检索结果-内蒙古大学图书馆

31st ACM International Conference on Information and Knowledge Management, CIKM 2022

作者： Ma, Xinyu Zhang, Ruqing Guo, Jiafeng Fan, Yixing Cheng, Xueqi Cas Key Lab of Network Data Science and Technology Ict Cas University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781450392365

Dense retrieval (DR) has shown promising results in information retrieval. In essence, DR requires high-quality text representations to support effective search in the representation space. Recent studies have shown that pre-trained autoencoder-based language models with a weak decoder can provide high-quality text representations, boosting the effectiveness and few-shot ability of DR models. However, even a weak autoregressive decoder has the bypass effect on the encoder. More importantly, the discriminative ability of learned representations may be limited since each token is treated equally important in decoding the input texts. To address the above problems, in this paper, we propose a contrastive pre-training approach to learn a discriminative autoencoder with a lightweight multi-layer perception (MLP) decoder. The basic idea is to generate word distributions of input text in a non-autoregressive fashion and pull the word distributions of two masked versions of one text close while pushing away from others. We theoretically show that our contrastive strategy can suppress the common words and highlight the representative words in decoding, leading to discriminative representations. Empirical results show that our method can significantly outperform the state-of-the-art autoencoder-based language models and other pre-trained models for dense retrieval. © 2022 ACM.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

LMP-GAN: Out-Of-Distribution Detection For Non-Control data Malware Attacks

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年 PP卷 PP页

作者： Wood, David Kapp, David Kebede, Temesgen Hirakawa, Keigo Wuhan University School of Computer Science China Wuhan University National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering China Zhongguancun Academy China Wuhan University State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing China Sun Yat-sen University School of Geography and Planning China Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates Chongqing University College of Computer Science China The University of Tokyo Japan RIKEN Center for Advanced Intelligence Project Japan Intelligent Science & Technology Academy Limited CASIC China iFlytek Company Ltd. National Engineering Research Center of Speech and Language Information Processing China Nanyang Technological University College of Computing & Data Science Singapore Henan Academy of Sciences Aerospace Information Research Institute China

Anomaly detection is a common application of machine learning. Out-of-distribution (OOD) detection in particular is a semi-supervised anomaly detection technique where the detection method is trained only on the inlier (in-distribution) samples - unlike the fully supervised variant, the distribution of the outlier samples are never explicitly modeled in OOD detection tasks. In this work, we design a novel GAN-based OOD detection network specifically designed to protect a cyber-physical signal systems from novel Trojan malware called non-control data (NCD) attack that evades conventional malware detection techniques. Inspired in part by the classical locally most powerful (LMP) test in statistical inferences, the proposed LMP-GAN trains the OOD detector (discriminator) by generating OOD samples that are aimed at making maximal alteration to the inlier samples while evading detection. We experimentally compare the results to the state-of-the-art anomaly detection methods to demonstrate the benefits and the appropriateness of the LMP-GAN OOD detector. © 2025 IEEE.

关键词： Malware

来源：评论

学校读者我要写书评

暂无评论

Practical decoy-state quantum secure direct communication

引用

science China(Physics,Mechanics & Astronomy) 2021年第12期64卷 68-75页

作者： Xin Liu Zijian Li Di Luo Chunfeng Huang Di Ma Minming Geng Junwei Wang Zhenrong Zhang Kejin Wei Guangxi Key Laboratory for Relativistic Astrophysics School of Physical Science and TechnologyGuangxi UniversityNanning 530004China Guangxi Key Laboratory of Multimedia Communications and Network Technology School of ComputerElectronicsand InformationGuangxi UniversityNanning 530004China CAS Quantum Network Co. LtdShanghai 201315China

Quantum secure direct communication(QSDC) has been demonstrated in both fiber-based and free-space channels using attenuated lasers. Decoy-state QSDC by exploiting four decoy states has been proposed to address the problem of photon-numbersplitting attacks caused by the use of attenuated lasers. In this study, we present an analysis of the practical aspects of decoy-state QSDC. First, we design a two-decoy-state protocol that only requires two decoy states, thereby significantly reducing experimental complexity. Second, we successfully perform full parameter optimization for a real-life QSDC system by introducing a genetic algorithm. Our simulation results show that the two-decoy-state protocol could be the best choice for developing a practical QSDC system. Furthermore, full optimization is crucial for a high-performance QSDC system. Our work serves as a major step toward the further development of practical decoy-state QSDC systems.

关键词： quantum secure direct communication decoy-state method full parameter optimization

来源：评论

学校读者我要写书评

暂无评论

Extended HMM and Ranking models for Chinese Spelling Correction 3

Extended HMM and Ranking models for Chinese Spelling Correct...

