检索结果-内蒙古大学图书馆

Attentionxml: label tree-based attention-aware deep model for high-performance extreme multi-label text classification

学校读者我要写书评

暂无评论

arXiv 2018年

作者： You, Ronghui Zhang, Zihan Wang, Ziye Dai, Suyang Mamitsuka, Hiroshi Zhu, Shanfeng Shanghai Key Lab of Intelligent Information Processing School of Computer Science Centre for Computational Systems Biology School of Mathematical Sciences Shanghai Institute of Artificial Intelligence Algorithms and ISTBI Fudan University Shanghai China Bioinformatics Center Institute for Chemical Research Kyoto University Japan Department of Computer Science Aalto University Helsinki Finland

Extreme multi-label text classification (XMTC) is an important problem in the era of big data, for tagging a given text with the most relevant multiple labels from an extremely large-scale label set. XMTC can be found in many applications, such as item categorization, web page tagging, and news annotation. Traditionally most methods used bag-of-words (BOW) as inputs, ignoring word context as well as deep semantic information. Recent attempts to overcome the problems of BOW by deep learning still suffer from 1) failing to capture the important subtext for each label and 2) lack of scalability against the huge number of labels. We propose a new label tree-based deep learning model for XMTC, called AttentionXML, with two unique features: 1) a multi-label attention mechanism with raw text as input, which allows to capture the most relevant part of text to each label;and 2) a shallow and wide probabilistic label tree (PLT), which allows to handle millions of labels, especially for "tail labels". We empirically compared the performance of AttentionXML with those of eight state-of-the-art methods over six benchmark datasets, including Amazon-3M with around 3 million labels. AttentionXML outperformed all competing methods under all experimental settings. Experimental results also show that AttentionXML achieved the best performance against tail labels among label tree-based methods. The code and datasets are available at http://***/yourh/AttentionXML . Copyright © 2018, The Authors. All rights reserved.

关键词： Benchmarking

Fog-assisted multi-user swipt networks: Local computing or offloading

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zheng, Haina Xiong, Ke Fan, Pingyi Zhong, Zhangdui Letaief, Khaled Ben School of Computer and Information Technology Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China Beijing Key Laboratory of Security and Privacy in Intelligent Transportation Beijing Jiaotong University Beijing100044 China National Laboratory for Information Science and Technology Department of Electronic Engineering Tsinghua University Beijing100084 China State Key Lab of Rail Traffic Control and Safety Beijing Engineering Research Center of High-speed Railway Broadband Mobile Communications Beijing Jiaotong University Beijing100044 China Clear Water Bay Hong Kong

This paper investigates a fog computing-assisted multi-user simultaneous wireless information and power transfer (SWIPT) network, where multiple sensors with power splitting (PS) receiver architectures receive information and harvest energy from a hybrid access point (HAP), and then process the received data by using local computing mode or fog offloading mode. For such a system, an optimization problem is formulated to minimize the sensors' required energy while guaranteeing their required information transmissions and processing rates by jointly optimizing the multi-user scheduling, the time assignment, the sensors' transmit powers and the PS ratios. Since the problem is a mixed integer programming (MIP) problem and cannot be solved with existing solution methods, we solve it by applying problem decomposition, variable substitutions and theoretical analysis. For a scheduled sensor, the closed-form and semi-closedform solutions to achieve its minimal required energy are derived, and then an efficient multi-user scheduling scheme is presented, which can achieve the suboptimal user scheduling with low computational complexity. Numerical results demonstrate our obtained theoretical results, which show that for each sensor, when it is located close to the HAP or the fog server (FS), the fog offloading mode is the better choice;otherwise, the local computing mode should be selected. The system performances in a frame-by-frame manner are also simulated, which show that using the energy stored in the batteries and that harvested from the signals transmitted by previous scheduled sensors can further decrease the total required energy of the sensors. Copyright © 2019, The Authors. All rights reserved.

关键词： Energy harvesting

Learning data-adaptive nonparametric kernels

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Liu, Fanghui Huang, Xiaolin Gong, Chen Yang, Jie Li, Li Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Department of Automation Tsinghua University

