检索结果-内蒙古大学图书馆

IEEE Annual Joint Conference: INFOCOM, IEEE Computer and Communications Societies

作者： En Wang Weiting Liu Wenbin Liu Chaocan Xiang Bo Yang Yongjian Yang College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China College of Computer Science Chongqing University China

Mobile CrowdSensing (MCS) is a data sensing paradigm that recruits users carrying mobile terminals to collect data. As its variant, Sparse MCS has been further proposed for large-scale and fine-grained sensing task with the advantage of collecting only a few data to infer unsensed data. However, in many real-world scenarios, such as early prevention of epidemic, people are interested in not only the data at the current, but also in the future or even long-term future, and the latter may be more important. Long-term prediction not only reduces sensing cost, but also identifies trends or other characteristics of the data. In this paper, we propose a spatiotemporal model based on Transformer to infer and predict the data with sparse sensed data by utilizing spatiotemporal relationships. We design a spatiotemporal feature embedding to embed the prior spatiotemporal information of sensing map into the model to guide model learning. Moreover, we also design a novel multi-head spatiotemporal attention mechanism to dynamically capture spatiotemporal relationships among data. Extensive experiments have been conducted on three types of typical urban sensing tasks, which verify the effectiveness of our proposed algorithms in improving the inference and long-term prediction accuracy with the sparse sensed data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Coarse-to-fine Cascaded Evidence-Distillation Neural Network for Explainable Fake News Detection 29

A Coarse-to-fine Cascaded Evidence-Distillation Neural Netwo...

引用

29th International Conference on computational Linguistics, COLING 2022

作者： Yang, Zhiwei Ma, Jing Chen, Hechang Lin, Hongzhan Luo, Ziyang Chang, Yi College of Computer Science and Technology Jilin University Changchun China Department of Computer Science Hong Kong Baptist University Hong Kong School of Artificial Intelligence International Center of Future Science Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education

Existing fake news detection methods aim to classify a piece of news as true or false and provide veracity explanations, achieving remarkable performances. However, they often tailor automated solutions on manual fact-checked reports, suffering from limited news coverage and debunking delays. When a piece of news has not yet been fact-checked or debunked, certain amounts of relevant raw reports are usually disseminated on various media outlets, containing the wisdom of crowds to verify the news claim and explain its verdict. In this paper, we propose a novel Coarse-to-fine Cascaded Evidence-Distillation (CofCED) neural network for explainable fake news detection based on such raw reports, alleviating the dependency on fact-checked ones. Specifically, we first utilize a hierarchical encoder for web text representation, and then develop two cascaded selectors to select the most explainable sentences for verdicts on top of the selected top-K reports in a coarse-to-fine manner. Besides, we construct two explainable fake news datasets, which is publicly available. Experimental results demonstrate that our model significantly outperforms state-of-the-art detection baselines and generates high-quality explanations from diverse evaluation perspectives. © 2022 Proceedings - International Conference on computational Linguistics, COLING. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Application of Hybrid Monocular SLAM Method in Augmented Reality 5

Application of Hybrid Monocular SLAM Method in Augmented Rea...

引用

2020 5th International Seminar on Computer Technology, Mechanical and Electrical engineering, ISCME 2020

作者： Zhang, Zuoming Wang, Hanwen Shu, Man Wang, Xin College of Software Engineering Jilin University Changchun Jilin130000 China Key Laboratory of Symbolic Computation and Knowledge Engineer of Ministry of Education Jilin University Changchun Jilin130000 China

In this paper, we design a hybrid (semi-direct) approach to simultaneous localization and mapping (SLAM) for monocular cameras and apply it to augmented reality (AR) for monocular cameras. We combine the advantagesof the direct method and the feature point method. We use both photometric bundle adjustment which is robust to camera exposure time and motion bundle adjustment which is geometrically robust based on feature points to do tracking process. This approach can maintain an intuitive direct local map as well as a reusable global sparse feature point map. Through the processing of point clouds, such as PCA plane detection and grid reconstruction, we greatly improve the effect of the augmented reality system. © Published under licence by IOP Publishing Ltd.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Fast Converging Anytime Model Counting

arXiv

引用

arXiv 2022年

作者： Lai, Yong Meel, Kuldeep S. Yap, Roland H.C. Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University China School of Computing National University of Singapore Singapore

Model counting is a fundamental problem which has been influential in many applications, from artificial intelligence to formal verification. Due to the intrinsic hardness of model counting, approximate techniques have been developed to solve real-world instances of model counting. This paper designs a new anytime approach called PartialKC for approximate model counting. The idea is a form of partial knowledge compilation to provide an unbiased estimate of the model count which can converge to the exact count. Our empirical analysis demonstrates that PartialKC achieves significant scalability and accuracy over prior state-of-the-art approximate counters, including satss and STS. Interestingly, the empirical results show that PartialKC reaches convergence for many instances and therefore provides exact model counting performance comparable to state-of-the-art exact counters. Copyright © 2022, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Application of Monocular Direct Vision Odometry in Augmented Reality 5

Application of Monocular Direct Vision Odometry in Augmented...

