检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is available at this url. © 2024, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Learning Unified Embeddings for Recommendation via Meta-path Semantics 21

Learning Unified Embeddings for Recommendation via Meta-path...

引用

29th ACM International Conference on Multimedia, MM 2021

作者： Hao, Qianxiu Xu, Qianqian Yang, Zhiyong Huang, Qingming 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 Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China Artificial Intelligence Research Center Peng Cheng Laboratory Shenzhen China

ISBN: (纸本)9781450386517

Heterogeneous information networks (HINs) have become a popular tool to capture complicated user-item relationships in recommendation problems in recent years. As a typical instantiation of HINs, meta-path is introduced in search of higher-level representations of user-item interactions. Though remarkable success has been achieved along this direction, existing meta-path-based recommendation methods face at least one of the following issues: 1) existing methods merely adopt simple meta-path fusion rules, which might be insufficient to exclude inconsistent information of different meta-paths that may hurt model performance;2) the representative power is limited by shallow/stage-wise formulations. To solve these issues, we propose an end-to-end and unified embedding-based recommendation framework with graph-based learning. To address 1), we propose a flexible fusion module to integrate meta-path-based similarities into relative similarities between users and items. To address 2), we take advantage of the powerful representative ability of deep neural networks to learn more complicated and flexible latent embeddings. Finally, empirical studies on real-world datasets demonstrate the effectiveness of our proposed method. © 2021 ACM.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques

arXiv

引用

arXiv 2024年

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Yang, Zhiyong Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China School of Cyber Science and Tech. Sun Yat-sen University Shenzhen Campus China

Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We discover that diffusion feature has been hindered by a hidden yet universal phenomenon that we call content shift. To be specific, there are content differences between features and the input image, such as the exact shape of a certain object. We locate the cause of content shift as one inherent characteristic of diffusion models, which suggests the broad existence of this phenomenon in diffusion feature. Further empirical study also indicates that its negative impact is not negligible even when content shift is not visually perceivable. Hence, we propose to suppress content shift to enhance the overall quality of diffusion features. Specifically, content shift is related to the information drift during the process of recovering an image from the noisy input, pointing out the possibility of turning off-the-shelf generation techniques into tools for content shift suppression. We further propose a practical guideline named GATE to efficiently evaluate the potential benefit of a technique and provide an implementation of our methodology. Despite the simplicity, the proposed approach has achieved superior results on various tasks and datasets, validating its potential as a generic booster for diffusion features. Our code is available at this url. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

computing optimal partition problems via Lagrange multiplier approach

arXiv

引用

arXiv 2024年

作者： Cheng, Qing Guo, Jing Wang, Dong Department of Mathematics Tongji University Shanghai200092 China Key Laboratory of Intelligent Computing and Applications Tongji University Ministry of Education China School of Science and Engineering The Chinese University of Hong Kong Guangdong Shenzhen518172 China Shenzhen International Center for Industrial and Applied Mathematics Shenzhen Research Institute of Big Data Guangdong518172 China

In this paper, we consider numerical approximations for the optimal partition problem using Lagrange multipliers. By rewriting it into constrained gradient flows, three and four steps numerical schemes based on the Lagrange multiplier approach [16, 17] are proposed to solve the constrained gradient system. Numerical schemes proposed for the constrained gradient flows satisfy the nice properties of orthogonality-preserving, norm-preserving, positivity-preserving and energy dissipating. The proposed schemes are very efficient in which only linear Poisson equations are solved at each time step. Extensive numerical results in 2D and 3D for optimal partition problem are presented to validate the effectiveness and accuracy of the proposed numerical schemes. Copyright © 2024, The Authors. All rights reserved.

关键词： Lagrange multipliers

来源：评论

学校读者我要写书评

暂无评论

Multi-granularity Causal Structure Learning

arXiv

引用

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

Dual-Stream Fusion Network With Multi-Head Self-Attention for Multi-Modal Fake News Detection

SSRN

引用

SSRN 2024年

作者： Yang, Yimei Liu, Jinping Yang, Yujun Cen, Lihui School of Mathematics and Statistics Hunan Normal University Changsha410081 China Huaihua University Hunan Huaihua418000 China College of Information Science and Engineering Hunan Normal University Changsha China School of Automation Central South University Changsha410083 China Key Laboratory of Wuling-Mountain Health Big Data Intelligent Processing Application in Hunan Province Universities Hunan Huaihua418000 China Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Hunan Huaihua418000 China

With the rapid development of social media platforms such as Weibo, WeChat, and other new media, as well as the rise of deepfake technologies, the identification and containment of fake information have posed significant challenges, becoming one of the key challenges faced by society and governmental institutions. Therefore, the development of intelligent and efficient methods for detecting fake news has become a top priority in combating misinformation. Addressing challenges in current fake news detection techniques, such as cross-lingual issues, data imbalance, and multimodal information fusion, this paper aims to propose a dual-stream fusion network model (DSF-MHSA) based on deep learning for detecting fake news across web pages, images, and text. The model combines the deep learning models ERNIE-M, AlexNet, ShuffleNet, and three multi-head self-attention mechanisms to extract and classify features from multilingual text and images. By utilizing two separate multi-head self-attention mechanisms to process extracted textual and image information, the model captures long-range dependencies among texts to better understand contextual information and captures global information among images to enhance object recognition and localization capabilities. Finally, a single multi-head self-attention mechanism is employed to integrate textual and image information to capture cross-modal correlations, thereby strengthening the model's understanding and identification capabilities of news content. This dual-stream fusion network architecture ensures the model's ability to detect multimodal news scenarios in both English and Chinese short texts and images. Experimental evaluations conducted on three publicly available datasets - Twitter, Weibo, and IKCEST-2023 dataset, which contains real online news data collected from domestic and international social media platforms - demonstrate superior performance of the proposed model in news detection tasks, achieving an accuracy rate

