检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Huang, Junjie Shen, Huawei Cao, Qi Tao, Shuchang Cheng, Xueqi Data Intelligence System Research Center Institute of Computing Technology Chinese Academy of Sciences Beijing China CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

Signed networks are such social networks having both positive and negative links. A lot of theories and algorithms have been developed to model such networks (e.g., balance theory). However, previous work mainly focuses on the unipartite signed networks where the nodes have the same type. Signed bipartite networks are different from classical signed networks, which contain two different node sets and signed links between two node sets. Signed bipartite networks can be commonly found in many fields including business, politics, and academics, but have been less studied. In this work, we firstly define the signed relationship of the same set of nodes and provide a new perspective for analyzing signed bipartite networks. Then we do some comprehensive analysis of balance theory from two perspectives on several real-world datasets. Specifically, in the peer review dataset, we find that the ratio of balanced isomorphism in signed bipartite networks increased after rebuttal phases. Guided by these two perspectives, we propose a novel Signed Bipartite Graph Neural networks (SBGNNs) to learn node embeddings for signed bipartite networks. SBGNNs follow most GNNs message-passing scheme, but we design new message functions, aggregation functions, and update functions for signed bipartite networks. We validate the effectiveness of our model on four real-world datasets on Link Sign Prediction task, which is the main machine learning task for signed networks. Experimental results show that our SBGNN model achieves significant improvement compared with strong baseline methods, including feature-based methods and network embedding methods. Copyright © 2021, 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

Dist-PU: Positive-Unlabeled Learning from a Label Distribution Perspective

arXiv

引用

arXiv 2022年

作者： Zhao, Yunrui Xu, Qianqian Jiang, Yangbangyan Wen, Peisong Huang, Qingming School of Computer Science and Technology University of Chinese Academy of Sciences China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS China State Key Laboratory of Information Security Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences China

Positive-Unlabeled (PU) learning tries to learn binary classifiers from a few labeled positive examples with many unlabeled ones. Compared with ordinary semi-supervised learning, this task is much more challenging due to the absence of any known negative labels. While existing cost-sensitive-based methods have achieved state-of-the-art performances, they explicitly minimize the risk of classifying unlabeled data as negative samples, which might result in a negative-prediction preference of the classifier. To alleviate this issue, we resort to a label distribution perspective for PU learning in this paper. Noticing that the label distribution of unlabeled data is fixed when the class prior is known, it can be naturally used as learning supervision for the model. Motivated by this, we propose to pursue the label distribution consistency between predicted and ground-truth label distributions, which is formulated by aligning their expectations. Moreover, we further adopt the entropy minimization and Mixup regularization to avoid the trivial solution of the label distribution consistency on unlabeled data and mitigate the consequent confirmation bias. Experiments on three benchmark datasets validate the effectiveness of the proposed method. Code available at: https://***/Ray-rui/Dist-PU-Positive-UnlabeledLearning-from-a-Label-Distribution-Perspective. Copyright © 2022, The Authors. All rights reserved.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Single node injection attack against graph neural networks

arXiv

引用

arXiv 2021年

作者： Tao, Shuchang Cao, Qi Shen, Huawei Huang, Junjie Wu, Yunfan Cheng, Xueqi Data Intelligence System Research Center Institute of Computing Technology Chinese Academy of Sciences Beijing China CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

Node injection attack on Graph Neural networks (GNNs) is an emerging and practical attack scenario that the attacker injects malicious nodes rather than modifying original nodes or edges to affect the performance of GNNs. However, existing node injection attacks ignore extremely limited scenarios, namely the injected nodes might be excessive such that they may be perceptible to the target GNN. In this paper, we focus on an extremely limited scenario of single node injection evasion attack, i.e., the attacker is only allowed to inject one single node during the test phase to hurt GNN’s performance. The discreteness of network structure and the coupling effect between network structure and node features bring great challenges to this extremely limited scenario. We first propose an optimization-based method to explore the performance upper bound of single node injection evasion attack. Experimental results show that 100%, 98.60%, and 94.98% nodes on three public datasets are successfully attacked even when only injecting one node with one edge, confirming the feasibility of single node injection evasion attack. However, such an optimization-based method needs to be re-optimized for each attack, which is computationally unbearable. To solve the dilemma, we further propose a Generalizable Node Injection Attack model, namely G-NIA, to improve the attack efficiency while ensuring the attack performance. Experiments are conducted across three well-known GNNs. Our proposed G-NIA significantly outperforms state-of-the-art baselines and is 500 times faster than the optimization-based method when inferring. Copyright © 2021, 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