引用

2020 5th International Seminar on Computer Technology, Mechanical and Electrical engineering, ISCME 2020

作者： Zhang, Zuoming Wang, Zixuan Wang, Hanwen Wang, Xin College of Software Engineering Jilin University Changchun Jilin130000 China Key Laboratory of Symbolic Computation and Knowledge Engineer of Ministry of Education Jilin University Changchun Jilin130000 China

In recent years, the unlabeled augmented reality system has been gradually applied to various mobile devices, among which stable, accurate, and fast registration is the key to realizing this function. For this technique, this paper introduces camera exposure parameters and puts the data association and pose estimation into a unified nonlinear optimization problem. Moreover, the direct monocular vision odometer is transplanted into the augmented reality system through the position adjustment module. We compare it with the traditional visual odometry method that matches the feature points. The results show that this improved method can be used to track more quickly and build a more visual semi-dense point cloud map, which can be used to support the registration and tracking of virtual objects in augmented reality. © Published under licence by IOP Publishing Ltd.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Noisetrans: Point Cloud Denoising with Transformers

SSRN

引用

SSRN 2022年

作者： Hou, Guangzhe Qin, Guihe Sun, Minghui Liang, Yanhua Yan, Jie Zhang, Zhonghan Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University 2699 Chaoyang District Changchun Jilin130012 China

Introduction: Point clouds obtained from capture devices or 3D reconstruction techniques are often noisy and interfere with downstream ***: The paper aims to recover the underlying surface of noisy point ***: We design a novel model, NoiseTrans, which uses transformer encoder architecture for point cloud denoising. Specifically, we obtain structural similarity of point-based point clouds with the assistance of the transformer's core self-attention mechanism. By expressing the noisy point cloud as a set of unordered vectors, we convert point clouds into point embeddings and employ Transformer to generate clean point clouds. To make the Transformer preserve details when sensing the point cloud, we design the Local Point Attention to prevent the point cloud from being over-smooth. In addition, we also propose sparse encoding, which enables the Transformer to better perceive the structural relationships of the point cloud and improve the denoising ***: Experiments show that our model outperforms state-of-the-art methods in various datasets and noise environments. © 2022, 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

Incomplete Graph Learning: A Comprehensive Survey

arXiv

引用

arXiv 2025年

作者： Xia, Riting Liu, Huibo Li, Anchen Liu, Xueyan Zhang, Yan Zhang, Chunxu Yang, Bo College of Computer Science Inner Mongolia University Hohhot010021 China School of Computer Science and Technology Jilin University Jilin Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China

Graph learning is a prevalent field that operates on ubiquitous graph data. Effective graph learning methods can extract valuable information from graphs. However, these methods are non-robust and affected by missing attributes in graphs, resulting in sub-optimal outcomes. This has led to the emergence of incomplete graph learning, which aims to process and learn from incomplete graphs to achieve more accurate and representative results. In this paper, we conducted a comprehensive review of the literature on incomplete graph learning. Initially, we categorize incomplete graphs and provide precise definitions of relevant concepts, terminologies, and techniques, thereby establishing a solid understanding for readers. Subsequently, we classify incomplete graph learning methods according to the types of incompleteness: (1) attribute-incomplete graph learning methods, (2) attribute-missing graph learning methods, and (3) hybrid-absent graph learning methods. By systematically classifying and summarizing incomplete graph learning methods, we highlight the commonalities and differences among existing approaches, aiding readers in selecting methods and laying the groundwork for further advancements. In addition, we summarize the datasets, incomplete processing modes, evaluation metrics, and application domains used by the current methods. Lastly, we discuss the current challenges and propose future directions for incomplete graph learning, with the aim of stimulating further innovations in this crucial field. To our knowledge, this is the first review dedicated to incomplete graph learning, aiming to offer valuable insights for researchers in related fields.1 Copyright © 2025, 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

When Federated Recommendation Meets Cold-Start Problem: Separating Item Attributes and User Interactions 24

When Federated Recommendation Meets Cold-Start Problem: Sepa...

