检索结果-内蒙古大学图书馆

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Jiacong Hu Jing Gao Jingwen Ye Yang Gao Xingen Wang Zunlei Feng Mingli Song College of Computer Science and Technology Zhejiang University and State Key Laboratory of Blockchain and Data Security Zhejiang University Robotics Institute School of Computer Science Carnegie Mellon University Electrical and Computer Engineering National University of Singapore Bangsheng Technology Co. Ltd. College of Computer Science and Technology Zhejiang University and Bangsheng Technology Co. Ltd. School of Software Technology Zhejiang University and State Key Laboratory of Blockchain and Data Security Zhejiang University and Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain College of Computer Science and Technology Zhejiang University and State Key Laboratory of Blockchain and Data Security Zhejiang University and Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security

ISBN: (纸本)9798331314385

With the rapid development of deep learning, the increasing complexity and scale of parameters make training a new model increasingly resource-intensive. In this paper, we start from the classic convolutional neural network (CNN) and explore a paradigm that does not require training to obtain new models. Similar to the birth of CNN inspired by receptive fields in the biological visual system, we draw inspiration from the information subsystem pathways in the biological visual system and propose Model Disassembling and Assembling (MDA). During model disassembling, we introduce the concept of relative contribution and propose a component locating technique to extract task-aware components from trained CNN classifiers. For model assembling, we present the alignment padding strategy and parameter scaling strategy to construct a new model tailored for a specific task, utilizing the disassembled task-aware components. The entire process is akin to playing with LEGO bricks, enabling arbitrary assembly of new models, and providing a novel perspective for model creation and reuse. Extensive experiments showcase that task-aware components disassembled from CNN classifiers or new models assembled using these components closely match or even surpass the performance of the baseline, demonstrating its promising results for model reuse. Furthermore, MDA exhibits diverse potential applications, with comprehensive experiments exploring model decision route analysis, model compression, knowledge distillation, and more. For more information, please visit https://***/.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DSCT:a novel deep-learning framework for rapid and accurate spatial transcriptomic cell typing

引用

National science Review 2025年第5期12卷 123-138页

作者： Yiheng Xu Bin Yu Xuan Chen Aibing Peng Quyuan Tao Youzhe He Yueming Wang Xiao-Ming Li Department of Neurology and Department of Psychiatry the Second Affiliated HospitalZhejiang University School of Medicine NHC and CAMS Key Laboratory of Medical Neurobiology MOE Frontier Center of Brain Science and Brain-machine Integration School of Brain Science and Brain MedicineZhejiang University College of Computer Science and Technology Zhejiang University Key Laboratory of Novel Targets and Drug Study for Neural Repair of Zhejiang Province Institute of brain and cognitive science Hangzhou City University School of Medicine Department of Neurobiology Affiliated Mental Health Center & Hangzhou Seventh People's HospitalZhejiang University School of Medicine BGI Research Qiushi Academy for Advanced Studies Zhejiang University The Nanhu Brain-computer Interface institute

Unraveling complex cell-type-composition and gene-expression patterns at the cellular spatial resolution is crucial for understanding intricate cell functions in the brain. In this study, we developed Deep Neural Network-based Spatial Cell Typing(DSCT)—an innovative framework for spatial cell typing within spatial transcriptomic data sets. This approach utilizes a synergistic integration of an enhanced gene-selection strategy and a lightweight deep neural network for data training, offering a more rapid and accurate solution for the analysis of spatial transcriptomic data. Based on comprehensive analysis, DSCT achieved exceptional accuracy in cell-type identification across various brain regions, species and spatial transcriptomic *** also performed well in mapping finer cell types, thereby showcasing its versatility and adaptability across diverse data sets. Strikingly, DSCT exhibited high efficiency and remarkable processing speed, with fewer computational resource demands. As such, this novel approach opens new avenues for exploring the spatial organization of cell types and gene-expression patterns, advancing our understanding of biological functions and pathologies within the nervous system.

关键词： DSCT spatial cell typing spatial transcriptomics deep-learning neural network

来源：评论

学校读者我要写书评

暂无评论

Multimedia Classification via Tensor Linear Discriminant Analysis

引用

IEEE Transactions on Broadcasting 2024年第4期70卷 1139-1152页

作者： Chang, Shih-Yu Wu, Hsiao-Chun Yan, Kun Chih-Hao Huang, Scott Wu, Yiyan San Jose State University Department Of Applied Data Science San JoseCA95192 United States Louisiana State University School Of Electrical Engineering And Computer Science Baton RougeLA70803 United States Yuan Ze University Innovation Center For Ai Applications Taoyuan32003 Taiwan Guilin University Of Electronic Technology Guangxi Key Laboratory Of Wireless Wideband Communication And Signal Processing Department Of Information And Telecommunication Guilin541004 China National Tsing Hua University Department Of Electrical Engineering Hsinchu300 Taiwan Western University Department Of Electrical And Computer Engineering LondonONN6A 3K7 Canada

