检索结果-内蒙古大学图书馆

arxiv 2022年

作者： Liu, Minmin Li, Xuechen Gao, xiangbo Chen, Junliang Shen, Linlin Wu, Huisi Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence of Robotics of Society Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China University of California Irvine United States

Due to the difficulty of cancer samples collection and annotation, cervical cancer datasets usually exhibit a long-tailed data distribution. When training a detector to detect the cancer cells in a WSI (Whole Slice Image) image captured from the TCT (Thinprep Cytology Test) specimen, head categories (e.g. normal cells and inflammatory cells) typically have a much larger number of samples than tail categories (e.g. cancer cells). Most existing state-of-the-art long-tailed learning methods in object detection focus on category distribution statistics to solve the problem in the long-tailed scenario, without considering the "hardness" of each sample. To address this problem, in this work we propose a Grad-Libra Loss that leverages the gradients to dynamically calibrate the degree of hardness of each sample for different categories, and re-balance the gradients of positive and negative samples. Our loss can thus help the detector to put more emphasis on those hard samples in both head and tail categories. Extensive experiments on a long-tailed TCT WSI image dataset show that the mainstream detectors, e.g. RepPoints, FCOS, ATSS, YOLOF, etc. trained using our proposed Gradient-Libra Loss, achieved much higher (7.8%) mAP than that trained using cross-entropy classification loss. Copyright © 2022, The Authors. All rights reserved.

关键词： Cytology

来源：评论

学校读者我要写书评

暂无评论

Improving Incremental Learning: A Closer Look at the Softmax Function

SSRN

引用

SSRN 2024年

作者： Zhai, Zheng Zhang, Jiali Wang, Haiyu Wu, Mingxin Yang, Keshun Qiao, xiaoyan Sun, Qiang Beijing Normal University No.18 Jinfeng Road Guangdong Zhuhai519087 China Shandong Technology and Business University Shandong Yantai China Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Shandong China Immersion Technology and Evaluation Shandong Engineering Research Center Shandong China School of Mathematics Sichuan University Chengdu China College of Liberal Arts and Sciences University of Illinois Urbana-Champaign IL United States Department of Statistical Sciences University of Toronto ON Canada Department of Computer Science University of Toronto ON Canada Department of Statistics and Data Science MBZUAI Abu Dhabi United Arab Emirates

This paper investigates the limitations of the widely adopted softmax cross-entropy loss in incremental learning problems. Specifically, we highlight how the shift-invariant property of this loss function can lead to multiple optimal solutions and imbalanced weights across different tasks, which exacerbates catastrophic forgetting. To address these issues, we propose two key modifications to the objective function: (1) regularizing or replacing the original joint distillation loss with a summation of task-specific distillation losses, and/or (2) utilizing a shift-sensitive prediction loss function, such as the binary cross-entropy loss. Numerical experiments validate the effectiveness of these proposals, demonstrating improved prediction accuracy and a significant reduction in forgetting. © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Towards Lightweight and Efficient Distributed Intrusion Detection Framework

Towards Lightweight and Efficient Distributed Intrusion Dete...

引用

2021 IEEE Global Communications Conference (GLOBECOM)

作者： Shuai Yuan Hongwei Li Rui Zhang Meng Hao Yiran Li Rongxing Lu School of Computer Science and Engineering University of Electronic Science and Technology of China China Chinese Academy of Sciences Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chongqing China Faculty of Computer Science University of New Brunswick Canada

ISBN: (纸本)9781728181059

Federated learning (FL), as a promising distributed learning paradigm, has put many efforts into distributed intrusion detection systems (IDS), for defending against various malicious attacks, such as SQL injection and DDoS attacks. Compared with traditional IDS based on centralized deep learning (DL), FL-based solutions require not to share users' raw data while yielding better detection performance. However, state-of-the-art FL-based methods still suffer from two key limitations: 1) insufficient detection performance on non-independent and identically distributed (non-IID) data, and 2) high communication and computational overheads due to the utilization of large-scale neural network models. In this paper, we propose a lightweight collaborative intrusion detection framework, called CoLGBM, the first of its kind in the regime of decentralized IDS, where decision tree and light gradient boosting machine (LGBM) are combined for constructing the detection scheme. The main insight is that through combining user-trained decision trees (each user's decision tree is derived from its own data with unique distribution), our framework can perform effectively on non-IID data while working efficiently for handling enormous samples. Compared with the current FL-based methods, our CoLGBM achieves higher accuracy and lower overhead on both IID and non-IID data. Extensive experiment results demonstrate our scheme with high-level performance.

