检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Cheng, Lei Huang, Xiaowen Sang, Jitao Yu, Jian The School of Computer Science and Technology Beijing Jiaotong University China The Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University China The Key Laboratory of Big Data & Artificial Intelligence in Transportation Beijing Jiaotong University Ministry of Education China

Recently, recommender system has achieved significant success. However, due to the openness of recommender systems, they remain vulnerable to malicious attacks. Additionally, natural noise in training data and issues such as data sparsity can also degrade the performance of recommender systems. Therefore, enhancing the robustness of recommender systems has become an increasingly important research topic. In this survey, we provide a comprehensive overview of the robustness of recommender systems. Based on our investigation, we categorize the robustness of recommender systems into adversarial robustness and non-adversarial robustness. In the adversarial robustness, we introduce the fundamental principles and classical methods of recommender system adversarial attacks and defenses. In the non-adversarial robustness, we analyze non-adversarial robustness from the perspectives of data sparsity, natural noise, and data imbalance. Additionally, we summarize commonly used datasets and evaluation metrics for evaluating the robustness of recommender systems. Finally, we also discuss the current challenges in the field of recommender system robustness and potential future research directions. Additionally, to facilitate fair and efficient evaluation of attack and defense methods in adversarial robustness, we propose an adversarial robustness evaluation library–ShillingREC, and we conduct evaluations of basic attack models and recommendation models. ShillingREC project is released at https://***/chengleileilei/ShillingREC. Copyright © 2024, The Authors. All rights reserved.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Overview of Essential Components in deep learning reference-based super resolution methods

引用

Procedia computer science 2024年 242卷 1243-1248页

作者： Jiayu Xue Junjie Liu Yong Shi School of Computer Science and Technology University of Chinese Academy of Sciences Beijing 101408 China Research Center on Fictitious Economy & Data Science Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China Sino-Danish College University of Chinese Academy of Sciences Beijing 100049 China School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China College of Information Science and Technology University of Nebraska at Omaha Omaha NE 68182 USA

Reference-based super resolution (RefSR) aims to recover the lost details in a low-resolution image and generate a high-resolution result, guided by a high-resolution reference image with similar contents or textures. In contrast to the traditional single-image super-resolution, which focuses on the intrinsic properties of the single low-resolution image, the challenge of RefSR lies in matching and aggregating highly-related but misaligned reference images with low-resolution images. Several effective but complex designs have been proposed to address this challenge, which poses difficulties in implementing RefSR in real-world applications. In order to better understand the working mechanism of RefSR and design a more efficient and lightweight architecture, we provide a review about the essential components of the existing deep learning-based RefSR. We decompose and classify the common pipeline into four submodules according to the functionalities. Then, we summarize and describe the implementation details of the commonly-adopted approaches in each submodule. Finally, we discuss the challenges and promising research directions.

关键词： Reference-based super resolution Deep learning Feature matching Feature alignment

来源：评论

学校读者我要写书评

暂无评论

Active Learning with Nonparallel Support Vector Machine for Binary Classification

Active Learning with Nonparallel Support Vector Machine for ...

引用

IEEE International Conference on data mining Workshops (ICDM Workshops)

作者： Xi Zhao Zhensong Chen Yong Shi School of Computer Science and Technology Beijing Institute of Technology Beijing China University of Chinese Academy of Sciences Beijing China Key Res. Lab. on Big Data Min. & Knowledge Manage. Beijing China

ISBN: (纸本)9781479942732

labeled data, in real world, is quite scarce compared with unlabeled data. Manual annotation is usually expensive and inefficient. Active learning paradigm is used to handle this problem by identifying the most informative instances to annotate. In this paper, we proposed a new active learning algorithm based on nonparallel support vector machine. Numeric experiment shows the effective performance of the proposed method compared with classical active learning based on support vector machine.

关键词： Support vector machines Mathematical model Accuracy Kernel Equations Educational institutions Optimization

来源：评论

学校读者我要写书评

暂无评论

Large-scale Nonparallel Support Vector Ordinal Regression Solver

引用

Procedia computer science 2017年 108卷 1261-1270页

作者： Huadong Wang Jianyu Miao Seyed Mojtaba Hosseini Bamakan Lingfeng Niu Yong Shi Research Center on Fictitious Economy & Data Science Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China School of Mathematical Sciences University of Chinese Academy of Sciences Beijing 100049 China College of Information Science and Technology University of Nebraska at Omaha Omaha NE 68118 USA

Large-scale linear classification is widely used in many areas. Although SVM-based models for ordinal regression problem are proven to be powerful techniques, the performance with nonlinear kernels are often suffering from time consuming. Recently, linear SVC not only is shown to obtain competitive performance in most of the cases, but also it is considerably fast during the process of training and testing. However, few studies focused on linear SVM-based ordinal regression models. In this paper, we propose a new approach, called linear Nonparallel Support Vector Ordinal Regression (NPSVOR), which can deal with large-scale problems. An efficient algorithm based on Alternating Direction Method of Multipliers (ADMM) is designed to solve the proposed model. Our experiments are performed on large document data sets to demonstrate the effectiveness of the proposed method.