Kernel methods have been extensively used in a variety of machine learning tasks such as classification, clustering, and dimensionality reduction. For complicated practical tasks, the traditional kernels, e.g., Gaussian kernel and sigmoid kernel, or their combinations are often not sufficiently flexible to fit the data. In this paper, we present a Data-Adaptive Nonparametric Kernel (DANK) learning framework in a data-driven manner. To be specific, in model formulation, we impose an adaptive matrix on the kernel/Gram matrix in an entry-wise strategy. Since we do not specify the formulation of the adaptive matrix, each entry in the adaptive matrix can be directly and flexibly learned from the data. Therefore, the solution space of the learned kernel is largely expanded, which makes our DANK model flexible to capture the data with different local statistical properties. Specifically, the proposed kernel learning framework can be seamlessly embedded to support vector machines (SVM) and support vector regression (SVR), which has the capability of enlarging the margin between classes and reducing the model generalization error. Theoretically, we demonstrate that the objective function of our DANK model embedded in SVM/SVR is gradient-Lipschitz continuous. Thereby, the training process for kernel and parameter learning in SVM/SVR can be efficiently optimized in a unified framework. Further, to address the scalability issue in nonparametric kernel learning framework, we decompose the entire optimization problem in DANK into several smaller easy-to-solve problems, so that our DANK model can be efficiently approximated by this partition. The effectiveness of this approximation is demonstrated by both empirical studies and theoretical guarantees. Experimentally, the proposed DANK model embedded in SVM/SVR achieves encouraging performance on various classification and regression benchmark datasets when compared with other representative kernel learning based algorithms. Copyrig

关键词： Matrix algebra

Maximum contributed component regression for the inverse problem in optical scatterometry

学校读者我要写书评

暂无评论

Optics express 2017年第14期25卷 15956-15966页

作者： Haiping Zhu Youngjoo Lee Hongming Shan Junping Zhang School of Computer Science Shanghai Key Lab of Intelligent Information Processing Fudan University Shanghai China Manufacturing Technology Center Samsung Electronics Suwon South Korea

Scatterometry has been widely applied in microelectronic manufacturing process monitoring. As a key part in scatterometry, inverse problem uses scatter signature to determine the shape of profile structure. The most common solutions for the inverse problem are model-based methods, such as library search, Levenberg-Marquardt algorithm and artificial neural network (ANN). However, they all require a pre-defined geometric model to extract 3D profile of the structure. When facing the complex structure in manufacturing process monitoring, the model-based methods will cost a long time and may fail to build a valid geometric model. Without the assumption of the geometric model, model-free methods are developed to find a mapping between profile parameter named label Y and corresponding spectral signature X. These methods need lots of labeled data obtained from transmission electron microscopy (TEM) or cross-sectional scanning electron microscopy (XSEM) with time-consuming and highly cost, leading to the increase of production costs. To address these issues, this paper develops a novel model-free method, called maximum contributed component regression (MCCR). It utilizes canonical correlation analysis (CCA) to estimate the maximum contributed components from pairwise relationship of economic unlabeled data with few expensive labeled data. In MCCR, the maximum contributed components are used to guide the solution of the inverse problem based on the conventional regression methods. Experimental results on both synthetic and real-world semiconductor datasets demonstrate the effectiveness of the proposed method given small amount of labeled data.

关键词： Atomic force microscopy Inverse problems Light scattering Process monitoring Scanning electron microscopy Transmission electron microscopy

Tracking the 3D position and orientation of flying swarms with learned kinematic pattern using LSTM network

学校读者我要写书评

暂无评论

Tracking the 3D position and orientation of flying swarms wi...

2017 IEEE International Conference on Multimedia and Expo, ICME 2017

作者： Wang, Shuo Hong Su, Hai Feng Cheng, Xi En Liu, Ye Quo, Aike Chen, Yan Qiu School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai China Institute of Neuroscience State Key Laboratory of Neuroscience CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai Institutes for Biological Sciences CAS Shanghai China Jingdezhen Ceramic Institute Jindezhen China College of Automation Nanjing University of Posts and Telecommunications China

ISBN: (纸本)9781509060672

Accurately and reliably tracking the 3D position and orientation of individuals in large flying swarms is valuable not only for scientific researches but also practical applications. However, large quantity, frequent occlusions, similar appearance, tiny body size and abrupt motion make it remain an open problem. The 3D flying swarm tracking method proposed in this paper tracks both position and orientation of each individual in the swarm using the particle filter framework. Particles are scattered more pertinently by the dynamic model based on the learned kinematic pattern of a single target with a Long Short-Term Memory (LSTM) network. In addition, the observation model combines the Weighted Occupancy Ratio (WOR) and Temporal Appearance Coherency (TAC) cues in each view to improve the accuracy and robustness of the reconstructed body orientation. Experiments on both simulation and real-world data sets demonstrate the effectiveness and superiority of the proposed method. © 2017 IEEE.

