检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Liang, Jiaxuan Wang, Jun Yu, Guoxian Xia, Shuyin Wang, Guoyin School of Software Shandong University Jinan China SDU-NTU Joint Centre for AI Research Shandong University Jinan China Chongqing Key Laboratory of Computational Intelligence Chongqing Uni. of Posts and Telecom. Chongqing China MOE Key Laboratory of Big Data Intelligent Computing Chongqing Uni. of Posts and Telecom. Chongqing China

Unveil, model, and comprehend the causal mechanisms underpinning natural phenomena stand as fundamental endeavors across myriad scientific disciplines. Meanwhile, new knowledge emerges when discovering causal relationships from data. Existing causal learning algorithms predominantly focus on the isolated effects of variables, overlook the intricate interplay of multiple variables and their collective behavioral patterns. Furthermore, the ubiquity of high-dimensional data exacts a substantial temporal cost for causal algorithms. In this paper, we develop a novel method called MgCSL (Multi-granularity Causal Structure Learning), which first leverages sparse auto-encoder to explore coarse-graining strategies and causal abstractions from micro-variables to macro-ones. MgCSL then takes multi-granularity variables as inputs to train multilayer perceptrons and to delve the causality between variables. To enhance the efficacy on high-dimensional data, MgCSL introduces a simplified acyclicity constraint to adeptly search the directed acyclic graph among variables. Experimental results show that MgCSL outperforms competitive baselines, and finds out explainable causal connections on fMRI datasets. Copyright © 2023, The Authors. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Accurate Latent Factor Analysis via Particle Swarm Optimizers

Accurate Latent Factor Analysis via Particle Swarm Optimizer...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Jia Chen Xin Luo MengChu Zhou School of Cyber Science and Technology Beihang University Beijing China Chongqing Key Lab. of Big Data and Intelligent Computing and the Chongqing Engineering Research Center of Big Data Application for Smart Cities Chongqing Institute of Green and Intelligent Technology Chongqing School University of Chinese Academy of Sciences Chongqing China New Jersey Institute of Technology Newark NJ USA

ISBN: (纸本)9781665442084

A stochastic-gradient-descent-based Latent Factor Analysis (LFA) model is highly efficient in representative learning of a High-Dimensional and Sparse (HiDS) matrix. Its learning rate adaptation is vital in ensuring its efficiency. Such adaptation can be realized with an evolutionary computing algorithm. However, a resultant model tends to suffer from two issues: a) the pre-mature convergence of the swarm of learning rates as caused by an adopted evolution algorithm, and b) the pre-mature convergence of the LFA model as caused jointly by evolution-based learning rate adaptation and an optimization algorithm. This paper focuses on the methods to address such issues. A Hierarchical Particle-swarm-optimization-incorporated Latent factor analysis (HPL) model with a two-layered structure is proposed, where the first layer pre-trains desired latent factors with a position-transitional particle-swarm-optimization-based LFA model, and the second layer performs latent factor refining with a newly-proposed mini-batch particle swarm optimizer. With such design, an HPL model can well handle the pre-mature convergence, which is supported by the positive experimental results achieved on HiDS matrices from industrial applications.

关键词： Adaptation models Analytical models Computational modeling Refining Predictive models Sparse matrices Particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

D4M: dataset Distillation via Disentangled Diffusion Model

arXiv

引用

arXiv 2024年

作者： Su, Duo Hou, Junjie Gao, Weizhi Tian, Yingjie Tang, Bowen School of Computer Science and Technology UCAS United Kingdom Sino-Danish College UCAS United Kingdom Department of Computer Science NCSU United States School of Economics and Management UCAS United Kingdom Research Center on Fictitious Economy and Data Science CAS China Key Laboratory of Big Data Mining and Knowledge Management CAS China MOE Social Science Laboratory of Digital Economic Forecasts and Policy Simulation UCAS United Kingdom Institute of Computing Technology CAS China

