检索结果-内蒙古大学图书馆

iSplit LBI: Individualized partial ranking with ties via split LBI

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Xu, Qianqian Sun, Xinwei Yang, Zhiyong Cao, Xiaochun Huang, Qingming Yao, Yuan Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS Microsoft Research Asia State Key Laboratory of Information Security Institute of Information Engineering CAS School of Cyber Security University of Chinese Academy of Sciences School of Computer Science and Tech. University of Chinese Academy of Sciences Key Laboratory of Big Data Mining and Knowledge Management CAS Peng Cheng Laboratory Department of Mathematics Hong Kong University of Science and Technology Hong Kong

Due to the inherent uncertainty of data, the problem of predicting partial ranking from pairwise comparison data with ties has attracted increasing interest in recent years. However, in real-world scenarios, different individuals often hold distinct preferences. It might be misleading to merely look at a global partial ranking while ignoring personal diversity. In this paper, instead of learning a global ranking which is agreed with the consensus, we pursue the tie-aware partial ranking from an individualized perspective. Particularly, we formulate a unified framework which not only can be used for individualized partial ranking prediction, but also be helpful for abnormal user selection. This is realized by a variable splitting-based algorithm called iSplitLBI. Specifically, our algorithm generates a sequence of estimations with a regularization path, where both the hyperparameters and model parameters are updated. At each step of the path, the parameters can be decomposed into three orthogonal parts, namely, abnormal signals, personalized signals and random noise. The abnormal signals can serve the purpose of abnormal user selection, while the abnormal signals and personalized signals together are mainly responsible for individual partial ranking prediction. Extensive experiments on simulated and real-world datasets demonstrate that our new approach significantly outperforms state-of-the-art alternatives. The code is now availiable at https://***/qianqianxu010/ NeurIPS2019-iSplitLBI. Copyright © 2019, The Authors. All rights reserved.

关键词： Forecasting

Local and global structure-aware entropy regularized mean teacher model for 3d left atrium segmentation 23rd

学校读者我要写书评

暂无评论

Local and global structure-aware entropy regularized mean te...

23rd International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2020

作者： Hang, Wenlong Feng, Wei Liang, Shuang Yu, Lequan Wang, Qiong Choi, Kup-Sze Qin, Jing School of Computer Science and Technology Nanjing Tech University Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Smart Health Big Data Analysis and Location Services Engineering Lab of Jiangsu Province Nanjing University of Posts and Telecommunications Nanjing China Department of Radiation Oncology Stanford University StanfordCA94305 United States CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Shenzhen China School of Nursing Hong Kong Polytechnic University Hong Kong

ISBN: (纸本)9783030597092

Emerging self-ensembling methods have achieved promising semi-supervised segmentation performances on medical images through forcing consistent predictions of unannotated data under different perturbations. However, the consistency only penalizes on independent pixel-level predictions, making structure-level information of predictions not exploited in the learning procedure. In view of this, we propose a novel structure-aware entropy regularized mean teacher model to address the above limitation. Specifically, we firstly introduce the entropy minimization principle to the student network, thereby adjusting itself to produce high-confident predictions of unannotated images. Based on this, we design a local structural consistency loss to encourage the consistency of inter-voxel similarities within the same local region of predictions from teacher and student networks. To further capture local structural dependencies, we enforce the global structural consistency by matching the weighted self-information maps between two networks. In this way, our model can minimize the prediction uncertainty of unannotated images, and more importantly that it can capture local and global structural information and their complementarity. We evaluate the proposed method on a publicly available 3D left atrium MR image dataset. Experimental results demonstrate that our method achieves outstanding segmentation performances than the state-of-the-art approaches in scenes with limited annotated images. © Springer Nature Switzerland AG 2020.

关键词： Forecasting

FRCNet: Frequency and Region Consistency for Semi-supervised Medical Image Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： He, Along Li, Tao Wu, Yanlin Zou, Ke Fu, Huazhu Tianjin Key Laboratory of Network and Data Security Technology College of Computer Science Nankai University Tianjin China Haihe Lab of ITAI China National Key Laboratory of Fundamental Science on Synthetic Vision Sichuan University Sichuan Chengdu China Institute of High Performance Computing Agency for Science Technology and Research Singapore

Limited labeled data hinder the application of deep learning in medical domain. In clinical practice, there are sufficient unlabeled data that are not effectively used, and semi-supervised learning (SSL) is a promising way for leveraging these unlabeled data. However, existing SSL methods ignore frequency domain and region-level information and it is important for lesion regions located at low frequencies and with significant scale changes. In this paper, we introduce two consistency regularization strategies for semi-supervised medical image segmentation, including frequency domain consistency (FDC) to assist the feature learning in frequency domain and multi-granularity region similarity consistency (MRSC) to perform multi-scale region-level local context information feature learning. With the help of the proposed FDC and MRSC, we can leverage the powerful feature representation capability of them in an effective and efficient way. We perform comprehensive experiments on two datasets, and the results show that our method achieves large performance gains and exceeds other state-of-the-art methods. © 2024, CC BY.