关键词： Long short-term memory

Effects of reciprocity on random walks in weighted networks

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Zhang, Zhongzhi Li, Huan Sheng, Yibin School of Computer Science Fudan University Shanghai200433 China Shanghai Key Lab of Intelligent Information Processing Fudan University Shanghai200433 China

It has been recently reported that the reciprocity of real-life weighted networks is very pronounced, however its impact on dynamical processes is poorly understood. In this paper, we study random walks in a scale-free directed weighted network with a trap at the central hub node, where the weight of each directed edge is dominated by a parameter controlling the extent of network reciprocity. We derive the mean first passage time (MFPT) to the trap, by using two different techniques, the results of which agree well with each other. We also analytically determine all the eigenvalues as well as their multiplicities for the fundamental matrix of the dynamical process, and show that the largest eigenvalue has an identical dominant scaling as that of the MFPT. We find that the weight parameter has a substantial effect on the MFPT, which behaves as a power-law function of the system size with the power exponent dependent on the parameter, signaling the crucial role of reciprocity in random walks occurring in weighted networks. Copyright © 2017, The Authors. All rights reserved.

关键词： Random processes

AON: Towards arbitrarily-oriented text recognition

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Cheng, Zhanzhan Xu, Yangliu Bai, Fan Niu, Yi Pu, Shiliang Zhou, Shuigeng Hikvision Research Institute Tongji University Shanghai China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China

Recognizing text from natural images is a hot research topic in computer vision due to its various applications. Despite the enduring research of several decades on op-tical character recognition (OCR), recognizing texts from natural images is still a challenging task. This is because scene texts are often in irregular (e.g. curved, arbitrarily-oriented or seriously distorted) arrangements, which have not yet been well addressed in the literature. Existing meth-ods on text recognition mainly work with regular (horizontal and frontal) texts and cannot be trivially generalized to handle irregular texts. In this paper, we develop the ar-bitrary orientation network (AON) to directly capture the deep features of irregular texts, which are combined into an attention-based decoder to generate character sequence. The whole network can be trained end-to-end by using only images and word-level annotations. Extensive experiments on various benchmarks, including the CUTE80, SVT-Perspective, IIIT5k, SVT and ICDAR datasets, show that the proposed AON-based method achieves the-state-of-the-art performance in irregular datasets, and is comparable to major existing methods in regular datasets. Copyright © 2017, The Authors. All rights reserved.

关键词： Character recognition

Dual Skipping Networks

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Cheng, Changmao Fu, Yanwei Jiang, Yu-Gang Liu, Wei Lu, Wenlian Feng, Jianfeng Xue, Xiangyang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University School of Data Science Fudan University Tencent Ai Lab Fudan University Istbi

Inspired by the recent neuroscience studies on the left right asymmetry of the human brain in processing low and high spatial frequency information, this paper introduces a dual skipping network which carries out coarse-to-fine object categorization. Such a network has two branches to simultaneously deal with both coarse and fine-grained classification tasks. Specifically, we propose a layer-skipping mechanism that learns a gating network to predict which layers to skip in the testing stage. This layer-skipping mechanism endows the network with good flexibility and capability in practice. Evaluations are conducted on several widely used coarse-to-fine object categorization benchmarks, and promising results are achieved by our proposed network model. Copyright © 2017, The Authors. All rights reserved.

关键词： Machine learning

POSTER: Provably Efficient Scheduling of Cache-Oblivious Wavefront Algorithms

学校读者我要写书评

暂无评论

ACM SIGPLAN Notices 2017年第8期52卷 435-436页

作者： Chowdhury, Rezaul Ganapathi, Pramod Tang, Yuan Tithi, Jesmin Jahan Department of Computer Science Stony Brook University New York United States School of Software Shanghai Key Lab of Intelligent Information Processing Fudan University Shanghai China Intel Corporation

Standard cache-oblivious recursive divide-and-conquer algorithms for evaluating dynamic programming recurrences have optimal serial cache complexity but often have lower parallelism compared with iterative wavefront algorithms due to artificial dependencies among subtasks. Very recently cache-oblivious recursive wavefront (COW) algorithms have been introduced which do not have any artificial dependencies. Though COW algorithms are based on fork-join primitives, they extensively use atomic operations, and as a result, performance guarantees provided by state-of-the-art schedulers for programs with fork-join primitives do not apply. In this work, we show how to systematically transform standard cache-oblivious recursive divide-and-conquer algorithms into recursive wavefront algorithms to achieve optimal parallel cache complexity and high parallelism under state-of-the-art schedulers for fork-join programs. Unlike COW algorithms these new algorithms do not use atomic operations. Instead, they use closed-form formulas to compute at what time each recursive function must be launched in order to achieve high parallelism without losing cache performance. The resulting implementations are arguably much simpler than implementations of known COW algorithms. © 2017 ACM.

关键词： Dynamic programming