引用

33rd ACM Web Conference, WWW 2024

作者： Zhang, Chunxu Long, Guodong Zhou, Tianyi Zhang, Zijian Yan, Peng Yang, Bo College of Computer Science and Technology Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China Australian Artificial Intelligence Institute FEIT University of Technology Sydney Sydney Australia Computer Science and Umiacs University of Maryland MD United States College of Computer Science and Technology Jilin University City University of Hong Kong Hong Kong City University of Hong Kong Hong Kong

ISBN: (纸本)9798400701719

Federated recommendation system usually trains a global model on the server without direct access to users' private data on their own devices. However, this separation of the recommendation model and users' private data poses a challenge in providing quality service, particularly when it comes to new items, namely cold-start recommendations in federated settings. This paper introduces a novel method called Item-aligned Federated Aggregation (IFedRec) to address this challenge. It is the first research work in federated recommendation to specifically study the cold-start scenario. The proposed method learns two sets of item representations by leveraging item attributes and interaction records simultaneously. Additionally, an item representation alignment mechanism is designed to align two item representations and learn the meta attribute network at the server within a federated learning framework. Experiments on four benchmark datasets demonstrate IFedRec's superior performance for cold-start scenarios. Furthermore, we also verify IFedRec owns good robustness when the system faces limited client participation and noise injection, which brings promising practical application potential in privacy-protection enhanced federated recommendation systems. The implementation code is available © 2024 ACM.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Generative Classifier for Domain Generalization

arXiv

引用

arXiv 2025年

作者： Long, Shaocong Zhou, Qianyu Li, Xiangtai Ying, Chenhao Tong, Yunhai Ma, Lizhuang Luo, Yuan Tao, Dacheng Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun China Nanyang Technological University Singapore Peking University Beijing China

Domain generalization (DG) aims to improve the generalizability of computer vision models toward distribution shifts. The mainstream DG methods predominantly focus on learning domain invariance across domains, however, such methods overlook the untapped potential inherent in domain-specific information. While the prevailing practice of discriminative linear classifier has been tailored to domain-invariant features, it struggles when confronted with diverse domain-specific information, e.g., intra-class shifts, that exhibits multi-modality. To address these issues, we explore the theoretical implications of relying on domain-invariant features, revealing the crucial role of domain-specific information in mitigating the target risk for DG. Drawing from these insights, we propose Generative Classifier-driven Domain Generalization (GCDG), introducing a generative paradigm for the DG classifier based on Gaussian Mixture Models (GMMs) for each class across domains. GCDG consists of three key modules: Heterogeneity Learning Classifier (HLC), Spurious Correlation Blocking (SCB), and Diverse Component Balancing (DCB). Concretely, HLC attempts to model the feature distributions and thereby capture valuable domain-specific information via GMMs. SCB identifies the neural units containing spurious correlations and perturbs them, mitigating the risk of HLC learning irrelevant spurious patterns. Meanwhile, DCB ensures a balanced contribution of components within HLC, preventing the underestimation or neglect of critical components. In this way, GCDG excels in capturing the nuances of domain-specific information characterized by diverse distributions. GCDG demonstrates the potential to reduce the target risk and encourage flat minima, improving the model’s generalizability. Extensive experiments show GCDG’s comparable performance on five DG benchmarks and one face anti-spoofing dataset, seamlessly integrating into existing DG methods with consistent improvements. Code will be avail

关键词： Discriminant analysis

来源：评论

学校读者我要写书评

暂无评论

Hybrid Parameter Update: Alleviating Imbalance Impacts for Distributed Deep Learning

Hybrid Parameter Update: Alleviating Imbalance Impacts for D...

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Hongliang Li Dong Xu Zhewen Xu Xiang Li College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education Changchun China

Nowadays, data parallelism has been widely applied to train large datasets on distributed deep learning clusters, but it has suffered from costly global parameter updates at batch barriers. Performance imbalance among worker instances, introduced by uneven workload partitioning or biased resource allocation, can cause straggly workers, which can lead to severe impacts on both training speed and result accuracy. This paper studies the issue focusing on the tradeoff between training speed and result accuracy. We propose Cooperate Grouping Parallel (CGP), a hybrid parameter update solution that allows the flexibility of both synchronous and asynchronous update schemes. We introduce a novel Cooperate Worker Grouping Problem (CWGP) that seeks a task grouping configuration that leads to maximum model accuracy and holds customized training speed guarantees. We propose an evolution-based Pareto local searching algorithm to compute efficient worker grouping configurations. Comprehensive evaluation results are presented to demonstrate the effectiveness of CGP under both persistent and fluctuant imbalances. The proposed method alleviates the imbalance impacts without introducing extra adjustment over-heads.

关键词： Training Deep learning computational modeling Focusing Distributed databases Parallel processing Resource management

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：