IR-GAN: Image Manipulation with Linguistic Instruction by Increment Reasoning

arXiv

引用

arXiv 2022年

作者： Liu, Zhenhuan Deng, Jincan Li, Liang Cai, Shaofei Xu, Qianqian Wang, Shuhui Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Peng Cheng Laboratory Shenzhen China

Conditional image generation is an active research topic including text2image and image translation. Recently image manipulation with linguistic instruction brings new challenges of multimodal conditional generation. However, traditional conditional image generation models mainly focus on generating high-quality and visually realistic images, and lack resolving the partial consistency between image and instruction. To address this issue, we propose an Increment Reasoning Generative Adversarial network (IR-GAN), which aims to reason the consistency between visual increment in images and semantic increment in instructions. First, we introduce the word-level and instruction-level instruction encoders to learn user's intention from history-correlated instructions as semantic increment. Second, we embed the representation of semantic increment into that of source image for generating target image, where source image plays the role of referring auxiliary. Finally, we propose a reasoning discriminator to measure the consistency between visual increment and semantic increment, which purifies user's intention and guarantees the good logic of generated target image. Extensive experiments and visualization conducted on two datasets show the effectiveness of IR-GAN. © 2022, CC BY.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Multi-Channel Hypergraph network for Sequential Diagnosis Prediction in Healthcare

Multi-Channel Hypergraph Network for Sequential Diagnosis Pr...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Xin Zhang Xueping Peng Weimin Chen Weiyu Zhang Xiaoqiang Ren Wenpeng Luv Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Australian Artificial Intelligence Institute University of Technology Sydney Sydney Australia Shandong Mental Health Center Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Sequential diagnosis prediction (SDP) is a complex and challenging task, aming to predict future diagnoses of patients by analyzing their historical medical records. Although graph neural networks(GNNs) has been applied to successfully address the challenge of heterogeneous data integration in electronic health records, relatively limited work has been done on GNNs for sequential diagnosis prediction. Graph neural network-based methods, aimed at capturing structural and relational patterns of EHR data for sequential diagnosis prediction, explore code-code pairwise relationships, resulting in an inability to learn fine-grained, higher-order interaction relationships among different types medical codes. As a result, they are difficult to effectively model complex, multi-dimensional interactions among different types of medical codes necessary for accurate and nuanced diagnosis predictions. To address these challenges, this paper proposes a novel approach called Multi-Channel Hypergraph network (MCHN) predictive framework for sequential diagnosis prediction. The proposed method aims to explore the fine-grained higher-order interactions between different types of medical codes via multi-channel hypergraphs. Specifically, MCHN learns two levels of code embeddings from multi-channel hypergraph learning module and line graph learning module, respectively: (i) multi-channel hypergraph learning module, which is to learn multi-channel hypergraph level code embeddings by modeling the higher-order relationships between medical codes in different hypergraphs; and (ii) line graph learning module, which is to learn the line graph level code embeddings by modeling code-code pairwise relationships. In MCHN, we propose a novel channel-level attention mechanism to help our model attend to the informativeness of the different channel for forecasting future patient diagnoses. We also design a code-level attention mechanism, which can to pay more attention to the medical codes that are m

关键词： Codes Attention mechanisms Federated learning Medical services Predictive models Benchmark testing Sequential diagnosis

来源：评论

学校读者我要写书评

暂无评论

Snake net with a neural network for detecting multiple phases in the phase diagram

引用

Physical Review E 2023年第6期107卷 065303-065303页

作者： Xiaodong Sun Huijiong Yang Nan Wu T. C. Scott Jie Zhang Wanzhou Zhang College of Physics and Optoelectronics Taiyuan University of Technology Shanxi 030024 China College of Data Science Taiyuan University of Technology Shanxi 030024 China School for Physical Sciences University of Science and Technology of China Hefei 230026 China Institut für Physikalische Chemie RWTH Aachen University Aachen 52056 Germany Hefei National Laboratory for Physical Sciences at the Microscale and Department of Modern Physics University of Science and Technology of China Hefei 230026 China CAS Key Laboratory for Theoretical Physics Institute of Theoretical Physics Chinese Academy of Sciences Beijing 100190 China

