检索结果-内蒙古大学图书馆

Forward and Backward Information Retention for Accurate Binary Neural Networks

学校读者我要写书评

暂无评论

Forward and Backward Information Retention for Accurate Bina...

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Haotong Qin Ruihao Gong Xianglong Liu Mingzhu Shen Ziran Wei Fengwei Yu Jingkuan Song State Key Lab of Software Development Environment Beihang University Beijing Advanced Innovation Center for Big Data-Based Precision Medicine Beihang University Beijing University of Posts and Telecommunications SenseTime Research Center for Future Media University of Electronic Science and Technology of China

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Weight and activation binarization is an effective approach to deep neural network compression and can accelerate the inference by leveraging bitwise operations. Although many binarization methods have improved the accuracy of the model by minimizing the quantization error in forward propagation, there remains a noticeable performance gap between the binarized model and the full-precision one. Our empirical study indicates that the quantization brings information loss in both forward and backward propagation, which is the bottleneck of training accurate binary neural networks. To address these issues, we propose an Information Retention Network (IR-Net) to retain the information that consists in the forward activations and backward gradients. IR-Net mainly relies on two technical contributions: (1) Libra Parameter Binarization (Libra-PB): simultaneously minimizing both quantization error and information loss of parameters by balanced and standardized weights in forward propagation; (2) Error Decay Estimator (EDE): minimizing the information loss of gradients by gradually approximating the sign function in backward propagation, jointly considering the updating ability and accurate gradients. We are the first to investigate both forward and backward processes of binary networks from the unified information perspective, which provides new insight into the mechanism of network binarization. Comprehensive experiments with various network structures on CIFAR-10 and ImageNet datasets manifest that the proposed IR-Net can consistently outperform state-of-the-art quantization methods.

关键词： Quantization (signal) Training Backpropagation Propagation losses Biological neural networks Information entropy

Exact single-source SimRank computation on large graphs

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wang, Hanzhi Wei, Zhewei Yuan, Ye Du, Xiaoyong Wen, Ji-Rong School of Information Renmin University of China Gaoling School of Artificial Intelligence Renmin University of China School of Computer Science and technology Beijing Institute of Technology MOE Key Lab DEKE Renmin University of China Beijing Key Lab of Big Data Management and Analysis Method Renmin University of China

SimRank is a popular measurement for evaluating the node-to-node similarities based on the graph topology. In recent years, single-source and top-k SimRank queries have received increasing attention due to their applications in web mining, social network analysis, and spam detection. However, a fundamental obstacle in studying SimRank has been the lack of ground truths. The only exact algorithm, Power Method, is computationally infeasible on graphs with more than 106 nodes. Consequently, no existing work has evaluated the actual trade-offs between query time and accuracy on large real-world graphs. In this paper, we present ExactSim, the first algorithm that computes the exact single-source and top-k SimRank results on large graphs. With high probability, this algorithm produces ground truths with a rigorous theoretical guarantee. We conduct extensive experiments on real-world datasets to demonstrate the efficiency of ExactSim. The results show that ExactSim provides the ground truth for any single-source SimRank query with a precision up to 7 decimal places within a reasonable query time. Copyright © 2020, The Authors. All rights reserved.

关键词： Graphic methods

NAS-Count: Counting-by-Density with Neural Architecture Search 16th

学校读者我要写书评

暂无评论

NAS-Count: Counting-by-Density with Neural Architecture Sear...

16th European Conference on Computer Vision, ECCV 2020

作者： Hu, Yutao Jiang, Xiaolong Liu, Xuhui Zhang, Baochang Han, Jungong Cao, Xianbin Doermann, David School of Electronic and Information Engineering Beihang University Beijing China Key Laboratory of Advanced Technologies for Near Space Information Systems Ministry of Industry and Information Technology Beijing China Beijing Advanced Innovation Center for Big Data-Based Precision Medicine Beijing China YouKu Cognitive and Intelligent Lab Alibaba Group Hangzhou China Beihang University Beijing China Computer Science Department Aberystwyth University AberystwythSY23 3FL United Kingdom Department of Computer Science and Engineering University at Buffalo New York United States