Linear discriminant analysis (LDA) is a well-known feature-extraction technique for data analytic and pattern classification. As the dimensionality of multimedia data has increased in this big era, it is often to characterize data by tensors. Over the past two decades, researchers have thus explored to extend LDA to the general tensor space, especially in two common ways: LDA of tensors using tensor decomposition methods (by conversion of tensors to matrices) and LDA of tensors built upon the T-product. However, both of the aforementioned approaches have restrictions thereby. A critical problem about how to carry out LDA of arbitrary scatter tensors based on the Einstein product still remains unsolved by the existing methods. Therefore, we propose a novel tensor LDA (a.k.a. TLDA) approach, which can carry out the LDA of arbitrary-dimensional scatter-tensors without any need of tensor decomposition. Besides, for reducing the computation time, we also design a parallel paradigm to execute our proposed TLDA in this work. Numerical experiments conducted over real multimedia data demonstrate the efficacy of our proposed new TLDA in terms of classification accuracy. Moreover, the comparison of the classification accuracies, computational-complexities, and memory-complexities of our proposed novel TLDA scheme and other existing tensor-based LDA methods is made. By leveraging TLDA for high-dimensional feature extraction, segmentation, and user-item interaction data processing, future multimedia recommendation systems can facilitate more accurate, engaging, and satisfactory user experience over the Internet. © 1963-12012 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Effective Reinforcement Learning Based on Structural Information Principles

arXiv

引用

arXiv 2024年

作者： Zeng, Xianghua Peng, Hao Su, Dingli Li, Angsheng State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing100191 China School of Cyber Science and Technology Beihang University Beijing100191 China

Although Reinforcement Learning (RL) algorithms acquire sequential behavioral patterns through interactions with the environment, their effectiveness in noisy and high-dimensional scenarios typically relies on specific structural priors. In this paper, we propose a novel and general Structural Information principles-based framework for effective Decision-Making, namely SIDM, approached from an information-theoretic perspective. This paper presents a specific unsupervised partitioning method that forms vertex communities in the state and action spaces based on their feature similarities. An aggregation function, which utilizes structural entropy as the vertex weight, is devised within each community to obtain its embedding, thereby facilitating hierarchical state and action abstractions. By extracting abstract elements from historical trajectories, a directed, weighted, homogeneous transition graph is constructed. The minimization of this graph’s high-dimensional entropy leads to the generation of an optimal encoding tree. An innovative two-layer skill-based learning mechanism is introduced to compute the common path entropy of each state transition as its identified probability, thereby obviating the requirement for expert knowledge. Moreover, SIDM can be flexibly incorporated into various single-agent and multi-agent RL algorithms, enhancing their performance. Finally, extensive evaluations on challenging benchmarks demonstrate that, compared with SOTA baselines, our framework significantly and consistently improves the policy’s quality, stability, and efficiency up to 32.70%, 88.26%, and 64.86%, respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Like an Ophthalmologist: Dynamic Selection Driven Multi-View Learning for Diabetic Retinopathy Grading 39

Like an Ophthalmologist: Dynamic Selection Driven Multi-View...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Luo, Xiaoling Xu, Qihao Wu, Huisi Liu, Chengliang Lai, Zhihui Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Key Laboratory of Visual Object Detection and Recognition Harbin Institute of Technology Shenzhen China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

ISBN: (纸本)157735897X

Diabetic retinopathy (DR), with its large patient population, has become a formidable threat to human visual health. In the clinical diagnosis of DR, multi-view fundus images are considered to be more suitable for DR diagnosis because of the wide coverage of the field of view. Therefore, different from the previous single-view DR grading methods, we design a dynamic selection-driven multi-view DR grading method to fit clinical scenarios better. Since lesion information plays a key role in DR diagnosis, previous methods usually boost the model performance by enhancing the lesion feature. However, during the actual diagnosis, ophthalmologists not only focus on the crucial parts, but also exclude irrelevant features to ensure the accuracy of judgment. To this end, we introduce the idea of dynamic selection and design a series of selection mechanisms from fine granularity to coarse granularity. In this work, we first introduce an Ophthalmic Image Reader (OIR) agent to provide the model with pixel-level prompts of suspected lesion areas. Moreover, we design a Multi-View Token Selection Module (MVTSM) that prunes redundant feature tokens and dynamically selects key information. In the final decision stage, we dynamically fuse multi-view features through the novel Multi-View Mixture of Experts Module (MVMoEM), to enhance key views and reduce the impact of conflicting views. Extensive experiments on a large multi-view fundus image dataset with 34,452 images prove that our method performs favorably against state-of-the-art models. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Knowledge-aware Multi-view Cross Learning for Edge-based Collaborative Recommendation