Unsupervised machine learning applied to the study of phase transitions is an ongoing and interesting research direction. The active contour model, also called the snake model, was initially proposed for target contour extraction in two-dimensional images. In order to obtain a physical phase diagram, the snake model with an artificial neural network is applied in an unsupervised learning way by the authors of [Phys. Rev. Lett. 120, 176401 (2018)]. It guesses the phase boundary as an initial snake and then drives the snake to convergence with forces estimated by the artificial neural network. In this work we extend this unsupervised learning method with one contour to a snake net with multiple contours for the purpose of obtaining several phase boundaries in a phase diagram. For the classical Blume-Capel model, the phase diagram containing three and four phases is obtained. Moreover, a balloon force is introduced, which helps the snake to leave a wrong initial position and thus may allow for greater freedom in the initialization of the snake. Our method is helpful in determining the phase diagram with multiple phases using just snapshots of configurations from cold atoms or other experiments without knowledge of the phases.

关键词： Phase diagrams Artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

Modeling the Relative Visual Tempo for Self-supervised Skeleton-based Action Recognition

Modeling the Relative Visual Tempo for Self-supervised Skele...

引用

International Conference on Computer Vision (ICCV)

作者： Yisheng Zhu Hu Han Zhengtao Yu Guangcan Liu Nanjing University of Posts and Telecommunications Key Laboratory of Intelligent Information Processing Institute of Computing Technology (ICT) Chinese Academy of Sciences (CAS) University of the Chinese Academy of Sciences Faculty of Information Engineering and Automation Kunming University of Science and Technology School of Automation Southeast University

Visual tempo characterizes the dynamics and the temporal evolution, which helps describe actions. Recent approaches directly perform visual tempo prediction on skeleton sequences, which may suffer from insufficient feature representation issue. In this paper, we observe that relative visual tempo is more in line with human intuition, and thus providing more effective supervision signals. Based on this, we propose a novel Relative Visual Tempo Contrastive Learning framework for skeleton action Representation (RVTCLR). Specifically, we design a Relative Visual Tempo Learning (RVTL) task to explore the motion information in intra-video clips, and an Appearance-Consistency (AC) task to learn appearance information simultaneously, resulting in more representative spatiotemporal features. Furthermore, skeleton sequence data is much sparser than RGB data, making the network learn shortcuts, and overfit to low-level information such as skeleton scales. To learn high-order semantics, we further design a new Distribution-Consistency (DC) branch, containing three components: Skeleton-specific data Augmentation (S-DA), Fine-grained Skeleton Encoding Module (FSEM), and Distribution-aware Diversity (DD) Loss. We term our entire method (RVTCLR with DC) as RVTCLR+. Extensive experiments on NTU RGB+D 60 and NTU RGB+D 120 datasets demonstrate that our RVTCLR+ can achieve competitive results over the state-of-the-art methods. Code is available at https://***/Zhuysheng/RVTCLR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Predictive Framework for Shipborne Wind Speed Measurement Correction Based on Self-Supervised Contrastive Learning

A Predictive Framework for Shipborne Wind Speed Measurement ...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Jian Song Xiang Li Zhenqiang Zhang Zhigang Zhao Chunxiao Wang Shunfang Wu Suiping Qi Jialiang Lv Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Key Laboratory of Computing Power Network and Information Security Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Institute of Oceanographic Instrumentation Qilu University of Technology (Shandong Academy of Sciences) Qingdao China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Accurate measurement of wind speed on maritime vessels is crucial for weather and sea condition forecasting, safe navigation, power generation, hydrological simulation, and other applications. However, the precision of measurements may be subject to certain errors due to factors such as vessel motion and environmental conditions. To enhance the precision of shipborne wind speed measurement, this paper introduces an innovative approach based on contrastive learning. Through proficient feature extraction and the application of a self-supervised contrastive learning algorithm, this method extracts features of varying granularity from marine observational data to predict and correct shipborne wind speed measurements. To the best of our knowledge, this study represents the first attempt to validate contrastive learning in the intelligent analysis of marine observational data. Validation experiment results demonstrate the outstanding performance of this method in both single-step and multi-step predictions, showcasing higher efficacy and robustness compared to alternative approaches.