ISBN: (纸本)9783030585419

Most of the recent advances in crowd counting have evolved from hand-designed density estimation networks, where multi-scale features are leveraged to address the scale variation problem, but at the expense of demanding design efforts. In this work, we automate the design of counting models with Neural Architecture Search (NAS) and introduce an end-to-end searched encoder-decoder architecture, Automatic Multi-Scale Network (AMSNet). Specifically, we utilize a counting-specific two-level search space. The encoder and decoder in AMSNet are composed of different cells discovered from micro-level search, while the multi-path architecture is explored through macro-level search. To solve the pixel-level isolation issue in MSE loss, AMSNet is optimized with an auto-searched Scale Pyramid Pooling Loss (SPPLoss) that supervises the multi-scale structural information. Extensive experiments on four datasets show AMSNet produces state-of-the-art results that outperform hand-designed models, fully demonstrating the efficacy of NAS-Count. © 2020, Springer Nature Switzerland AG.

关键词： Decoding

Optimizing biomedical ontology alignment in lexical vector space

学校读者我要写书评

暂无评论

Optimizing biomedical ontology alignment in lexical vector s...

作者： Xue, Xingsi Wu, Xiaojing Fujian Key Lab for Automotive Electronics and Electric Drive Fujian University of Technology Fuzhou Fujian Minhou China College of Information Science and Engineering Fujian University of Technology Fuzhou Fujian Minhou China Intelligent Information Processing Research Center Fujian University of Technology Fuzhou Fujian Minhou China Institute of Artificial Intelligence Fujian University of Technology Fuzhou Fujian Minhou China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou Fujian Minhou China

Biomedical ontology matching dedicates to find two heterogeneous ontologies' alignment and address their heterogeneity problem. Typically, a biomedical ontology has various biomedical concepts that are described with various labels and datatype property names, which forms a lexical space where each label or datatype property represents one dimension. Therefore, it is an effective way to present two biomedical concepts in a vector space, and use the cosine distance to measure their similarity. In this work, we present two biomedical concepts in a lexical vector space which is constructed with their inner and context concepts' lexical information, and then utilize two vector's cosine distance to measure similarity value. Then, we propose a compact Evolutionary Algorithm (cEA) to find the concept correspondences. The experiment uses Ontology Alignment Evaluation Initiative (OAEI)'s testing cases, and the expeirmental results with Vector space Based Ontology Matcher (VBOM), Genetic Algorithm based Ontology Matcher (GAOM) and OAEI's participants show the effectiveness of our proposal. © 2020 - IOS Press and the authors. All rights reserved.

关键词： Vector spaces

Exploring the Pan-Relationship Between Disease and Symptom Related to Coronary Heart Disease from Chinese Electronic Medical Records 15th

学校读者我要写书评

暂无评论

Exploring the Pan-Relationship Between Disease and Symptom R...

15th International Conference on Intelligent Computing, ICIC 2019

作者： Yang, Ronggen Wang, Yichen Wang, Bo Gong, Lejun Faculty of Intelligent Science and Control Engineering Jinling Institute of Technology Nanjing211169 China Jiangsu Key Lab of Big Data Security and Intelligent Processing School of Computer Science Nanjing University of Posts and Telecommunications Nanjing210046 China School of Geography and Bioinformatics Nanjing University of Posts and Telecommunication Nanjing China

ISBN: (纸本)9783030267650

Electronic Medical Records (EMRs) arises from the clinical treatment process, which reflects a patient’s physical condition, the disease, the treatment process, etc. It has an important significance for the recovery of the patient. As the amount of electronic medical records continues to increase, people are actively looking for ways to get the valid data contained in electronic medical records. More effective methods are urgently needed for processing EMRs. In this paper, 108 real EMRs of coronary heart disease were analyzed, through named entity recognition and entity relation extraction. Pan-relationship between entities was defined in the process. Experimental results showed the analysis of pan-relation between coronary heart disease and symptom is helpful for treatment of coronary heart disease. © 2019, Springer Nature Switzerland AG.

关键词： Diseases

Improved performance of wireless sensor network based on fuzzy logic for clustering scheme 2nd

学校读者我要写书评

暂无评论

Improved performance of wireless sensor network based on fuz...