Knowledge-aware Multi-view Cross Learning for Edge-based Col...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Yang Dai Shunmei Meng Huanhuan Gu Nan Liu Longchuan Tu School of Cyberspace Security NanJing University of Science and Technology Nanjing China State Key Lab. for Novel Software Technology NanJing University Nanjing China Department of Computer Science and Engineering NanJing University of Science and Technology Nanjing China Nanjing Sinovatio Technology Co. Ltd. Nanjing China

In order to effectively overcome the sparsity and cold start challenges of collaborative filtering in actual scenarios, and provide more accurate suggestions, knowledge graphs are commonly utilized in recommender systems. Graph neural networks are increasingly used in knowledge graph-based recommender systems. Nevertheless, conventional recommender systems overlook the relationship information between items and entities as well as the sparse supervision signal, potentially leading to a decline in the actual recommendation performance. In this investigation, we propose KMCL, a Knowledge-aware Multi-view Cross-learning framework for edge-based collaborative recommendation. In contrast to the typical manner of dealing with knowledge graphs, our approach investigates three different graph views to improve users’ and items’ embedding representations, respectively. Firstly, the merged user-item KG graph is utilized to integrate the multi-hop neighbor information of each user, with the Graph Attention Network assigning various weights to different neighbors. Secondly, Graph Neural Network collects the top-x neighbor nodes for learning in the collaborative view of user-item graph and item-entity graph. Finally, a cross module is developed to share high-level information between embeddings with the same features. In addition, we also introduce the idea of edge computing, which preprocesses and calculates the locally obtained user preferences first, and then inputs them into different views to improve the recommendation efficiency. Experimental results demonstrate that KMCL delivers better suggestions than state-of-the-art baseline models in delivering superior recommendations. Furthermore, our approach maintains higher accuracy in predicting outcomes in less familiar interaction scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Migrant Resettlement by Evolutionary Multi-objective Optimization

arXiv

引用

arXiv 2023年

作者： Liu, Dan-Xuan Gu, Yu-Ran Qian, Chao Mu, Xin Tang, Ke National Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China School of Artificial Intelligence Nanjing University Nanjing210023 China Peng Cheng Laboratory Shenzhen518000 China Shenzhen Key Laboratory of Computational Intelligence Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China

Migration has been a universal phenomenon, which brings opportunities as well as challenges for global development. As the number of migrants (e.g., refugees) increases rapidly in recent years, a key challenge faced by each country is the problem of migrant resettlement. This problem has attracted scientific research attention, from the perspective of maximizing the employment rate. Previous works mainly formulated migrant resettlement as an approximately submodular optimization problem subject to multiple matroid constraints and employed the greedy algorithm, whose performance, however, may be limited due to its greedy nature. In this paper, we propose a new framework MR-EMO based on Evolutionary Multi-objective Optimization, which reformulates Migrant Resettlement as a bi-objective optimization problem that maximizes the expected number of employed migrants and minimizes the number of dispatched migrants simultaneously, and employs a Multi-Objective Evolutionary Algorithm (MOEA) to solve the bi-objective problem. We implement MR-EMO using three MOEAs, the popular NSGA-II, MOEA/D as well as the theoretically grounded GSEMO. To further improve the performance of MR-EMO, we propose a specific MOEA, called GSEMO-SR, using matrix-swap mutation and repair mechanism, which has a better ability to search for feasible solutions. We prove that MR-EMO using either GSEMO or GSEMO-SR can achieve better theoretical guarantees than the previous greedy algorithm. Experimental results under the interview and coordination migration models clearly show the superiority of MR-EMO (with either NSGA-II, MOEA/D, GSEMO or GSEMO-SR) over previous algorithms, and that using GSEMO-SR leads to the best performance of MR-EMO. Copyright © 2023, The Authors. All rights reserved.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Study on over Minimization for Nonnegative Signal Recovery

引用

Journal of Scientific Computing 2023年第3期95卷 1-24页

作者： Tao, Min Zhang, Xiao-Ping Department of Mathematics National Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Tsinghua-Berkeley Shenzhen Institute Tsinghua University Beijing China Department of Electrical Computer and Biomedical Engineering Toronto Metropolitan University Toronto Canada

