检索结果-内蒙古大学图书馆

Cumulative activation in social networks

science China(Information sciences) 2019年第5期62卷 108-128页

作者： Xiaohan SHAN Wei CHEN Qiang LI Xiaoming SUN Jialin ZHANG Department of Computer Science and Technology Tsinghua University Microsoft CAS Key Lab of Network Data Science and Technology Institute of Computing TechnologyChinese Academy of Sciences University of Chinese Academy of Sciences

Most studies on influence maximization focus on one-shot propagation, i.e., the influence is propagated from seed users only once following a probabilistic diffusion model and users' activation are determined via single cascade. In reality it is often the case that a user needs to be cumulatively impacted by receiving enough pieces of information propagated to her before she makes the final purchase decision. In this paper we model such cumulative activation as the following process: first multiple pieces of information are propagated independently in the social network following the classical independent cascade model, then the user will be activated(and adopt the product) if the cumulative pieces of information she received reaches her cumulative activation threshold. Two optimization problems are investigated under this framework: seed minimization with cumulative activation(SM-CA), which asks how to select a seed set with minimum size such that the number of cumulatively active nodes reaches a given requirement η; influence maximization with cumulative activation(IM-CA), which asks how to choose a seed set with fixed budget to maximize the number of cumulatively active nodes. For SM-CA problem, we design a greedy algorithm that yields a bicriteria O(ln n)-approximation when η = n, where n is the number of nodes in the network. For both SM-CA problem with η < n and IM-CA problem, we prove strong inapproximability results. Despite the hardness results, we propose two efficient heuristic algorithms for SM-CA and IM-CA respectively based on the reverse reachable set approach. Experimental results on different real-world social networks show that our algorithms significantly outperform baseline algorithms.

关键词： social networks cumulative activation influence maximization seed minimization

来源：评论

学校读者我要写书评

暂无评论

A Novel Configurable High-precision and Low-cost Circuit Design of Sigmoid and Tanh Activation Function

A Novel Configurable High-precision and Low-cost Circuit Des...

引用

IEEE International Conference on Integrated Circuits, Technologies and Applications (ICTA)

作者： Feng Liu Bowen Zhang Gang Chen Guoliang Gong Huaxiang Lu Wenchang Li Institute of Semiconductors Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Semiconductor Neural Network Intelligent Perception and Computing Technology Beijing Key Lab Beijing China Center for Excellence in Brain Science and Intelligence Technology CAS Shanghai China

ISBN: (纸本)9781665417488

This paper proposes a configurable Sigmoid and Tanh activation function circuit design by second-order approximation and deviation compensation. The proposed circuit is synthesized in TSMC 180nm technology within a 7218 um 2 area at 500MHz, it is also deployed on Xilinx ZC706 FPGA by 158 LUTs and 46 FFs at 333MHz. It achieves almost 4.68× better precision and 20.2% less area than previous works. The experimental results show that our method has almost no accuracy loss on LSTM Chinese speech recognition tasks and the YOLOv3 image recognition post-processing task.

关键词： Integrated circuit technology Image recognition Costs Conferences Speech recognition Hardware Circuit synthesis

来源：评论

学校读者我要写书评

暂无评论

Novel node classification framework

arXiv

引用

arXiv 2019年

作者： Cen, Keting Shen, Huawei Gao, Jinhua Cao, Qi Xu, Bingbing Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology

GCN is a recent effective algorithm which effectively learns a function incorporate both graph structure and node features for semisupervised graph based node classification. Although GCN exceeds other state-of-the-art methods, the number of parameters that need to be learned are still significantly more than the number of used samples. Because only labeled nodes and their 2-hop neighbors are used for learning parameters in GCN. As a consequence the accuracy of node classification declines sharply when decreasing the size of train data. In order to reducing parameters and making better use of unlabeled nodes, we proposes to use unsupervised representation algorithm such as autoencoder to pretrain a embedding for each node, which captures effective information from input features and reduce parameters in graph convolution layers. Experiments show that our model has increased by 0.87%, 1.96%, 1.87% compared to baseline on Cora, Citeseer and Pubmed data respectively. The performance of our model declines slower than GCN when decreasing the train samples. Copyright © 2019, The Authors. All rights reserved.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

label-consistency based graph neural networks for semi-supervised node classification

arXiv

引用

arXiv 2020年

作者： Xu, Bingbing Huang, Junjie Hou, Liang Shen, Huawei Gao, Jinhua Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China School of Computer and Control Engineering University of Chinese Academy of Sciences China

Graph neural networks (GNNs) achieve remarkable success in graph-based semi-supervised node classification, leveraging the information from neighboring nodes to improve the representation learning of target node. The success of GNNs at node classification depends on the assumption that connected nodes tend to have the same label. However, such an assumption does not always work, limiting the performance of GNNs at node classification. In this paper, we propose label-consistency based graph neural network (LC-GNN), leveraging node pairs unconnected but with the same labels to enlarge the receptive field of nodes in GNNs. Experiments on benchmark datasets demonstrate the proposed LC-GNN outperforms traditional GNNs in graph-based semi-supervised node classification. We further show the superiority of LC-GNN in sparse scenarios with only a handful of labeled nodes. Copyright © 2020, 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

Quantum Lovász local lemma: Shearer’s bound is tight 2019

Quantum Lovász local lemma: Shearer’s bound is tight

引用

51st Annual ACM SIGACT Symposium on Theory of Computing, STOC 2019

作者： He, Kun Li, Qian Sun, Xiaoming Zhang, Jiapeng CAS Key Lab of Network Data Science and Technology Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China Shenzhen Institute of Computing Sciences Shenzhen University China University of California San DiegoCA United States

ISBN: (纸本)9781450367059

Lovász Local Lemma (LLL) is a very powerful tool in combinatorics and probability theory to show the possibility of avoiding all "bad" events under some "weakly dependent" condition. Over the last decades, the algorithmic aspect of LLL has also attracted lots of attention in theoretical computer science. A tight criterion under which the abstract version LLL (ALLL) holds was given by Shearer. It turns out that Shearer’s bound is generally not tight for variable version LLL (VLLL). Recently, Ambainis et al. introduced a quantum version LLL (QLLL), which was then shown to be powerful for the quantum satisfiability problem. In this paper, we prove that Shearer’s bound is tight for QLLL, i.e., the relative dimension of the smallest satisfying subspace is completely characterized by the independent set polynomial, affirming a conjecture proposed by Sattath et al. Our result also shows the tightness of Gilyén and Sattath’s algorithm, and implies that the lattice gas partition function fully characterizes quantum satisfiability for almost all Hamiltonians with large enough qudits. Commuting LLL (CLLL), LLL for commuting local Hamiltonians which are widely studied in the literature, is also investigated here. We prove that the tight regions of CLLL and QLLL are different in general. This result might imply that it is possible to design an algorithm for CLLL which is still efficient beyond Shearer’s bound. In applications of LLLs, the symmetric cases are most common, i.e., the events are with the same probability and the Hamiltonians are with the same relative dimension. We give the first lower bound on the gap between the symmetric VLLL and Shearer’s bound. Our result can be viewed as a quantitative study on the separation between quantum and classical constraint satisfaction problems. Additionally, we obtain similar results for the symmetric CLLL. As an application, we give lower bounds on the critical thresholds of VLLL and CLLL for several of the most common lattices. ©

关键词： Hamiltonians

来源：评论

学校读者我要写书评

暂无评论

Graph wavelet neural network 7

Graph wavelet neural network

引用

7th International Conference on Learning Representations, ICLR 2019

作者： Xu, Bingbing Shen, Huawei Cao, Qi Qiu, Yunqi Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing China