引用

3rd CIPS-SIGHAN Joint Conference on Chinese Language Processing, CLP 2014

作者： Xiong, Jinhua Zhao, Qiao Hou, Jianpeng Wang, Qianbo Wang, Yuanzhuo Cheng, Xueqi Cas Key Laboratory of Network Data Science and Technology Institute of Computing Technology University of Chinese Academy of Sciences Chinese Academy of Sciences China

Spelling correction has been studied for many decades, which can be classified into two categories: (1) regular text spelling correction, (2) query spelling correction. Although the two tasks share many common techniques, they have different concerns. This paper presents our work on the CLP-2014 bake-off. The task focuses on spelling checking on foreigner Chinese essays. Compared to online search query spelling checking task, more complicated techniques can be applied for better performance. Therefore, we proposed a unified framework for Chinese essays spelling correction based on extended HMM and ranker-based models, together with a rule-based model for further polishing. Our system showed better performance on the test dataset. © 2014 CLP 2014 - 3rd CIPS-SIGHAN Joint Conference on Chinese Language Processing. All rights reserved.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

NeuInfer: Knowledge inference on N-ary facts 58

NeuInfer: Knowledge inference on N-ary facts

引用

58th Annual Meeting of the Association for Computational Linguistics, ACL 2020

作者： Guan, Saiping Jin, Xiaolong Guo, Jiafeng Wang, Yuanzhuo Cheng, Xueqi School of Computer Science and Technology University of Chinese Academy of Sciences CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences

ISBN: (纸本)9781952148255

Knowledge inference on knowledge graph has attracted extensive attention, which aims to find out connotative valid facts in knowledge graph and is very helpful for improving the performance of many downstream applications. However, researchers have mainly poured attention to knowledge inference on binary facts. The studies on n-ary facts are relatively scarcer, although they are also ubiquitous in the real world. Therefore, this paper addresses knowledge inference on n-ary facts. We represent each n-ary fact as a primary triple coupled with a set of its auxiliary descriptive attribute-value pair(s). We further propose a neural network model, NeuInfer, for knowledge inference on n-ary facts. Besides handling the common task to infer an unknown element in a whole fact, NeuInfer can cope with a new type of task, flexible knowledge inference. It aims to infer an unknown element in a partial fact consisting of the primary triple coupled with any number of its auxiliary description(s). Experimental results demonstrate the remarkable superiority of NeuInfer. © 2020 Association for Computational Linguistics

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

MetaSLRCL: A Self-Adaptive Learning Rate and Curriculum Learning Based Framework for Few-Shot Text Classification 29

MetaSLRCL: A Self-Adaptive Learning Rate and Curriculum Lear...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Zhao, Kailin Jin, Xiaolong Guan, Saiping Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of SciencesSchool of Computer Science and Technology University of Chinese Academy of Sciences

Due to the lack of labeled data in many realistic scenarios, a number of few-shot learning methods for text classification have been proposed, among which the meta learning based ones have recently attracted much attention. Such methods usually consist of a learner as the classifier and a meta learner for specializing the learner to different tasks. For the learner, learning rate is crucial to its performance. However, existing methods treat it as a hyper parameter and adjust it manually, which is time-consuming and laborious. Intuitively, for different tasks and neural network layers, the learning rates should be different and self-adaptive. For the meta learner, it requires a good generalization ability so as to quickly adapt to new tasks. Motivated by these issues, we propose a novel meta learning framework, called MetaSLRCL, for few-shot text classification. Specifically, we present a novel meta learning mechanism to obtain different learning rates for different tasks and neural network layers so as to enable the learner to quickly adapt to new training data. Moreover, we propose a task-oriented curriculum learning mechanism to help the meta learner achieve a better generalization ability by learning from different tasks with increasing difficulties. Extensive experiments on three benchmark datasets demonstrate the effectiveness of MetaSLRCL. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Text processing

来源：评论

学校读者我要写书评

暂无评论

Efficient quantum state transmission via perfect quantum network coding

引用

science China(Information sciences) 2019年第1期62卷 191-204页

作者： Zhen-Zhen LI Gang XU Xiu-Bo CHEN Zhiguo QU Xin-Xin NIU Yi-Xian YANG Information Security Center State Key Laboratory of Networking and Switching TechnologyBeijing University of Posts and Telecommunications Guizhou Provincial Key Laboratory of Public Big Data Guizhou University Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and Technology

Quantum network coding with the assistance of auxiliary resources can achieve perfect transmission of the quantum state. This paper suggests a novel perfect network coding scheme to efficiently solve the quantum k-pair problem, in which only a few assisting resources are introduced. Specifically, only one pair of maximally entangled state needs to be pre-shared between two intermediate nodes, and only O(k) of classical information is transmitted though the network. Moreover, the classical communication used in our protocol does not cause transmission congestion, providing better adaptability to large-scale quantum k-pair *** relevant analyses and comparisons, we demonstrate that our proposed scheme saves resources and has good application value, thereby showing its high efficiency. Furthermore, the proposed scheme achieves 1-max flow quantum communication, and the achievable rate region result is extended from its counterpart over the butterfly network.

