检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Xia, Shuyin Shi, Bolun Wang, Yifan Xie, Jiang Wang, Guoyin Gao, Xinbo Chongqing Key Laboratory of Computational Intelligence The Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education The Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and Telecommunications Chongqing400065 China

Traditional clustering algorithms often focus on the most fine-grained information and achieve clustering by calculating the distance between each pair of data points or implementing other calculations based on points. This way is not inconsistent with the cognitive mechanism of "global precedence" in human brain, resulting in those methods’ bad performance in efficiency, generalization ability and robustness. To address this problem, we propose a new clustering algorithm called granular-ball clustering (GBCT) via granular-ball computing. Firstly, GBCT generates a smaller number of granular-balls to represent the original data, and forms clusters according to the relationship between granular-balls, instead of the traditional point relationship. At the same time, its coarse-grained characteristics are not susceptible to noise, and the algorithm is efficient and robust;besides, as granular-balls can fit various complex data, GBCT performs much better in non-spherical data sets than other traditional clustering methods. The completely new coarse granularity representation method of GBCT and cluster formation mode can also used to improve other traditional methods. All codes can be available from the following link. Copyright © 2024, The Authors. All rights reserved.

关键词： Granular computing

来源：评论

学校读者我要写书评

暂无评论

Knowledge Circuits in Pretrained Transformers

arXiv

引用

arXiv 2024年

作者： Yao, Yunzhi Zhang, Ningyu Xi, Zekun Wang, Mengru Xu, Ziwen Deng, Shumin Chen, Huajun Zhejiang University China National University of Singapore NUS-NCS Joint Lab Singapore Zhejiang Key Laboratory of Big Data Intelligent Computing China

The remarkable capabilities of modern large language models are rooted in their vast repositories of knowledge encoded within their parameters, enabling them to perceive the world and engage in reasoning. The inner workings of how these models store knowledge have long been a subject of intense interest and investigation among researchers. To date, most studies have concentrated on isolated components within these models, such as the Multilayer Perceptrons and attention head. In this paper, we delve into the computation graph of the language model to uncover the knowledge circuits that are instrumental in articulating specific knowledge. The experiments, conducted with GPT2 and TinyLLAMA, have allowed us to observe how certain information heads, relation heads, and Multilayer Perceptrons collaboratively encode knowledge within the model. Moreover, we evaluate the impact of current knowledge editing techniques on these knowledge circuits, providing deeper insights into the functioning and constraints of these editing methodologies. Finally, we utilize knowledge circuits to analyze and interpret language model behaviors such as hallucinations and in-context learning. We believe the knowledge circuits hold potential for advancing our understanding of Transformers and guiding the improved design of knowledge editing1 Copyright © 2024, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Prior Semantic-Embedding Representation Learning for On-the-Fly

SSRN

引用

SSRN 2024年

作者： Liu, Yingge Dai, Dawei Zhou, Kenan Tan, Xiufang Wu, Yiqiao Wang, Guoyin Chongqing Key Laboratory of Computational Intelligence Key Laboratory of Big Data Intelligent Computing Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing University of Posts and Telecommunications Chongqing400065 China

In the context of fine-grained sketch-based image retrieval (FG-SBIR) framework, sketch drawing is a time-consuming and skill-intensive process that greatly restricts its practical application. Our study aims to enhance the early-stage retrieval efficiency by utilizing partial sketches with a minimum number of strokes in the on-the-fly FG-SBIR framework. Nevertheless, partial sketches with few strokes usually lack global information and consist only of sparse local details. This lack of detail results in ambiguous semantic content and indistinct differences among images, which consequently impairs early-stage retrieval. To acquire an efficient representation for these sketches, we propose a multi-granularity feature representation model that utilizes prior knowledge embedding to deal with the sketch drawing process. In the first stage,we design a triplet network to learn the joint a coarse representation embedding space that is common between the complete sketch and the image. In the second stage, We enhanced the semantic representation of sketches by utilizing prior knowledge, which aids in supplementing missing fine-grained features. This was achieved by formalizing the prior knowledge and integrating it into the feature vector obtained in the initial stage, thereby acquiring the final representation of a subset of sketches. Experiments conducted on two public datasets indicate that our method outperforms the state-of-the-art baseline during the early retrieval phase. In practical applications, our approach has also achieved good results. © 2024, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Granular-ball Representation Learning for Deep CNN on Learning with Label Noise

arXiv

引用

arXiv 2024年

作者： Dai, Dawei Zhu, Hao Xia, Shuyin Wang, Guoyin Chongqing Key Laboratory of Computational Intelligence Key Laboratory of Big Data Intelligent Computing Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing University of Posts and Telecommunications Chongqing400065 China