2nd International Conference on Smart Vehicular Technology, Transportation, Communication and Applications, VTCA 2018

作者： Nguyen, Trong-The Pan, Jeng-Shyang Chu, Shu-Chuan Dao, Thi-Kien Do, Van-Chieu Fujian Provincial Key Lab of Big Data Mining and Applications Fujian University of Technology FuzhouFujian China College of Science and Engineering Flinders University TonsleySA5042 Australia Department of Information Technology Hai-Phong Private University Hai Phong Viet Nam

ISBN: (纸本)9783030045845

The wireless sensor network (WSN) consists of a large number of sensor nodes collaborative to collect and transmit data to the end user. Since the network’s long life is an utmost requirement of WSN. Clustering is one of the most effective ways of prolonging the lifetime of the network. In clustering, a node takes charge of the cluster to coordinate and receive information from the member nodes and transfer it to the sink. With the imbalance of energy dissipation by the sensor node, it may lead to premature failure of the network. Therefore, a robust balanced clustering algorithm can solve this issue in which a worthy candidate will play the cluster head role in each round. This paper proposes an improvement of WSN based on fuzzy logic for clustering. Residual energy, distance from the sink, and density of the nodes in its locality are taken account as the input to feed into fuzzy inference system. Compared results with the other approaches in the literature show the proposed scheme provides the better performance in terms of stability period and protracted lifetime. © Springer Nature Switzerland AG 2019.

关键词： Energy efficiency

A universal opportunity model for human mobility

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Er-Jian Yan, Xiao-Yong Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport Ministry of Transport Beijing Jiaotong University Beijing100044 China Institute of Transportation System Science and Engineering Beijing Jiaotong University Beijing100044 China Compleχ Lab University of Electronic Science and Technology of China Chengdu611731 China

Predicting human mobility between locations has practical applications in transportation science, spatial economics, sociology and many other fields. For more than 100 years, many human mobility prediction models have been proposed, among which the gravity model analogous to Newton's law of gravitation is widely used. Another classical model is the intervening opportunity (IO) model, which indicates that an individual selecting a destination is related to both the destination's opportunities and the intervening opportunities between the origin and the destination. The IO model established from the perspective of individual selection behavior has recently triggered the establishment of many new IO class models. Although these IO class models can achieve accurate prediction at specific spatiotemporal scales, an IO class model that can describe an individual's destination selection behavior at different spatiotemporal scales is still lacking. Here, we develop a universal opportunity model that considers two human behavioral tendencies: one is the exploratory tendency, and the other is the cautious tendency. Our model establishes a new framework in IO class models and covers the classical radiation model and opportunity priority selection model. Furthermore, we use various mobility data to demonstrate our model's predictive ability. The results show that our model can better predict human mobility than previous IO class models. Moreover, this model can help us better understand the underlying mechanism of the individual's destination selection behavior in different types of human mobility. Copyright © 2020, The Authors. All rights reserved.

关键词： Forecasting

Meta mask correction for nuclei segmentation in histopathological image

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Shi, Jiangbo Jia, Chang Gao, Zeyu Gong, Tieliang Wang, Chunbao Li, Chen National Engineering Lab for Big Data Analytics Xi'an Jiao Tong University 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.R&D 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

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, CC BY.

关键词： Deep learning

MCNE: An end-to-end framework for learning multiple conditional network representations of social network

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Wang, Hao Xu, Tong Liu, Qi Lian, Defu Chen, Enhong Du, Dongfang Wu, Han Su, Wen Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China Tencent Inc China

Recently, the Network Representation Learning (NRL) techniques, which represent graph structure via low-dimension vectors to support social-oriented application, have attracted wide attention. Though large efforts have been made, they may fail to describe the multiple aspects of similarity between social users, as only a single vector for one unique aspect has been represented for each node. To that end, in this paper, we propose a novel end-to-end framework named MCNE to learn multiple conditional network representations, so that various preferences for multiple behaviors could be fully captured. Specifically, we first design a binary mask layer to divide the single vector as conditional embeddings for multiple behaviors. Then, we introduce the attention network to model interaction relationship among multiple preferences, and further utilize the adapted message sending and receiving operation of graph neural network, so that multi-aspect preference information from high-order neighbors will be captured. Finally, we utilize Bayesian Personalized Ranking loss function to learn the preference similarity on each behavior, and jointly learn multiple conditional node embeddings via multi-task learning framework. Extensive experiments on public datasets validate that our MCNE framework could significantly outperform several state-of-the-art baselines, and further support the visualization and transfer learning tasks with excellent interpretability and robustness. Copyright © 2019, The Authors. All rights reserved.

关键词： Network embeddings