检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on Machine Learning

作者： Xingcheng Fu Yisen Gao Yuecen Wei Qingyun Sun Hao Peng Jianxin Li Xianxian Li Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China Institute of Artificial Intelligence Beihang University Beijing China and Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China School of Software Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing School of Computer Science and Engineering Beihang University Beijing China

Diffusion models have made significant contributions to computer vision, sparking a growing interest in the community recently regarding the application of them to graph generation. Existing discrete graph diffusion models exhibit heightened computational complexity and diminished training efficiency. A preferable and natural way is to directly diffuse the graph within the latent space. However, due to the non-Euclidean structure of graphs is not isotropic in the latent space, the existing latent diffusion models effectively make it difficult to capture and preserve the topological information of graphs. To address the above challenges, we propose a novel geometrically latent diffusion framework HypDiff. Specifically, we first establish a geometrically latent space with interpretability measures based on hyperbolic geometry, to define anisotropic latent diffusion processes for graphs. Then, we propose a geometrically latent diffusion process that is constrained by both radial and angular geometric properties, thereby ensuring the preservation of the original topological properties in the generative graphs. Extensive experimental results demonstrate the superior effectiveness of HypDiff for graph generation with various topologies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Event detection and evolution in multi-lingual social streams

引用

Frontiers of Computer Science 2020年第5期14卷 213-227页

作者： Yaopeng Liu Hao Peng Jianxin Li Yangqiu Song Xiong Li Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang UniversityBeijing100083China State Key Laboratory of Software Development Environment Beihang UniversityBeijing100083China Department of Computer Science and Engineering HKUSTHong Kong99907China National Computer Network Emergency Response Technical Team/Coordination Center of China Beijing100029China

Real-life events are emerging and evolving in social and news *** methods have succeeded in capturing designed features of monolingual events,but lack of interpretability and multi-lingual *** this end,we propose a multi-lingual event mining model,namely MLEM,to automatically detect events and generate evolution graph in multilingual hybrid-length text streams including English,Chinese,French,German,Russian and ***,we merge the same entities and similar phrases and present multiple similarity measures by incremental word2vec *** propose an 8-tuple to describe event for correlation analysis and evolution graph *** evaluate the MLEM model using a massive human-generated dataset containing real world *** results show that our new model MLEM outperforms the baseline method both in efficiency and effectiveness.

关键词： event detection event evolution stream processing multi-lingual anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Quantum Graph Convolutional Neural Networks

Quantum Graph Convolutional Neural Networks

引用

第40届中国控制会议

作者： Jin Zheng Qing Gao Yanxuan Lü School of Automation Science and Electrical Engineering Beihang University Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University

At present, there are a large number of quantum neural network models to deal with Euclidean spatial data, while little research have been conducted on non-Euclidean spatial data. In this paper, we propose a novel quantum graph convolutional neural network（QGCN） model based on quantum parametric circuits and utilize the computing power of quantum systems to accomplish graph classification tasks in traditional machine learning. The proposed QGCN model has a similar architecture as the classical graph convolutional neural networks, which can illustrate the topology of the graph type data and efficiently learn the hidden layer representation of node features as well. Numerical simulation results on a graph dataset demonstrate that the proposed model can be effectively trained and has good performance in graph level classification tasks.

关键词： Quantum machine learning Quantum computing Quantum graph convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Aware Relational Graph Neural Network for Few-Shot Knowledge Graph Completion

arXiv

引用

arXiv 2024年

作者： Li, Qian Guo, Shu Chen, Yingjia Ji, Cheng Sheng, Jiawei Li, Jianxin Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100083 China The State Key Laboratory of Software Development Environment Beihang University Beijing100083 China National Computer Network Emergency Response Technical Team Coordination Center of China Beijing100083 China School of Mathematics Edinburgh University Edinburgh United Kingdom Institute of Information Engineering Chinese Academy of Sciences Beijing100083 China School of Cyber Security University of Chinese Academy of Sciences Beijing100083 China