In actual scenarios, whether manually or automatically annotated, label noise is inevitably generated in the training data, which can affect the effectiveness of deep CNN models. The popular solutions require data cleaning or designing additional optimizations to punish the data with mislabeled data, thereby enhancing the robustness of models. However, these methods come at the cost of weakening or even losing some data during the training process. As we know, content is the inherent attribute of an image that does not change with changes in annotations. In this study, we propose a general granular-ball computing (GBC) module that can be embedded into a CNN model, where the classifier finally predicts the label of granular-ball (gb) samples instead of each individual samples. Specifically, considering the classification task: (1) in forward process, we split the input samples as gb samples at feature-level, each of which can correspond to multiple samples with varying numbers and share one single label;(2) during the backpropagation process, we modify the gradient allocation strategy of the GBC module to enable it to propagate normally;and (3) we develop an experience replay policy to ensure the stability of the training process. Experiments demonstrate that the proposed method can improve the robustness of CNN models with no additional data or optimization. Copyright © 2024, The Authors. All rights reserved.

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

Scale‐wise interaction fusion and knowledge distillation network for aerial scene recognition

引用

CAAI Transactions on Intelligence Technology 2023年第4期8卷 1178-1190页

作者： Hailong Ning Tao Lei Mengyuan An Hao Sun Zhanxuan Hu Asoke K.Nandi School of Computer Science and Technology Xi'an University of Posts and TelecommunicationsShaanxi Key Laboratory of Network Data Analysis and Intelligent ProcessingXi'anChina Xi'an Key Laboratory of Big Data and Intelligent Computing Xi'anChina School of Electronic Information and Artificial Intelligence Shaanxi University of Science and TechnologyXi'anChina School of Computer Central China Normal UniversityWuhanChina Department of Electronic and Electrical Engineering Brunel University LondonLondonUK Xi'an Jiaotong University Xi'anChina

Aerial scene recognition(ASR)has attracted great attention due to its increasingly essential *** of the ASR methods adopt the multi‐scale architecture because both global and local features play great roles in ***,the existing multi‐scale methods neglect the effective interactions among different scales and various spatial locations when fusing global and local features,leading to a limited ability to deal with challenges of large‐scale variation and complex background in aerial scene *** addition,existing methods may suffer from poor generalisations due to millions of to‐belearnt parameters and inconsistent predictions between global and local *** tackle these problems,this study proposes a scale‐wise interaction fusion and knowledge distillation(SIF‐KD)network for learning robust and discriminative features with scaleinvariance and background‐independent *** main highlights of this study include two *** the one hand,a global‐local features collaborative learning scheme is devised for extracting scale‐invariance features so as to tackle the large‐scale variation problem in aerial scene ***,a plug‐and‐play multi‐scale context attention fusion module is proposed for collaboratively fusing the context information between global and local *** the other hand,a scale‐wise knowledge distillation scheme is proposed to produce more consistent predictions by distilling the predictive distribution between different scales during *** experimental results show the proposed SIF‐KD network achieves the best overall accuracy with 99.68%,98.74%and 95.47%on the UCM,AID and NWPU‐RESISC45 datasets,respectively,compared with state of the arts.

关键词： deep learning image analysis image classification information fusion

来源：评论

学校读者我要写书评

暂无评论

CQUPT-HDS: Health big data Security Monitoring Scheme for the Whole Life Cycle

CQUPT-HDS: Health Big Data Security Monitoring Scheme for th...

引用

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Yunpeng Xiao Yun Lu Xiaohan Liu Peiyan Pei Dengke Zhao Yutong Guo Zhenzhou Xue Guoyin Wang Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and Telecommunications Chongqing China

ISBN: (数字)9798350377613

ISBN: (纸本)9798350377620

Federal Learning (FL) has made remarkable achievements in the medical field, but the technology still faces challenges in data sharing and privacy protection, which limits its application in the medical field. To solve these problems, we developed the CQUPT-HDS system. The system is dedicated to solving the security and privacy protection problems in cross-domain collaborative analysis, ensuring the security of data and models. In view of the sensitivity of medical data, complexity of cross-domain sharing and privacy protection, key technologies such as local differential privacy algorithm and searchable encryption algorithm are adopted to optimize model training, data transmission and role rights management, so as to achieve secure and efficient cross-domain data sharing and collaborative computing. The purpose of introducing the system is to realize comprehensive security situation awareness and detection, build a multi-level defense system, solve the challenges of data sharing and privacy protection in the medical field, and provide a reliable solution for cross-domain sharing and collaborative computing of medical data.

关键词： Training Process monitoring Sensitivity Scalability Collaboration Training data data models Reliability Protection Faces

来源：评论

学校读者我要写书评

暂无评论

A Multi-granularity Graph-based Representation for Image Recognition

A Multi-granularity Graph-based Representation for Image Rec...