dataset distillation offers a lightweight synthetic dataset for fast network training with promising test accuracy. To imitate the performance of the original dataset, most approaches employ bi-level optimization and the distillation space relies on the matching architecture. Nevertheless, these approaches either suffer significant computational costs on large-scale datasets or experience performance decline on cross-architectures. We advocate for designing an economical dataset distillation framework that is independent of the matching architectures. With empirical observations, we argue that constraining the consistency of the real and synthetic image spaces will enhance the cross-architecture generalization. Motivated by this, we introduce dataset Distillation via Disentangled Diffusion Model (D4M), an efficient framework for dataset distillation. Compared to architecture-dependent methods, D4M employs latent diffusion model to guarantee consistency and incorporates label information into category prototypes. The distilled datasets are versatile, eliminating the need for repeated generation of distinct datasets for various architectures. Through comprehensive experiments, D4M demonstrates superior performance and robust generalization, surpassing the SOTA methods across most aspects. Copyright © 2024, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Programming Variational Quantum Circuits with Quantum-Train Agent

Programming Variational Quantum Circuits with Quantum-Train ...

引用

Quantum Communications, Networking, and computing (QCNC), International Conference on

作者： Chen-Yu Liu Samuel Yen-Chi Chen Kuan-Cheng Chen Wei-Jia Huang Yen-Jui Chang Graduate Institute of Applied Physics National Taiwan University Taipei Taiwan Hon Hai (Foxconn) Research Institute Taipei Taiwan Wells Fargo New York NY USA Department of Electrical and Electronic Engineering Imperial College London London UK Centre for Quantum Engineering Science and Technology (QuEST) Imperial College London London UK Quantum Information Center Chung Yuan Christian University Taoyuan City Taiwan Master Program in Intelligent Computing and Big Data Chung Yuan Christian University Taoyuan City Taiwan

ISBN: (数字)9798331531591

ISBN: (纸本)9798331531607

This study introduces the Quantum-Train Quantum Fast Weight Programmer (QT-QFWP) framework, enabling efficient and scalable programming of variational quantum circuits (VQCs) through quantum-driven parameter updates for the classical slow programmer controlling the fast programmer VQC. By optimizing quantum and classical parameter management, QT-QFWP significantly reduces parameters (by 70–90%) compared to Quantum Long Short-Term Memory (QLSTM) and Quantum Fast Weight Programmer (QFWP) while maintaining accuracy. Benchmarking on time-series tasks—including Damped Simple Harmonic Motion (SHM), NARMA5, and Simulated Gravitational Waves (GW)—demonstrates superior efficiency and predictive accuracy. QT-QFWP is particularly advantageous for near-term quantum systems, addressing qubit and gate fidelity constraints, enhancing VQC deployment in time-sensitive applications, and expanding quantum computing’s role in machine learning.

关键词： Quantum system Accuracy Computational modeling Qubit Neural networks Programming Predictive models Quantum circuit Physics Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Interpretable text-to-sql generation with joint optimization 1

引用

17th International Conference on Web Information Systems and Applications, WISA 2020

作者： Zhu, Mingdong Wang, Xianfang Zhang, Yang School of Computer Science and Technology Henan Institute of Technology Xinxiang China Intelligent Industrial Big Data Application Engineering Technology Research Center of Xinxiang Xinxiang China

ISBN: (数字)9783030600297

ISBN: (纸本)9783030600280

The purpose of Text-to-SQL is to obtain the correct answer for a textual question from the database, which can take advantage of advanced database system to provide reliable and efficient response. Existing Text-to-SQL methods generally focus on accuracy by designing complex deep neural network models, and hardly consider interpretability, which is very important for serious applications. To address this, in this paper we propose a novel framework for Interpretable Text-to-SQL Generation (ITSG) with joint optimization, which achieves state-of-the-art accuracy and possesses two-level interpretability at the same time. The framework mainly consists of three layers: a sequence encoder which encodes questions, table headers and significant table contents, an attention-based LSTM layer which generates SQL queries and a reinforcement learning layer which boosts the execution accuracy. Comparing with state-of-the-art methods on benchmark datasets, the experimental results show the effectiveness and interpretability of our ITSG framework. © Springer Nature Switzerland AG 2020.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

FlashWalker: An In-Storage Accelerator for Graph Random Walks

FlashWalker: An In-Storage Accelerator for Graph Random Walk...