We present graph wavelet neural network (GWNN), a novel graph convolutional neural network (CNN), leveraging graph wavelet transform to address the shortcomings of previous spectral graph CNN methods that depend on graph Fourier transform. Different from graph Fourier transform, graph wavelet transform can be obtained via a fast algorithm without requiring matrix eigendecomposition with high computational cost. Moreover, graph wavelets are sparse and localized in vertex domain, offering high efficiency and good interpretability for graph convolution. The proposed GWNN significantly outperforms previous spectral graph CNNs in the task of graph-based semi-supervised classification on three benchmark datasets: Cora, Citeseer and Pubmed. © 7th International Conference on Learning Representations, ICLR 2019. All Rights Reserved.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Meta Mask Correction for Nuclei Segmentation in Histopathological Image

Meta Mask Correction for Nuclei Segmentation in Histopatholo...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Shi, Jiangbo Jia, Chang Gao, Zeyu Gong, Tieliang Wang, Chunbao Li, Chen Xi'An Jiao Tong University National Engineering Lab for Big Data Analytics Shaanxi Xi'an710049 China School of Computer Science and Technology Xi'An Jiao Tong University Shaanxi Xi'an710049 China Shaanxi Province Key Laboratory of Satellite and Terrestrial Network Tech.RandD Xi'An Jiao Tong University Shaanxi Xi'an710049 China Department of Pathology The First Affiliated Hospital of xi'An Jiaotong University Shaanxi Xi'an710061 China

ISBN: (纸本)9781665401265

Nuclei segmentation is a fundamental task in digital pathology analysis and can be automated by deep learning-based methods. However, the development of such an automated method requires a large amount of data with precisely annotated masks which is hard to obtain. Training with weakly labeled data is a popular solution for reducing the workload of annotation. In this paper, we propose a novel meta-learning-based nuclei segmentation method which follows the label correction paradigm to leverage data with noisy masks. Specifically, we design a fully conventional meta-model that can correct noisy masks using a small amount of clean meta-data. Then the corrected masks can be used to supervise the training of the segmentation model. Meanwhile, a bi-level optimization method is adopted to alternately update the parameters of the main segmentation model and the meta-model in an end-to-end way. Extensive experimental results on two nuclear segmentation datasets show that our method achieves the state-of-the-art result. It even achieves comparable performance with the model training on supervised data in some noisy settings. © 2021 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Semantics-Guided Contrastive network for Zero-Shot Object Detection

arXiv

引用

arXiv 2021年

作者： Yan, Caixia Chang, Xiaojun Luo, Minnan Liu, Huan Zhang, Xiaoqin Zheng, Qinghua The Ministry of Education Key Lab of Intelligent Networks and Network Security National Engineering Lab for Big Data Analytics School of Electronic and Information Engineering Xi'an Jiaotong University Shaanxi710049 China The ReLER Lab AAAI Faculty of Engineering and Information Technology University of Technology Sydney Australia The College of Computer Science and Artificial Intelligence Wenzhou University China

Zero-shot object detection (ZSD), the task that extends conventional detection models to detecting objects from unseen categories, has emerged as a new challenge in computer vision. Most existing approaches tackle the ZSD task with a strict mapping-transfer strategy that may lead to suboptimal ZSD results: 1) the learning process of these models neglects the available semantic information on unseen classes, which can easily bias towards the seen categories;2) the original visual feature space is not well-structured for the ZSD task due to the lack of discriminative information. To address these issues, we develop a novel Semantics-Guided Contrastive network for ZSD, named ContrastZSD, a detection framework that first brings contrastive learning mechanism into the realm of zero-shot detection. Particularly, ContrastZSD incorporates two semantics-guided contrastive learning subnets that contrast between region-category and region-region pairs respectively. The pairwise contrastive tasks take advantage of supervision signals derived from both the ground truth label and class similarity information. By performing supervised contrastive learning over those explicit semantic supervision, the model can learn more knowledge about unseen categories to avoid the bias problem to seen concepts, while optimizing the visual data structure to be more discriminative for better visual-semantic alignment. Extensive experiments are conducted on two popular benchmarks for ZSD, i.e., PASCAL VOC and MS COCO. Results show that our method outperforms the previous state-of-the-art on both ZSD and generalized ZSD tasks. © 2021, CC BY.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Long-distance entanglement purification for quantum communication