关键词： Deep learning Distance learning Neural networks Intrusion detection Distributed databases SQL injection Boosting

来源：评论

学校读者我要写书评

暂无评论

Mobility-aware Seamless Service Migration and Resource Allocation in Multi-edge IoV Systems

arXiv

引用

arxiv 2025年

作者： Chen, Zheyi Huang, Sijin Min, Geyong Ning, Zhaolong Li, Jie Zhang, Yan College of Computer and Data Science Fuzhou University Fuzhou350116 China Engineering Research Center of Big Data Intelligence Ministry of Education Fujian Key Laboratory of Network Fuzhou350002 China Computing and Intelligent Information Processing [Fuzhou University Fuzhou350116 China Department of Computer Science Faculty of Environment Science and Economy University of Exeter ExeterEX4 4QF United Kingdom School of Communications and Information Engineering Chongqing University of Posts and Telecommunications Chongqing400065 China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China Department of Informatics University of Oslo Oslo0316 Norway

Mobile Edge computing (MEC) offers low-latency and high-bandwidth support for Internet-of-Vehicles (IoV) applications. However, due to high vehicle mobility and finite communication coverage of base stations, it is hard to maintain uninterrupted and high-quality services without proper service migration among MEC servers. Existing solutions commonly rely on prior knowledge and rarely consider efficient resource allocation during the service migration process, making it hard to reach optimal performance in dynamic IoV environments. To address these important challenges, we propose SR-CL, a novel mobility-aware seamless Service migration and Resource allocation framework via Convex-optimization-enabled deep reinforcement Learning in multi-edge IoV systems. First, we decouple the Mixed Integer Nonlinear Programming (MINLP) problem of service migration and resource allocation into two sub-problems. Next, we design a new actor-critic-based asynchronous-update deep reinforcement learning method to handle service migration, where the delayed-update actor makes migration decisions and the one-step-update critic evaluates the decisions to guide the policy update. Notably, we theoretically derive the optimal resource allocation with convex optimization for each MEC server, thereby further improving system performance. Using the real-world datasets of vehicle trajectories and testbed, extensive experiments are conducted to verify the effectiveness of the proposed SR-CL. Compared to benchmark methods, the SR-CL achieves superior convergence and delay performance under various scenarios. Copyright © 2025, The Authors. All rights reserved.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

A Diverse Biases Non-negative Latent Factorization of Tensors Model for Dynamic Network Link Prediction

A Diverse Biases Non-negative Latent Factorization of Tensor...

引用

2020 IEEE International Conference on Networking, Sensing and Control, ICNSC 2020

作者： Wu, Xuke Gou, Hang Wu, Hao Wang, Juan Chen, Minzhi Lai, Siyu Computer School China West Normal University Nanchong Sichuan637002 China Chongqing Engineering Research Center of Big Data Application for Smart Cities Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China University of Chinese Academy of Sciences Beijing100049 China Department of Medical Imaging North Sichuan Medical College Nanchong Sichuan637000 China

ISBN: (纸本)9781728168531

Dynamic networks vary over time, making it vital to capture networks temporal patterns for predicting missing links with high accuracy. A biased non-negative latent factorization of tensors (BNLFT) model is very effective in extracting such patterns from dynamic data. However, a BNLFT model only integrates single bias, which cannot adequately represents the volatility of the dynamic data. To address this issue, this paper presents a Diverse Biases Non-negative Latent Factorization of Tensors (DBNT) model for accurate prediction of missing links in dynamic networks. Meanwhile, for further prediction accuracy improvement, the preprocessing bias is integrated into the DBNT model. Empirical studies on two dynamic networks datasets from real applications show that compared with state of the art predictors, a DBNT model achieves higher prediction accuracy. © 2020 IEEE.