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

A Survey of Route Recommendations: Methods, Applications, and Opportunities

arXiv

引用

arXiv 2024年

作者： Zhang, Shiming Luo, Zhipeng Yang, Li Teng, Fei Li, Tianrui School of Computing and Artificial Intelligence Southwest Jiaotong University China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Sichuan Chengdu611756 China

Nowadays, with advanced information technologies deployed citywide, large data volumes and powerful computational resources are intelligentizing modern city development. As an important part of intelligent transportation, route recommendation and its applications are widely used, directly influencing citizens' travel habits. Developing smart and efficient travel routes based on big data (possibly multi-modal) has become a central challenge in route recommendation research. Our survey offers a comprehensive review of route recommendation work based on urban computing. It is organized by the following three parts: 1) Methodology-wise. We categorize a large volume of classic methods and modern deep learning methods. Also, we discuss their historical relations and reveal the edge-cutting progress. 2) Application-wise. We present numerous novel applications related to route commendation within urban computing scenarios. 3) We discuss current problems and challenges and envision several promising research directions. We believe that this survey can help relevant researchers quickly familiarize themselves with the current state of route recommendation research and then direct them to future research trends. Copyright © 2024, 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

a branch-and-price approach for the nurse rostering problem with multiple units

arXiv

引用

arXiv 2023年

作者： Hu, Wanzhe He, Xiaozhou Luo, Li Pardalos, Panos M. School of Economics and Management Chongqing University of Posts and Telecommunications Chongqing China Business School Sichuan University Sichuan Chengdu China Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and Telecommunications Chongqing China Department of Industrial and Systems Engineering Center for Applied Optimization University of Florida Gainesville United States

In this paper, we study the nurse rostering problem that considers multiple units and many soft time-related constraints. An efficient branch and price solution approach that relies on a fast algorithm to solve the pricing subproblem of the column generation process is presented. For the nurse rostering problem, its pricing subproblem can be formulated as a shortest path problem with resource constraints, which has been the backbone of several solutions for several classical problems like vehicle routing problems. However, approaches that perform well on these problems cannot be used since most constraints in the nurse rostering problem are soft. Based on ideas borrowed from global constraints in constraint programming to model rostering problems, an efficient dynamic programming algorithm with novel label definitions and dominating rules specific to soft time-related constraints is proposed. In addition, several acceleration strategies are employed to improve the branch and price algorithm. Computational results on instances of different sizes indicate that the proposed algorithm is a promising solution for the nurse rostering problem with multiple units. Copyright © 2023, The Authors. All rights reserved.

关键词： Constraint programming

来源：评论

学校读者我要写书评

暂无评论

ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Detection

arXiv

引用

arXiv 2023年

作者： He, Junwei Xu, Qianqian Jiang, Yangbangyan Wang, Zitai Huang, Qingming 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 Institute of Information Engineering CAS Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

Graph anomaly detection is crucial for identifying nodes that deviate from regular behavior within graphs, benefiting various domains such as fraud detection and social network. Although existing reconstruction-based methods have achieved considerable success, they may face the Anomaly Overfitting and Homophily Trap problems caused by the abnormal patterns in the graph, breaking the assumption that normal nodes are often better reconstructed than abnormal ones. Our observations indicate that models trained on graphs with fewer anomalies exhibit higher detection performance. Based on this insight, we introduce a novel two-stage framework called Anomaly-Denoised Autoencoders for Graph Anomaly Detection (ADA-GAD). In the first stage, we design a learning-free anomaly-denoised augmentation method to generate graphs with reduced anomaly levels. We pretrain graph autoencoders on these augmented graphs at multiple levels, which enables the graph autoencoders to capture normal patterns. In the next stage, the decoders are retrained for detection on the original graph, benefiting from the multi-level representations learned in the previous stage. Meanwhile, we propose the node anomaly distribution regularization to further alleviate Anomaly Overfitting. We validate the effectiveness of our approach through extensive experiments on both synthetic and real-world datasets. Copyright © 2023, The Authors. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Transition in collective motion decision making

引用

Physical Review E 2022年第1期106卷 014611-014611页

作者： Biao Wang Yue Wu Guangwei Wang Lan Liu Guanrong Chen Hai-Tao Zhang School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control State Key Laboratory of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan 430074 China National Engineering Laboratory for Educational Big Data Central China Normal University Wuhan 430079 China Department of Electrical Engineering City University of Hong Kong Hong Kong SAR China

Collective decision making in a biological motion group requires fast and robust transmission of information. Typically, directional switching information propagation across the whole group obeys a linear dispersion law. However, conventional dynamic collective motion models, such as the Vicsek model and the Couzin model did not take into account ultrafast directional synchronous motions. In the present paper, a multiparticle model is proposed based on inertial spin self-propel action, which can provide adequate description of such group motion. By considering both spin mechanism and collision avoidance, the proposed self-propelled particle spin model can nicely describe collective motion with fast directional switching. By analyzing the order parameter of the group-velocity synchronization, a mechanism of group decision making is revealed, which is based on the difference between two clusters of divergent leaders, showing a transition from the compromising phase (i.e., following the group average) to the preferred phase (i.e., aligning to a leader cluster). The finding provides new insight to the decision-making process of followers when they face with divergent leaders in group motion.

关键词： Collective behavior in networks Network phase transitions Pattern formation Self-organized systems

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：