Few-shot knowledge graph completion (FKGC) aims to query the unseen facts of a relation given its few-shot reference entity pairs. The side effect of noises due to the uncertainty of entities and triples may limit the few-shot learning, but existing FKGC works neglect such uncertainty, which leads them more susceptible to limited reference samples with noises. In this paper, we propose a novel uncertainty-aware few-shot KG completion framework (UFKGC) to model uncertainty for a better understanding of the limited data by learning representations under Gaussian distribution. Uncertainty representation is first designed for estimating the uncertainty scope of the entity pairs after transferring feature representations into a Gaussian distribution. Further, to better integrate the neighbors with uncertainty characteristics for entity features, we design an uncertainty-aware relational graph neural network (UR-GNN) to conduct convolution operations between the Gaussian distributions. Then, multiple random samplings are conducted for reference triples within the Gaussian distribution to generate smooth reference representations during the optimization. The final completion score for each query instance is measured by the designed uncertainty optimization to make our approach more robust to the noises in few-shot scenarios. Experimental results show that our approach achieves excellent performance on two benchmark datasets compared to its competitors. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

MG-DVD: A real-time framework for malware variant detection based on dynamic heterogeneous graph learning

arXiv

引用

arXiv 2021年

作者： Liu, Chen Li, Bo Zhao, Jun Su, Ming Liu, Xu-Dong School of Computer Science and Engineering Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University China

Detecting the newly emerging malware variants in real time is crucial for mitigating cyber risks and proactively blocking intrusions. In this paper, we propose MG-DVD, a novel detection framework based on dynamic heterogeneous graph learning, to detect malware variants in real time. Particularly, MG-DVD first models the fine-grained execution event streams of malware variants into dynamic heterogeneous graphs and investigates real-world meta-graphs between malware objects, which can effectively characterize more discriminative malicious evolutionary patterns between malware and their variants. Then, MG-DVD presents two dynamic walk-based heterogeneous graph learning methods to learn more comprehensive representations of malware variants, which significantly reduces the cost of the entire graph retraining. As a result, MG-DVD is equipped with the ability to detect malware variants in real time, and it presents better interpretability by introducing meaningful meta-graphs. Comprehensive experiments on large-scale samples prove that our proposed MG-DVD outperforms state-of-the-art methods in detecting malware variants in terms of effectiveness and efficiency. Copyright © 2021, The Authors. All rights reserved.

关键词： Malware

来源：评论

学校读者我要写书评

暂无评论

Efficient Low-Resolution Face Recognition via Bridge Distillation

arXiv

引用

arXiv 2024年

作者： Ge, Shiming Zhao, Shengwei Li, Chenyu Zhang, Yu Li, Jia The Institute of Information Engineering Chinese Academy of Sciences Beijing100095 China School of Cyber Security University of Chinese Academy of Sciences Beijing100049 China SenseTime Group Limited 100084 China The State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University China The Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China The Peng Cheng Laboratory Shenzhen518055 China

Face recognition in the wild is now advancing towards light-weight models, fast inference speed and resolution-adapted capability. In this paper, we propose a bridge distillation approach to turn a complex face model pretrained on private high-resolution faces into a light-weight one for low-resolution face recognition. In our approach, such a cross-dataset resolution-adapted knowledge transfer problem is solved via two-step distillation. In the first step, we conduct cross-dataset distillation to transfer the prior knowledge from private high-resolution faces to public high-resolution faces and generate compact and discriminative features. In the second step, the resolution-adapted distillation is conducted to further transfer the prior knowledge to synthetic low-resolution faces via multi-task learning. By learning low-resolution face representations and mimicking the adapted high-resolution knowledge, a light-weight student model can be constructed with high efficiency and promising accuracy in recognizing low-resolution faces. Experimental results show that the student model performs impressively in recognizing low-resolution faces with only 0.21M parameters and 0.057MB memory. Meanwhile, its speed reaches up to 14,705, 934 and 763 faces per second on GPU, CPU and mobile phone, respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Distributed time-varying formation control with uncertainties based on an event-triggered mechanism

引用

Science China(Information Sciences) 2021年第3期64卷 167-176页

作者： Xiaoduo LI Yumeng BAI Xiwang DONG Qingdong LI Zhang REN Science and Technology on Aircraft Control Laboratory School of Automation Science and Electrical EngineeringBeihang University Department of Electrical and Computer Engineering University of Wisconsin-Madison Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University

This paper investigates the distributed time-varying formation(TVF) problems for general linear multi-agent systems(MASs) subject to matched bounded uncertainties based on an adaptive event-triggered mechanism. A TVF protocol was designed with an event-triggered mechanism by introducing adaptive weights into the formation control protocol and triggering condition, and the large chattering phenomenon was avoided by the σ-modification adaptive law. According to the Lyapunov stability theory, proof has been established that the MASs in the presence of uncertainties can realize the expected formation that satisfies the given feasible condition. Finally, an example is provided to verify the effectiveness of the proposed algorithm.