关键词： Factorization

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Characteristic Decomposition of Parametric Polynomial Systems 21

Comprehensive Characteristic Decomposition of Parametric Pol...

引用

46th International Symposium on Symbolic and Algebraic Computation, ISSAC 2021

作者： Dong, Rina Lu, Dong Mou, Chenqi Wang, Dongming Chongqing Key Laboratory of Automated Reasoning and Cognition Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China Beijing Advanced Innovation Center for Big Data and Brain Computing School of Mathematical Sciences Beihang University Beijing100191 China LMIB-School of Mathematical Sciences Beihang University Beijing100191 China Centre National de la Recherche Scientifique Paris cedex 1675794 France

ISBN: (纸本)9781450383820

This paper presents an algorithm that decomposes an arbitrary set F of multivariate polynomials involving parameters into finitely many sets Gi of (lexicographical) Gröbner bases G ij such that associated with each Gi there is a system Ai of parametric constraints, all the Ai's partition the parameter space, all the Gij's in each Gi remain Gröbner bases under specialization of the parameters satisfying the constraints in Ai, and for each i the Gröbner bases Gij together with their corresponding W-characteristic sets form a normal characteristic decomposition of F. The sets of Gröbner bases computed by the algorithm provide a comprehensive characteristic decomposition of F that is structure-invariant under the associated constraints and possesses many algebraic and geometric properties, including most of the notable properties on comprehensive Gröbner systems and comprehensive triangular decomposition. Some of these properties are highlighted in the paper and advantages of the proposed algorithm are discussed briefly from the aspects of methodological simplicity and computational performance using illustrative examples and preliminary experiments. © 2021 ACM.

关键词： Polynomials

来源：评论

学校读者我要写书评

暂无评论

Deep Sentiment Learning Network for Temporal-aware Recommendation Based on User Reviews

Deep Sentiment Learning Network for Temporal-aware Recommend...

引用

IEEE International Conference on big data Analysis (ICBDA)

作者： xinxin Li Tianqi Shang Dezhong Peng xiaoyu Shi School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China College of Computer Science Sichuan University Chengdu China Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing China

Recently, many websites encourage users to fill in reviews on items and services to improve the quality of personalized recommendation, because of the rich sentiment information hidden in user reviews. However, most existing recommendation methods based on reviews heavily emphasize extracting the rich sentiment information from reviews by using deep learning technologies as far as possible and always ignore the effects of temporal dynamical of user preferences. To address the above issues, we propose DSL- TR, a deep sentiment learning framework for the temporal-aware recommendation, using an intricate combination of bidirectional long short-term memory (BLSTM) and Convolution Neural Network (CNN). It consists of four layers: embedding layer, BLSTM layer, CNN layer and feature fusion layer. In the embedding layer, we explicitly combine the time information in the review embedding layer by regarding the review time as an independent factor. Then, we utilize the BLSTM and CNN networks to extract the long and short-terms of latent features of user and item in parallel. Finally, the factorization machine technique, as a rating predictor, is introduced on the last layer to estimate the rating based on the learned user and item latent features. We conduct extensive experiments on Amazon's four data sets. The results demonstrate that our proposed method outperforms several state-of-art methods consistently.

关键词： Deep learning Convolution Conferences Neural networks big data Feature extraction data mining

来源：评论

学校读者我要写书评

暂无评论

Graph Regularized Nonnegative Latent Factor Analysis Model for Temporal Link Prediction in Cryptocurrency Transaction Networks

Graph Regularized Nonnegative Latent Factor Analysis Model f...