关键词： Ordinal Regression Support Vector Machine ADMM

来源：评论

学校读者我要写书评

暂无评论

General Two-Stage Network Systems Based on Stackelberg Game

SSRN

引用

SSRN 2023年

作者： Zhang, Linyan Zhang, Jian Guo, Chuanyin School of Economics and Management Beijing Information Science & Technology University Beijing100192 China Research Center for Knowledge Management Beijing100192 China Beijing Key Lab of Green Development Decision Based on Big Data Beijing100192 China

Noncooperative approach is a key technique for modeling network systems. In general, there are two types of noncooperative network models in the literature. One is the bilevel model based on Stackelberg game, which is often transformed into a parametric linear program. The other is the leader-follower model, which uses only Stackelberg game concept, which may yield an infeasible solution. The current study shows that the bilevel model can be solved by using two linear models, without having to resort to solving heuristic parametric linear models. Furthermore, the global optimal solution is guaranteed for the nonlinear bilevel model. We prove the equivalence between the bilevel technique and our two linear-model approach. We further improve the existing leader-follower models, and as well the newly developed approaches are extended to general two-stage structures. The newly developed approaches are illustrated with a numerical data set and a real-world case. © 2023, The Authors. All rights reserved.

关键词： Linear programming

来源：评论

学校读者我要写书评

暂无评论

GPTR: Gestalt-Perception Transformer for Diagram Object Detection

arXiv

引用

arXiv 2022年

作者： Hu, Xin Zhang, Lingling Liu, Jun Fan, Jinfu You, Yang Wu, Yaqiang Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering School of Computer Science and Technology Xi’an Jiaotong University China National Engineering Lab for Big Data Analytics Xi’an Jiaotong University China Department of Control Science and Engineering Tongji University Shanghai China Department of Computer Science National University of Singapore Singapore Lenovo Research Beijing China

Diagram object detection is the key basis of practical applications such as textbook question answering. Because the diagram mainly consists of simple lines and color blocks, its visual features are sparser than those of natural images. In addition, diagrams usually express diverse knowledge, in which there are many low-frequency object categories in diagrams. These lead to the fact that traditional data-driven detection model is not suitable for diagrams. In this work, we propose a gestalt-perception transformer model for diagram object detection, which is based on an encoder-decoder architecture. Gestalt perception contains a series of laws to explain human perception, that the human visual system tends to perceive patches in an image that are similar, close or connected without abrupt directional changes as a perceptual whole object. Inspired by these thoughts, we build a gestalt-perception graph in transformer encoder, which is composed of diagram patches as nodes and the relationships between patches as edges. This graph aims to group these patches into objects via laws of similarity, proximity, and smoothness implied in these edges, so that the meaningful objects can be effectively detected. The experimental results demonstrate that the proposed GPTR achieves the best results in the diagram object detection task. Our model also obtains comparable results over the competitors in natural image object detection. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Contourlet and nearest feature line based feature extraction approach for one prototype sample problem

引用

Journal of Information Hiding and Multimedia Signal Processing 2016年第5期7卷 1052-1059页

作者： Pan, Jeng-Shyang Yan, Lijun Chu, Shu-Chuan Roddick, John F. Fujian University of International Studies and Trade Fujian Province China Fujian Provincial Key Lab of Big Data Mining and Applications Fujian University of Technology China Shenzhen Institute of Information Technology Shenzhen China School of Computer Science Engineering and Mathematics Flinders University Australia

In this paper, a novel algorithm for face recognition with one sample per person is proposed. The proposed algorithm is based on contourlet transformation. For simple prototype sample problem, many discriminant learning methods can not work. Because for most discriminant learning methods, the within class scatter of the prototype samples are very important. However, simple prototype sample problem does not have within class scatter. To enhance the representative capability of the prototype samples set, some new samples are generated using contourlet transformation. Multiple prototype samples for each class are constructed through the decomposition and reconstruction of original training images by contourlet transformation. Thus neighborhood discriminant nearest feature line analysis can be performed on the new database. The experimental results demonstrate the efficiency of the proposed algorithm. © 2016, Ubiquitous International. All Rights Reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