关键词： Deep learning

Quantum key distribution with the single-photon-added coherent source

学校读者我要写书评

暂无评论

Physical Review A 2014年第6期90卷 062315-062315页

作者： Dong Wang Mo Li Feng Zhu Zhen-Qiang Yin Wei Chen Zheng-Fu Han Guang-Can Guo Qin Wang Key Laboratory of Quantum Information University of Science and Technology of China CAS Hefei Anhui 230026 China Synergetic Innovation Center of Quantum Information & Quantum Physics University of Science and Technology of China Hefei Anhui 230026 China Institute of Signal Processing Transmission Nanjing University of Posts and Telecommunications Nanjing 210003 China Key Lab of Broadband Wireless Communication and Sensor Network Technology Nanjing University of Posts and Telecommunications Ministry of Education Nanjing 210003 China

In this paper, we present schemes on implementing the single-photon-added coherent source in quantum key distributions. We apply this source in either the standard BB84 protocol or the recently proposed measurement-device-independent quantum key distribution, comparing their performance with the cases of using other existing sources, e.g., the weak coherent source or the heralded single-photon source, and giving out corresponding numerical simulations. Our simulation results show that in both protocols the single-photon-added coherent source can greatly exceed all other existing sources. Moreover, even when taking statistical fluctuation into account, a high key generation rate can still be achieved at long distance by applying this source.

关键词： SINGLE photon generation QUANTUM measurement COHERENT scattering QUANTUM communication (Optics) QUANTUM states

Deep Feature Surgery: Towards Accurate and Efficient Multi-Exit networks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Gong, Cheng Chen, Yao Luo, Qiuyang Lu, Ye Li, Tao Zhang, Yuzhi Sun, Yufei Zhang, Le College of Software Nankai University China College of Computer Science Nankai University China National University of Singapore Singapore School of Information and Communication Engineering University of Electronic Science and Technology of China China HAIHE Lab of ITAI China Tianjin Key Laboratory of Network and Data Security Technology China Key Laboratory of Data and Intelligent System Security Ministry of Education

Multi-exit network is a promising architecture for efficient model inference by sharing backbone networks and weights among multiple exits. However, the gradient conflict of the shared weights results in sub-optimal accuracy. This paper introduces Deep Feature Surgery (DFS), which consists of feature partitioning and feature referencing approaches to resolve gradient conflict issues during the training of multi-exit networks. The feature partitioning separates shared features along the depth axis among all exits to alleviate gradient conflict while simultaneously promoting joint optimization for each exit. Subsequently, feature referencing enhances multi-scale features for distinct exits across varying depths to improve the model accuracy. Furthermore, DFS reduces the training operations with the reduced complexity of backpropagation. Experimental results on Cifar100 and ImageNet datasets exhibit that DFS provides up to a 50.00% reduction in training time and attains up to a 6.94% enhancement in accuracy when contrasted with baseline methods across diverse models and tasks. Budgeted batch classification evaluation on MSDNet demonstrates that DFS uses about 2× fewer average FLOPs per image to achieve the same classification accuracy as baseline methods on Cifar100. The code is available at https: //***/GongCheng1919/dfs. Copyright © 2024, The Authors. All rights reserved.

关键词： Budget control

Spatio-Temporal meets Wavelet: Disentangled Traffic Flow Forecasting via Efficient Spectral Graph Attention network

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Fang, Yuchen Qin, Yanjun Luo, Haiyong Zhao, Fang Xu, Bingbing Wang, Chenxing Zeng, Liang School of Computer Science National Pilot Software Engineering School Beijing University of Posts and Telecommunications China Research Center for Ubiquitous Computing Systems Institute of Computing Technology Chinese Academy of Sciences China CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China Tsinghua University China

Traffic forecasting is crucial for public safety and resource optimization, yet is very challenging due to three aspects: i) current existing works mostly exploit intricate temporal patterns (e.g., the short-term thunderstorm and long-term daily trends) within a single method, which fail to accurately capture spatio-temporal dependencies under different schemas;ii) the under-exploration of the graph positional encoding limit the extraction of spatial information in the commonly used full graph attention network;iii) the quadratic complexity of the full graph attention introduces heavy computational needs. To achieve the effective traffic flow forecasting, we propose an efficient spectral graph attention network with disentangled traffic sequences. Specifically, the discrete wavelet transform is leveraged to obtain the low- and high-frequency components of traffic sequences, and a dual-channel encoder is elaborately designed to accurately capture the spatio-temporal dependencies under long- and short-term schemas of the low- and high-frequency components. Moreover, a novel wavelet-based graph positional encoding and a query sampling strategy are introduced in our spectral graph attention to effectively guide message passing and efficiently calculate the attention. Extensive experiments on four real-world datasets show the superiority of our model, i.e., the higher traffic forecasting precision with lower computational cost. Copyright © 2021, The Authors. All rights reserved.