In this paper, we carry out a comprehensive study for the unconstrained $$L_1$$ over $$L_2$$ sparsity promoting model, widely used in the regime of coherent dictionaries for recovering nonnegative sparse signals. First, we prove the existence of global solutions. Second, we analyze the sparse property of any local minimizer of the $$L_{1}/L_{2}$$ model. This property serves as a certificate to rule out the nonlocal minimizers. Third, we focus on algorithmic development on the unconstrained model with nonnegative constraint. We derive an analytical solution for the proximal operator of the $$L_{1} / L_{2}$$ with nonnegative constraint. Then, we apply the alternating direction method of multipliers in a particular splitting way, referred to as ADMM $$_p^+$$ . We establish its global convergence to a d-stationary solution (sharpest stationary) by verifying the Lyapunov function with the Kurdyka-Łojasiewicz property instead of imposing. Extensive numerical simulations confirm the superiority of ADMM $$_p^+$$ over the existing state-of-the-art methods in nonnegative sparse recovery.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Locating Framework-specific Crashing Faults with Compact and Explainable Candidate Set

Locating Framework-specific Crashing Faults with Compact and...

引用

International Conference on software Engineering (ICSE)

作者： Jiwei Yan Miaomiao Wang Yepang Liu Jun Yan Long Zhang Technology Center of Software Engineering Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China

Nowadays, many applications do not exist independently but rely on various frameworks or libraries. The frequent evolution and the complex implementation of framework APIs induce lots of unexpected post-release crashes. Starting from the crash stack traces, existing approaches either perform application-level call graph (CG) tracing or construct datasets with similar crash-fixing records to locate buggy methods. However, these approaches are limited by the completeness of CG or dependent on historical fixing records, and some of them only focus on specific manually modeled exception types. To achieve effective debugging on complex framework-specific crashes, we propose a code-separation-based locating approach that weakly relies on CG tracing and does not require any prior knowledge. Our key insight is that one crash trace with the description message can be mapped to a definite exception-thrown point in the framework, the semantics analysis of which can help to figure out the root causes of the crash-triggering procedure. Thus, we can pre-construct reusable summaries for all the framework-specific exceptions to support fault localization in application code. Based on that idea, we design the exception-thrown summary (ETS) that describes both the key variables and key APIs related to the exception triggering. Then, we perform static analysis to automatically compute such summaries and make a data-tracking of key variables and APIs in the application code to get the ranked buggy candidates. In the scenario of locating Android framework-specific crashing faults, our tool CrashTracker exhibited an overall MRR value of 0.91 and outperforms the state-of-the-art tool Anchor with higher precision. It only provides a compact candidate set and gives user-friendly reports with explainable reasons for each candidate.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bedrock Models in Communication and Sensing: Advancing Generalization, Transferability, and Performance

arXiv

引用

arXiv 2025年

作者： Luo, Cheng Xiang, Luping Hu, Jie Yang, Kun The School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu611731 China The State Key Laboratory of Novel Software Technology Nanjing University Nanjing210008 China School of Intelligent Software and Engineering Nanjing University Suzhou Campus Suzhou China The School of Computer Science and Electronic Engineering University of Essex ColchesterCO4 3SQ United Kingdom

Deep learning (DL) has emerged as a powerful tool for addressing the intricate challenges inherent in communication and sensing systems, significantly enhancing the intelligence of future sixth-generation (6G) networks. A substantial body of research has highlighted the promise of DL-based techniques in these domains. However, in addition to improving accuracy, new challenges must be addressed regarding the generalization and transferability of DL-based systems. To tackle these issues, this paper introduces a series of mathematically grounded and modularized models, referred to as bedrock models, specifically designed for integration into both communication and sensing systems. Due to their modular architecture, these models can be seamlessly incorporated into existing communication and sensing frameworks. For communication systems, the proposed models demonstrate substantial performance improvements while also exhibit strong transferability, enabling direct parameter sharing across different tasks, which greatly facilitates practical deployment. In sensing applications, the integration of the bedrock models into existing systems results in superior performance, reducing delay and Doppler estimation errors by an order of magnitude compared to traditional methods. Additionally, a pre-equalization strategy based on the bedrock models is proposed for the transmitter. By leveraging sensing information, the transmitted communication signal is dynamically adjusted without altering the communication model pre-trained in AWGN channels. This adaptation enables the system to effectively cope with doubly dispersive channels, restoring the received signal to an AWGN-like condition and achieving near-optimal performance. Simulation results substantiate the effectiveness and transferability of the proposed bedrock models, underscoring their potential to advance both communication and sensing systems. Copyright © 2025, The Authors. All rights reserved.

关键词： Deep learning

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：