引用

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： Fuping Niu Jianhui Yue Jiangqiu Shen Xiaofei Liao Haikun Liu 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 Department of Computer Science Michigan Technological University Houghton Michigan USA

Graph random walk is widely used in the graph processing as it is a fundamental component in graph analysis, ranging from vertices ranking to the graph embedding. Different from traditional graph processing workload, random walk features massive processing parallelisms and poor graph data reuse, being limited by low I/O efficiency. Prior designs for random walk mitigate slow I/O operations. However, the state-of-the-art random walk processing systems are bounded by slow disk I/O bandwidth, which is confirmed by our experiments with real-world graphs. To address this issue, we propose FlashWalker, an in-storage accelerator for random walk that moves walk updating close to graph data stored in flash memory, by exploiting significant parallelisms inside SSD. Featuring a heterogeneous and parallel processing system, FlashWalker includes a board-level accelerator, channel-level accelerators, and chip-level accelerators. To address challenges posed by the tight resource constraints for processing large-scale graphs, we propose novel designs: storing a few popular subgraphs in accelerators, the pre-walking for dense walks, two optimizations to search the subgraph mapping table, and a subgraph scheduling algorithm. We implement FlashWalker in RTL, showing small circuit area overhead. Our evaluation shows FlashWalker reduces the execution time of random walk algorithms by up to 660.50×, compared with GraphWalker, which is the state-of-the-art system for random walk algorithms.

关键词： Distributed processing Scheduling algorithms Bandwidth Parallel processing Distance measurement Flash memories Optimization

来源：评论

学校读者我要写书评

暂无评论

A large model method for fine-tuning segmentation of all abdominal tumors based on the AdaLoRA approach

A large model method for fine-tuning segmentation of all abd...

引用

IEEE International Conference on Signal and Image Processing (ICSIP)

作者： Hongliang Wang Hu Li Lijun Fu Xiaozhou Liu Jing Xu Shenyang Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Liaoning Province Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China Shandong University Big Data Technology and Cognitive Intelligence Laboratory University of Chinese Academy of Sciences Shenyang China Stomatological Hospital Affiliated to China Medical University Shenyang China

ISBN: (数字)9798350350920

ISBN: (纸本)9798350350937

Medical image segmentation is an important task in the field of medical image processing, and deep learning-based methods have made significant progress in this area. However, traditional segmentation models have limitations when dealing with complex and diverse medical images, and they lack interactivity. To overcome these limitations, the SAM adapter is introduced into the SAM algorithm to provide greater flexibility and scalability. We also introduce an object detection interactive algorithm to enhance the interactivity of the model. The SAM adapter allows for customized model adjustments to adapt to different medical image segmentation tasks and datasets. By finetuning the SAM adapter using the AdaLORA method, we propose the AdaSAMed algorithm, which enables researchers to conveniently develop adaptive and accurate segmentation models, thus promoting further advancement in medical image segmentation of gastrointestinal tumors.

关键词： Learning systems Image segmentation Adaptation models Scalability Object detection Robustness Gastrointestinal tract

来源：评论

学校读者我要写书评

暂无评论

CellAgent: An LLM-driven Multi-Agent Framework for Automated Single-cell data Analysis

arXiv

引用

arXiv 2024年

作者： Xiao, Yihang Liu, Jinyi Zheng, Yan Xie, Xiaohan Hao, Jianye Li, Mingzhi Wang, Ruitao Ni, Fei Li, Yuxiao Luo, Jintian Jiao, Shaoqing Peng, Jiajie AI for Science Interdisciplinary Research Center School of Computer Science Northwestern Polytechnical University No.1 Dongxiang Road Xi’an China College of Intelligence and Computing Tianjin University No.92 Weijin Road Tianjin China Key Laboratory of Big Data Storage and Management Northwestern Polytechnical University Ministry of Industry and Information Technology No.1 Dongxiang Road Xi’an China