关键词： formation control multi-agent systems event-triggered adaptive control

来源：评论

学校读者我要写书评

暂无评论

DOANet: Point Cloud Registration with Deep Overlap Attention

DOANet: Point Cloud Registration with Deep Overlap Attention

引用

Chinese Automation Congress (CAC)

作者： Haining Guan Qing Gao Baochang Zhang School of Automation Science and Electrical Engineering Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China

ISBN: (纸本)9781665426480

Pairwise point cloud registration is a fundamental task in 3D computer vision and various approaches have been proposed to handle this problem in recent years. Despite the fast evolution of registration algorithms, little attention has been drawn to align point cloud pairs with a low-overlap ratio (≤30%). In this paper, we propose a new neural network architecture named the DOANet, an end-to-end trainable fully convolutional neural network, to deal with the problem of registration with low overlap. In particular, we leverage sparse convolutions to extract robust and discriminative dense features, and further utilize attention mechanisms to explicitly predict the overlap region for point cloud fragments. The receptive field of our local point patches is constrained within the overlap region generated on the fly, which prevents the local point features from being contaminated by geometric information outside the overlap region. Experiments indicate the effectiveness and advantages of our method on both 3DLoMatch (all pairs under 30% overlap-ratio) and 3DMatch and illustrate obvious improvement over the existing results.

关键词： Point cloud compression Computer vision Three-dimensional displays Automation Neural networks Computer architecture Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

CausalTester: Measuring the Consistency of Replicated Services via Causality Semantics

CausalTester: Measuring the Consistency of Replicated Servic...

引用

Asian Test Symposium (ATS)

作者： Yu Tang Le Zhao Wei Yuan Xu Wang Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing China Chengdu Aircraft Design & Research Institute Chengdu China

ISBN: (纸本)9781665440523

Cloud and big data systems often replicate data and prefer weak consistency such as eventual consistency for better scalability and availability. Such weak consistency may produce unexpected and harmful system behaviors, for example, stale reads and conflicting writes. In order to measure the consistency levels and help developers understand the harmful degree, we propose a testing framework called CausalTester to evaluate the causality semantics of replicated systems, including 12 real test cases collected from Twitter, Flickr, Amazon, the corresponding benchmark services, and the automatic detection of causality violation with crash injection. We implement the testing framework and measure the consistency of three widely-used distributed databases. The experimental results show that it is effective to detect the consistency violations for the weak consistency and helpful to find consistency-related bugs if the strong consistency is violated.

关键词： Social networking (online) Image databases Scalability Semantics Multimedia Web sites Computer bugs Blogs

来源：评论

学校读者我要写书评

暂无评论

Two-stage Generative Adversarial Recovery Network for MR brain Images Containing Tumors 9

Two-stage Generative Adversarial Recovery Network for MR Bra...

引用

9th International Conference on Bioinformatics and Biomedical Science, ICBBS 2020

作者： Kong, Meng Zhao, Haifeng Zhang, Shaojie Tang, Zhenyu School of Computer Science and Technology Anhui University HefeiAnhui230601 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China

ISBN: (纸本)9781450388658

brain image registration (BIR) plays an important role in neuroscience. However, for the registration of brain image containing tumors, the existence of tumor could cause great influence to BIR. One possible solution for getting rid of such influence is to recover the tumor brain image to "normal"appearance brain image (no tumor). Most of existing methods for tumor brain image recovery are based on low-rank, which is time consuming and low recovery quality. In this paper, wepropose a novel deep-learning based method for tumor brain image recovery. Specifically, a two-stage generative adversarial network comprising a region recovery stage and an image recovery stage is presented. For the input tumor brain image, the region recovery stage first generates a recovered brain region image containing three different regions (i.e., the gray matter, the white matter and the cerebrospinal fluid). The recovered brain region image is used in the image recovery stage as priori information to get the final "normal"appearance brain image. Both stages are trained under the generative adversarial framework. The experimental results demonstrate that the registration accuracy of tumor brain images can be significantly enhanced by our network as compared to the state-of-the-art image recovery methods. © 2020 ACM.

关键词： Tumors

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：