LadRa-Net: Locally-aware dynamic re-read attention net for sentence semantic matching

arXiv

引用

arXiv 2021年

作者： Zhang, Kun Lv, Guangyi Wu, Le Chen, Enhong Liu, Qi Wang, Meng Key Laboratory of Knowledge Engineering with Big Data School of Computer and Information Hefei University of Technology Anhui Hefei230029 China AI Lab at Lenovo Research Beijing100094 China University of Science and Technology of China Hefei230026 China

Sentence semantic matching requires an agent to determine the semantic relation between two sentences, which is widely used in various natural language tasks, such as Natural Language Inference (NLI), Paraphrase Identification (PI), and so on. Much recent progress has been made in this area, especially attention-based methods and pre-trained language model based methods. However, most of these methods focus on all the important parts in sentences in a static way and only emphasize how important the words are to the query, inhibiting the ability of attention mechanism. In order to overcome this problem and boost the performance of attention mechanism, we propose a novel dynamic re-read attention, which can pay close attention to one small region of sentences at each step and re-read the important parts for better sentence representations. Based on this attention variation, we develop a novel Dynamic Re-read Network (DRr-Net) for sentence semantic matching. Moreover, selecting one small region in dynamic re-read attention seems insufficient for sentence semantics, and employing pre-trained language models as input encoders will introduce incomplete and fragile representation problems. To this end, we extend DRr-Net to Locally-Aware Dynamic Re-read Attention Net (LadRa-Net), in which local structure of sentences is employed to alleviate the shortcoming of Byte-Pair Encoding (BPE) in pre-trained language models and boost the performance of dynamic reread attention. Extensive experiments on two popular sentence semantic matching tasks demonstrate that DRr-Net can significantly improve the performance of sentence semantic matching. Meanwhile, LadRa-Net is able to achieve better performance by considering the local structures of sentences. In addition, it is exceedingly interesting that some discoveries in our experiments are consistent with some findings of psychological research. © 2021, CC BY.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

A Brief Survey of Distribution Robust Graph Neural Networks

引用

Procedia computer science 2024年 242卷 1281-1286页

作者： Lei Zheng Pei Quan Yong Shi Lingfeng Niu The School of Mathematical Sciences University of Chinese Academy of Sciences Beijing 100190 China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China The College of Economics and Management Beijing University of Technology Beijing 100124 China The School of Economics and Management University of Chinese Academy of Sciences Beijing 1001090 China

Graph neural network is a powerful tool for solving various graph tasks, such as node classification and graph classification. However, there is increasing evidence suggesting that it is sensitive to distribution shifts and its performance is reduced by at least 10% when distribution shifts happen. In the last three years, to solve the wide existing distribution shifts, some distribution robust strategies have been designed specifically for graph neural networks. It is also one of the popular research topics in graph neural networks in recent years. Therefore, in this paper, we divide these strategies into three categories depending on the specific problems they solve: distribution shift for semi-supervised node classification, distribution shift for unsupervised node classification, and out-of-distribution shift for graph classification. Furthermore, we discuss and summarize the strategies for each type of problem. After investigating these strategies, we put forward future development direction.

关键词： Graph neural networks Shift robust Distribution generalization

来源：评论

学校读者我要写书评

暂无评论

Towards Unified Token Learning for Vision-Language Tracking

arXiv

引用

arXiv 2023年

作者： Zheng, Yaozong Zhong, Bineng Liang, Qihua Li, Guorong Ji, Rongrong Li, Xianxian The Key Laboratory of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin541004 China The Guangxi Key Laboratory of Multi-Source Information Mining and Security Guangxi Normal University Guilin541004 China The School of Computer Science and Technology Key Laboratory of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences Beijing100049 China Media Analytics and Computing Lab Department of Artificial Intelligence School of Informatics Xiamen University 361005 China

In this paper, we present a simple, flexible and effective vision-language (VL) tracking pipeline, termed MMTrack, which casts VL tracking as a token generation task. Traditional paradigms address VL tracking task indirectly with sophisticated prior designs, making them over-specialize on the features of specific architectures or mechanisms. In contrast, our proposed framework serializes language description and bounding box into a sequence of discrete tokens. In this new design paradigm, all token queries are required to perceive the desired target and directly predict spatial coordinates of the target in an auto-regressive manner. The design without other prior modules avoids multiple sub-tasks learning and hand-designed loss functions, significantly reducing the complexity of VL tracking modeling and allowing our tracker to use a simple cross-entropy loss as unified optimization objective for VL tracking task. Extensive experiments on TNL2K, LaSOT, LaSOText and OTB99-Lang benchmarks show that our approach achieves promising results, compared to other state-of-the-arts. Copyright © 2023, The Authors. All rights reserved.

关键词： Modeling languages

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：