Single-cell RNA sequencing (scRNA-seq) data analysis is crucial for biological research, as it enables the precise characterization of cellular heterogeneity. However, manual manipulation of various tools to achieve desired outcomes can be labor-intensive for researchers. To address this, we introduce CellAgent (http://***/), an LLM-driven multi-agent framework, specifically designed for the automatic processing and execution of scRNA-seq data analysis tasks, providing high-quality results with no human intervention. Firstly, to adapt general LLMs to the biological field, CellAgent constructs LLM-driven biological expert roles—planner, executor, and evaluator—each with specific responsibilities. Then, CellAgent introduces a hierarchical decision-making mechanism to coordinate these biological experts, effectively driving the planning and step-by-step execution of complex data analysis tasks. Furthermore, we propose a self-iterative optimization mechanism, enabling CellAgent to autonomously evaluate and optimize solutions, thereby guaranteeing output quality. We evaluate CellAgent on a comprehensive benchmark dataset encompassing dozens of tissues and hundreds of distinct cell types. Evaluation results consistently show that CellAgent effectively identifies the most suitable tools and hyperparameters for single-cell analysis tasks, achieving optimal performance. This automated framework dramatically reduces the workload for science data analyses, bringing us into the "Agent for Science" era. Copyright © 2024, The Authors. All rights reserved.

关键词： Cells

来源：评论

学校读者我要写书评

暂无评论

I4R: Promoting deep reinforcement learning by the indicator for expressive representations 29

I4R: Promoting deep reinforcement learning by the indicator ...

引用

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Luo, Xufang Meng, Qi He, Di Chen, Wei Wang, Yunhong Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China Microsoft Research Beijing China School of EECS Peking University China

ISBN: (纸本)9780999241165

Learning expressive representations is always crucial for well-performed policies in deep reinforcement learning (DRL). Different from supervised learning, in DRL, accurate targets are not always available, and some inputs with different actions only have tiny differences, which stimulates the demand for learning expressive representations. In this paper, firstly, we empirically compare the representations of DRL models with different performances. We observe that the representations of a better state extractor (SE) are more scattered than a worse one when they are visualized. Thus, we investigate the singular values of representation matrix, and find that, better SEs always correspond to smaller differences among these singular values. Next, based on such observations, we define an indicator of the representations for DRL model, which is the Number of Significant Singular Values (NSSV) of a representation matrix. Then, we propose I4R algorithm, to improve DRL algorithms by adding the corresponding regularization term to enhance the NSSV. Finally, we apply I4R to both policy gradient and value based algorithms on Atari games, and the results show the superiority of our proposed method.1,. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

DAGAD: data Augmentation for Graph Anomaly Detection

DAGAD: Data Augmentation for Graph Anomaly Detection

引用

IEEE International Conference on data Mining (ICDM)

作者： Fanzhen Liu Xiaoxiao Ma Jia Wu Jian Yang Shan Xue Amin Beheshti Chuan Zhou Hao Peng Quan Z. Sheng Charu C. Aggarwal School of Computing Macquarie University Sydney Australia School of Computing and Information Technology University of Wollongong Wollongong Australia Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China IBM T. J. Watson Research Center Yorktown NY USA

Graph anomaly detection in this paper aims to distinguish abnormal nodes that behave differently from the benign ones accounting for the majority of graph-structured instances. Receiving increasing attention from both academia and industry, yet existing research on this task still suffers from two critical issues when learning informative anomalous behavior from graph data. For one thing, anomalies are usually hard to capture because of their subtle abnormal behavior and the shortage of background knowledge about them, which causes severe anomalous sample scarcity. Meanwhile, the overwhelming majority of objects in real-world graphs are normal, bringing the class imbalance problem as well. To bridge the gaps, this paper devises a novel data Augmentation-based Graph Anomaly Detection (DAGAD) framework for attributed graphs, equipped with three specially designed modules: 1) an information fusion module employing graph neural network encoders to learn representations, 2) a graph data augmentation module that fertilizes the training set with generated samples, and 3) an imbalance-tailored learning module to discriminate the distributions of the minority (anomalous) and majority (normal) classes. A series of experiments on three datasets prove that DAGAD outperforms ten state-of-the-art baseline detectors concerning various mostly-used metrics, together with an extensive ablation study validating the strength of our proposed modules.

关键词： Measurement Training Industries Sensitivity analysis Blogs Detectors Graph neural networks

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：