highest absorption efﬁciency.

关键词： Mean time to absorption self-similar network Sierpinski Gasket

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：