引用

Power Electronics, Computer Applications (ICPECA), IEEE International Conference on

作者： Danfeng Lan Dawei Dai Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and Telecommunications Chongqing China

Graph neural networks (GNNs) are specially designed to process graph data because of their ability to effectively capture complex structures and relationships within graphs. However, due to the pixel-based nature of images, representing them as graphs and then using graph networks poses challenges. Inspired by granular computing, we propose a method to compute multi-granularity structured features from image tiles, which facilitates efficient and direct graph-based representation learning. Specifically: (1) We design a method to reorganize all regional features into multiple tiles and construct a multi-granularity graph representation, which includes nodes and edges. (2) We use gray-level co-occurrence matrices to extract the image texture features to compensate for the information lost during graph representation. (3) We design a graph neural network classifier that combines the above graph features and image texture features. Experimental evaluations on two benchmark image classification datasets demonstrate the efficiency of our proposed method and its potential to establish a new paradigm for image processing. Codes are available at https://***/ddw2AIGROUP2CQUPT/MGRIR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation 38

AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmenta...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Han, Boyu Xu, Qianqian Yang, Zhiyong Bao, Shilong Wen, Peisong Jiang, Yangbangyan Huang, Qingming Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China School of Computer Science and Tech. University of Chinese Academy of Sciences China Peng Cheng Laboratory China Key Laboratory of Big Data Mining and Knowledge Management CAS China

The Area Under the ROC Curve (AUC) is a well-known metric for evaluating instance-level long-tail learning problems. In the past two decades, many AUC optimization methods have been proposed to improve model performance under long-tail distributions. In this paper, we explore AUC optimization methods in the context of pixel-level long-tail semantic segmentation, a much more complicated scenario. This task introduces two major challenges for AUC optimization techniques. On one hand, AUC optimization in a pixel-level task involves complex coupling across loss terms, with structured inner-image and pairwise inter-image dependencies, complicating theoretical analysis. On the other hand, we find that mini-batch estimation of AUC loss in this case requires a larger batch size, resulting in an unaffordable space complexity. To address these issues, we develop a pixel-level AUC loss function and conduct a dependency-graph-based theoretical analysis of the algorithm's generalization ability. Additionally, we design a Tail-Classes Memory Bank (T-Memory Bank) to manage the significant memory demand. Finally, comprehensive experiments across various benchmarks confirm the effectiveness of our proposed AUCSeg method. The code is available at https://***/boyuh/AUCSeg. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A New Model Based on Differential Evolutionary Algorithm and Markov Clustering for Identifying Protein Complexes 42

A New Model Based on Differential Evolutionary Algorithm and...

引用

42nd Chinese Control Conference, CCC 2023

作者： Feng, Zengyu Tuo, Shouheng Chen, Tianrui School of Computer Science and Technology Xi'an University of Posts and Telecommunications Shaanxi Xi'an710121 China Xi'an Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi'an710121 China

ISBN: (纸本)9789887581543

As the material basis for all life activities, proteins play a crucial role in performing life activities. Most real-life proteins perform various functions in the form of protein complexes, so it is essential for understanding of life activities to accurately identify protein complexes. Most of the existing approaches learn protein interactions directly from protein topology, ignoring the biological characteristics of the actual proteins. Nevertheless, actual protein complexes are usually composed of protein cores and protein attachments. In this study, a new MP-DE algorithm is designed from the core-attachment structure to generate protein complex cores using Markov clustering, while searching for attached proteins in the second-order neighborhood of core protein complexes based on differential evolution(DE) algorithm. The experimental results show that the proposed method has high detection accuracy and efficiency on the current mainstream protein-protein interaction(PPI) database. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

Multi-View Fusion Networks for Multimodal Fake News Detection 11

Multi-View Fusion Networks for Multimodal Fake News Detectio...

引用

11th Joint International Information Technology and Artificial Intelligence Conference, ITAIC 2023

作者： Cui, Wei Li, Pu Zhang, Xuerui College of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China Chongqing Institute of Green and Intelligent Technology Chongqing Key Laboratory of Big Data and Intelligent Computing Chinese Academy of Sciences Chongqing China

ISBN: (纸本)9798350333664

The proliferation of multimedia fake news misleads social opinion, damages social harmony, and seriously challenges the authority of news media. Current multimodal fake news detection methods focus on extracting better unimodal features using pre-trained models and developing complex networks for visual and textual feature fusion, mostly ignoring social contextual information. In the text, we present a novel Multi-View Fusion Network (MVFN) for fake news detection, which attempts to achieve fusion learning of heterogeneous multimodal features. The model not only explores cross-modal graph interactions between visual regions and sentence words, but also investigates the effect of social context on feature learning. In addition, we consider the alignment relationship of features in both perspectives for better feature fusion. Experimental results on Chinese and English datasets show that the proposed model outperforms current multimodal detection approaches. © 2023 IEEE.

关键词： fake news graph multi view multimodal

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：