引用

IEEE International Conference on Networking, Sensing and Control

作者： Yue Zhou ZhiGang Liu Ye Yuan School of Computer Science and Technology Choncgqing University of Posts and Telecommunications Chongqing China School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing 400714 China and with the Chongqing School University of Chinese Academy of Sciences Chongqing China College of Computer and Information Science Southwest University Chongqing China

ISBN: (纸本)9781665472449

With the development of blockchain technology, a cryptocurrency based on blockchain technology is becoming more and more popular. The huge cryptocurrency transaction network has therefore received widespread attention. The link prediction learning structure of the network is supportive to understand the mechanism of networks, so it also has been widely studied in the cryptocurrency network. However, the dynamics of cryptocurrency transaction networks have been neglected in past studies. In this study, therefore, we use a graph-regularized method to link past transaction records with future transactions. Based on this, we propose a single latent factor-dependent, nonnegative, multiplicative, and graph regularized-incorporated update (SLF-NMGRU) algorithm and further propose a graph regularized nonnegative latent factor analysis (GrNLFA) model. Eventually, the experimental results on a real cryptocurrency transaction network show that the proposed method improves both the accuracy and computational efficiency.

关键词： Analytical models Tensors Computational modeling Heuristic algorithms Optimization methods Predictive models Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

The Minority Matters: A Diversity-Promoting Collaborative Metric Learning Algorithm

arXiv

引用

arxiv 2022年

作者： Bao, Shilong Xu, Qianqian Yang, Zhiyong He, Yuan Cao, xiaochun Huang, Qingming State Key Laboratory of Information Security 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 School of Computer Science and Tech. University of Chinese Academy of Sciences China Alibaba Group China School of Cyber Science and Technology Shenzhen Campus Sun Yat-sen University China Key Laboratory of Big Data Mining and Knowledge Management CAS China Peng Cheng Laboratory China

Collaborative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and Collaborative Filtering. Following the convention of RS, existing methods exploit unique user representation in their model design. This paper focuses on a challenging scenario where a user has multiple categories of interests. Under this setting, we argue that the unique user representation might induce preference bias, especially when the item category distribution is imbalanced. To address this issue, we propose a novel method called Diversity-Promoting Collaborative Metric Learning (DPCML), with the hope of considering the commonly ignored minority interest of the user. The key idea behind DPCML is to include a multiple set of representations for each user in the system. Based on this embedding paradigm, user preference toward an item is aggregated from different embeddings by taking the minimum item-user distance among the user embedding set. Furthermore, we observe that the diversity of the embeddings for the same user also plays an essential role in the model. To this end, we propose a diversity control regularization term to accommodate the multi-vector representation strategy better. Theoretically, we show that DPCML could generalize well to unseen test data by tackling the challenge of the annoying operation that comes from the minimum value. Experiments over a range of benchmark datasets speak to the efficacy of DPCML. © 2022, CC BY-NC-SA.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

UEIN: A User Evolving Interests Network for Click-Through Rate Prediction

UEIN: A User Evolving Interests Network for Click-Through Ra...

引用

big data Science and Engineering (bigdataSE), IEEE International Conference on

作者： Jianxiong Xu xiaoyu Shi Hezhe Qiao Mingsheng Shang xianbo He Qingyu He The Computer School of China West Normal University Nanchong Sichuan China Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing China College of Land and Resources China West Normal University Nanchong Sichuan China

ISBN: (纸本)9781665400398

The Click-Through Rate (CTR) prediction via modeling the change of user interest is of great significance task to industrial applications. Most of the existing methods based on collaborative filtering (CF) and recurrent neural network (RNN) that focus on capturing user's long-term and short-term interests separately, or combine these interests in a tough way. However, the effect of long- and short-term interests accounts different ratios to the next-item decision of user, rather than equally. To address this issue, we propose UEIN, a novel User Evolving Interest Network for CTR prediction task, that can capture the change of user preference via adaptively fusion the user's long-term and short-term interests over time. To explicitly learn the user preference on item category, we add the item category information into user behavior sequence, by clustering the items into different categories. Then we divide user historical behaviors into two sequence parts, long-term and short-term behaviors sequence. Based on this, we leverage the attention network to learn the user's current interest from the short-term behaviors sequence, while a dense network is adopted to extract the user's general interest from the long-term sequence. After that, an adaptive fusion mechanism is proposed to combine the current and general interest adaptively, and the prediction result is generated based on the user's combined interest. Extensive experimental results on industrial datasets demonstrated that the superiority of our proposed model, compared to the state-of-the-art models.

关键词： Adaptation models Recurrent neural networks Conferences Collaborative filtering Clustering methods Predictive models Feature extraction

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：