arXiv

引用

arXiv 2021年

作者： Hu, Xiao-Min Huang, Cen-Xiao Sheng, Yu-Bo Zhou, Lan Liu, Bi-Heng Guo, Yu Zhang, Chao Xing, Wen-Bo Huang, Yun-Feng Li, Chuan-Feng Guo, Guang-Can CAS Key Laboratory of Quantum Information University of Science and Technology of China Hefei230026 China Institute of Quantum Information and Technology Nanjing University of Posts and Telecommunications Nanjing210003 China College of Mathematics & Physics Nanjing University of Posts and Telecommunications Nanjing210003 China CAS Center For Excellence in Quantum Information and Quantum Physics University of Science and Technology of China Hefei230026 China Key Lab of Broadband Wireless Communication and Sensor Network Technology Nanjing University of Posts and Telecommunications Ministry of Education Nanjing210003 China

High quality long-distance entanglement is essential for both quantum communication and scalable quantum networks. Entanglement purification is to distill high-quality entanglement from low-quality entanglement in a noisy environment and it plays a key role in quantum repeaters. The previous significant entanglement purification experiments require two pairs of low-quality entangled states and were demonstrated in table-top. Here we propose and report a high-efficiency and long-distance entanglement purification using only one pair of hyperentangled state. We also demonstrate its practical application in entanglement-based quantum key distribution (QKD). One pair of polarization spatial-mode hyperentanglement was distributed over 11 km multicore fiber (noisy channel). After purification, the fidelity of polarization entanglement arises from 0.771 to 0.887 and the effective key rate in entanglement-based QKD increases from 0 to 0.332. The values of Clauser-Horne-Shimony-Holt (CHSH) inequality of polarization entanglement arises from 1.829 to 2.128. Moreover, by using one pair of hyperentanglement and deterministic controlled-NOT gate, the total purification efficiency can be estimated as 6.6 × 103 times than the experiment using two pairs of entangled states with spontaneous parametric down conversion (SPDC) sources. Our results offer the potential to be implemented as part of a full quantum repeater and large scale quantum network. Copyright © 2021, The Authors. All rights reserved.

关键词： Quantum communication

来源：评论

学校读者我要写书评

暂无评论

Optimal algorithm for profiling dynamic arrays with finite values 22

Optimal algorithm for profiling dynamic arrays with finite v...

引用

22nd International Conference on Extending database technology, EDBT 2019

作者： Yang, Dingcheng Yu, Wenjian Deng, Junhui Liu, Shenghua BNRist Dept. Computer Science and Tech. Tsinghua Univ. Beijing China CAS Key Lab. Network Data Science and Tech. Inst. Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783893180813

How can one quickly answer the most and top popular objects at any time, given a large log stream in a system of billions of users? It is equivalent to find the mode and top-frequent elements in a dynamic array corresponding to the log stream. However, most existing work either restrain the dynamic array within a sliding window, or do not take advantages of only one element can be added or removed in a log stream. Therefore, we propose a profiling algorithm, named S-Profile, which is of O(1) time complexity for every updating of the dynamic array, and optimal in terms of computational complexity. With the profiling results, answering the queries on the statistics of dynamic array becomes trivial and fast. With the experiments of various settings of dynamic arrays, our accurate S-Profile algorithm outperforms the existing methods, showing at least 2X speedup to the heap based approach and 13X speedup to the balanced tree based approach. © 2019 Copyright held by the owner/author(s).

关键词： Trees (mathematics)

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：