关键词： Accuracy Power measurement Wind speed Time series analysis Sea measurements Contrastive learning Predictive models

来源：评论

学校读者我要写书评

暂无评论

An efficient quantum algorithm for independent component analysis

arXiv

引用

arXiv 2023年

作者： Xu, Xiao-Fan Xue, Cheng Chen, Zhao-Yun Wu, Yu-Chun Guo, Guo-Ping CAS Key Laboratory of Quantum Information University of Science and Technology of China Hefei230026 China CAS Center for Excellence in Quantum Information and Quantum Physics University of Science and Technology of China Hefei230026 China Hefei National Laboratory University of Science and Technology of China Hefei230088 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Anhui Hefei230026 China Origin Quantum Computing Company Limited Anhui Hefei230026 China

Independent component analysis (ICA) is a fundamental data processing technique to decompose the captured signals into as independent as possible components. computing the contrast function, which serves as a measure of independence of signals, is vital in the separation process using ICA. This paper presents a quantum ICA algorithm which focuses on computing a specified contrast function on a quantum computer. Using the quantum acceleration in matrix operations, we efficiently deal with Gram matrices and estimate the contrast function with the complexity of O(Ε1−2polylog(N/Ε1)). This estimation subprogram, combined with the classical optimization framework, enables our quantum ICA algorithm, which exponentially reduces the complexity dependence on the data scale compared with classical algorithms. The outperformance is further supported by numerical experiments, while a source separation of a transcriptomic dataset is shown as an example of application. © 2023, CC0.

关键词： data handling

来源：评论

学校读者我要写书评

暂无评论

Prefrontal Internal Event-Driven Analysis of Dynamical Electroencephalographic Biomarkers in Depression During Emotional Auditory Task

SSRN

引用

SSRN 2024年

作者： Zhao, Qinglin Cui, Kunbo Jiang, Hua Wu, Zhongqing Zhang, Lixin Zhao, Mingqi Hu, Bin Gansu Provincial Key Laboratory of Wearable Computing School of Information Science and Engineering Lanzhou University Lanzhou730000 China School of Medical Technology Beijing Institute of Technology Beijing100081 China CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai Institutes for Biological Sciences Chinese Academy of Sciences Shanghai200000 China Joint Research Center for Cognitive Neurosensor Technology Lanzhou University Institute of Semiconductors Chinese Academy of Sciences Lanzhou730000 China

The prefrontal cortex is considered as one of the key brain regions for the study of affective dysfunction in depression. The study of neural processes in this region during specific emotional tasks may enhance our understanding on the mechanisms of depression. One powerful, direct and convenient tool is electroencephalography (EEG);yet in many experimental paradigms, the absence of external events limits the effectiveness of resolving such emotional task-specific prefrontal and brain-wide electroencephalographic dynamics. To address this issue, we analyzed 64-channel EEG data acquired from 55 healthy and 55 depressed participants during a three-polar (positive, neutral and negative) emotional auditory task in a prefrontal internal event-driven approach. Specifically, we extracted depression-related prefrontal internal events according to signals acquired from Fp1, Fpz, and Fp2 by statistically comparing the microstates identified with an unsupervised Gaussian mixture model. We then examined such event-related neural dynamics in terms of power change in neural oscillations and cross-oscillation interaction in a reconstructed brain source space. Our results suggested that the prefrontal events can be used to resolve abnormal neural dynamics in depression. Our results revealed emotional process-specific and internal event-related abnormalities dynamically in the brain source space, as evaluated by internal event-related changes in power of neural oscillations and in modulations of low frequency phases to high frequency amplitudes. Overall, our findings present new insights for dynamical electroencephalographic biomarkers in depression, which potentially provide EEG signal decoding solutions for EEG feedback-based closed loop intervention of depression. © 2024, The Authors. All rights reserved.

关键词： Electroencephalography

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：