关键词： Message passing

Long-Distance Entanglement Purification for Quantum Communication

学校读者我要写书评

暂无评论

Physical Review Letters 2021年第1期126卷 010503-010503页

作者： Xiao-Min Hu Cen-Xiao Huang Yu-Bo Sheng Lan Zhou Bi-Heng Liu Yu Guo Chao Zhang Wen-Bo Xing Yun-Feng Huang Chuan-Feng Li Guang-Can Guo CAS Key Laboratory of Quantum Information University of Science and Technology of China Hefei 230026 People’s Republic of China CAS Center For Excellence in Quantum Information and Quantum Physics University of Science and Technology of China Hefei 230026 People’s Republic of China Institute of Quantum Information and Technology Nanjing University of Posts and Telecommunications Nanjing 210003 People’s Republic of China School of Science Nanjing University of Posts and Telecommunications Nanjing 210003 People’s Republic of China Key Lab of Broadband Wireless Communication and Sensor Network Technology Nanjing University of Posts and Telecommunications Ministry of Education Nanjing 210003 People’s Republic of 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 tabletop. 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 inequality of polarization entanglement arises from 1.829 to 2.128. Moreover, by using one pair of hyperentanglement and deterministic controlled-NOT gates, 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 sources. Our results offer the potential to be implemented as part of a full quantum repeater and large-scale quantum network.

关键词： Entanglement manipulation Optical quantum information processing Quantum communication Quantum optics Quantum protocols

Roland: Robust In-band Parallel Communication for Magnetic MIMO Wireless Power Transfer System

学校读者我要写书评

暂无评论

Roland: Robust In-band Parallel Communication for Magnetic M...

IEEE Annual Joint Conference: INFOCOM, IEEE Computer and Communications Societies

作者： Wangqiu Zhou Hao Zhou Xiang Cui Xinyu Wang Xiaoyan Wang Zhi Liu LINKE Lab School of Computer Science and Technology University of Science and Technology of China CAS Key Laboratory of Wireless-Optical Communications University of Science and Technology of China Deqing Alpha Innovation Institute Huzhou China Graduate School of Science and Engineering Ibaraki University Ibaraki Japan Department of Computer and Network Engineering The University of Electro-Communications Tokyo Japan

In recent years, receiver (RX) feedback communication has attracted increasing attention to enhance the charging performance for magnetic resonant coupling (MRC) based wireless power transfer (WPT) systems. People prefer to adopt the in-band implementation with minimal overhead costs. However, the influence of RX-RX coupling couldn’t be directly ignored like that in the RFID field, i.e., strong couplings and relay phenomenon. In order to solve these two critical issues, we propose a Robust layer-level in-band parallel communication protocol for MIMO MRC-WPT systems (called Roland). Technically, we first utilize the observed channel decomposability to construct group-level channel relationship graph for eliminating the interference caused by strong RX-RX couplings. Then, we generalize such method to deal with the RX dependency due to relay phenomenon. Finally, we conduct extensive experiments on a prototype testbed to evaluate the effectiveness of the proposed scheme. The results demonstrate that our Roland could provide ≥95% average decoding accuracy for concurrent feedback communication of 14 devices. Compared with the state-of-the-art solution, the proposed protocol Roland can achieve an average decoding accuracy improvement of 20.41%.

关键词：

Self-Supervised Teaching and Learning of Representations on Graphs 23

学校读者我要写书评

暂无评论

Self-Supervised Teaching and Learning of Representations on ...

2023 World Wide Web Conference, WWW 2023

作者： Wan, Liangtian Fu, Zhenqiang Sun, Lu Wang, Xianpeng Xu, Gang Yan, Xiaoran Xia, Feng Key Laboratory for Ubiquitous Network Service Software of Liaoning Province School of Software Dalian University of Technology Dalian China Department of Communication Engineering Institute of Information Science Technology Dalian Maritime University Dalian China State Key Laboratory of Marine Resource Utilization in South China Sea School of Information and Communication Engineering Hainan University Haikou China State Key Laboratory of Millimeter Waves School of Information Science and Engineering Southeast University Nanjing China Research Center of Big Data Intelligence Research Institute of Artificial Intelligence Zhejiang Lab Hangzhou China School of Computing Technologies Rmit University Melbourne Australia

ISBN: (纸本)9781450394161

Recent years have witnessed significant advances in graph contrastive learning (GCL), while most GCL models use graph neural networks as encoders based on supervised learning. In this work, we propose a novel graph learning model called GraphTL, which explores self-supervised teaching and learning of representations on graphs. One critical objective of GCL is to retain original graph information. For this purpose, we design an encoder based on the idea of unsupervised dimensionality reduction of locally linear embedding (LLE). Specifically, we map one iteration of the LLE to one layer of the network. To guide the encoder to better retain the original graph information, we propose an unbalanced contrastive model consisting of two views, which are the learning view and the teaching view, respectively. Furthermore, we consider the nodes that are identical in muti-views as positive node pairs, and design the node similarity scorer so that the model can select positive samples of a target node. Extensive experiments have been conducted over multiple datasets to evaluate the performance of GraphTL in comparison with baseline models. Results demonstrate that GraphTL can reduce distances between similar nodes while preserving network topological and feature information, yielding better performance in node classification. © 2023 ACM.

关键词： Classification (of information)