关键词： perfect quantum network coding quantum k-pair problem efficient quantum state transmission communication efficiency achievable rate region

来源：评论

学校读者我要写书评

暂无评论

XAI-PSSGAN: Perception-Enhanced Spectrum Shift Generative Adversarial network with Explainable AI System for NIR-II Fluorescence Molecular Imaging

XAI-PSSGAN: Perception-Enhanced Spectrum Shift Generative Ad...

引用

IEEE International Symposium on Biomedical Imaging

作者： Lidan Fu Binchun Lu Lingbing Li Xiaojing Shi Jie Tian Zhenhua Hu CAS Key Laboratory of Molecular Imaging Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Department of Precision Instrument Tsinghua University Beijing China Interventional Radiology Department Chinese PLA General Hospital Beijing China Beijing Advanced Innovation Center for Big Data-based Precision Medicine School of Engineering Medicine Beihang University Beijing China Engineering Research Center of Molecular and Neuro Imaging of Ministry of Education School of Life Science and Technology Xidian University Xi'an China National Key Laboratory of Kidney Diseases Beijing China

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Fluorescence imaging in the second near-infrared window (NIR-II) facilitates the real-time optical contrast for in vivo biomedical imaging. However, the detection noise is an inevitable byproduct of the real-time imaging process. Additionally, fluorescent probes currently approved for clinical use remain limited within the wavelength of NIR-IIa (1000–1300 nm). NIR-IIb (1500–1700 nm) imaging has the potential to deliver higher resolution than NIR-IIa, but relies on toxic fluorescent probes not approved for human use. To support clinical high-precision imaging, we propose a NIR-II fluorescence enhanced imaging method based on perception-enhanced spectrum shift generative adversarial network with explainable AI systems (xAI-PSSGAN). The proposed method tackles the problem of limited unpaired data training, and generates NIR-IIb resembling images with enhanced resolution and reduced noise. Experimental results demonstrate that proposed method effectively improves the imaging quality and surpasses competing alternatives, which is of great significance to promote the high-quality NIR-II imaging in clinical practice.

关键词： Training Image resolution Explainable AI Statistical analysis Noise Imaging Fluorescence Generative adversarial networks Real-time systems Probes

来源：评论

学校读者我要写书评

暂无评论

Sparse word embeddings using l1 regularized online learning 25

Sparse word embeddings using l1 regularized online learning

引用

25th International Joint Conference on Artificial Intelligence, IJCAI 2016

作者： Sun, Fei Guo, Jiafeng Lan, Yanyan Xu, Jun Xueqi, Cheng CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China

Recently, Word2Vec tool has attracted a lot of interest for its promising performances in a variety of natural language processing (NLP) tasks. However, a critical issue is that the dense word representations learned in Word2Vec are lacking of interpretability. It is natural to ask if one could improve their interpretability while keeping their performances. Inspired by the success of sparse models in enhancing interpretability, we propose to introduce sparse constraint into Word2Vec. Specifically, we take the Continuous Bag of Words (CBOW) model as an example in our study and add the l regularizer into its learning objective. One challenge of optimization lies in that stochastic gradient descent (SGD) cannot directly produce sparse solutions with l regularizer in online training. To solve this problem, we employ the Regularized Dual Averaging (RDA) method, an online optimization algorithm for regularized stochastic learning. In this way, the learning process is very efficient and our model can scale up to very large corpus to derive sparse word representations. The proposed model is evaluated on both expressive power and interpretability. The results show that, compared with the original CBOW model, the proposed model can obtain state-of-the-art results with better interpretability using less than 10% non-zero elements.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Enhanced Self-Supervised Prototypical network for Few-Shot Event Detection

Knowledge-Enhanced Self-Supervised Prototypical Network for ...

引用

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Zhao, Kailin Jin, Xiaolong Bai, Long Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences School of Computer Science and Technology University of Chinese Academy of Sciences China

Prototypical network based joint methods have attracted much attention in few-shot event detection, which carry out event detection in a unified sequence tagging framework. However, these methods suffer from the inaccurate prototype representation problem, due to two main reasons: the number of instances for calculating prototypes is limited;And, they do not well capture the relationships among event prototypes. To deal with this problem, we propose a Knowledge-Enhanced self-supervised Prototypical network, called KE-PN, for few-shot event detection. KE-PN adopts hybrid rules, which can automatically align event types to an external knowledge base, i.e., FrameNet, to obtain more instances. It proposes a self-supervised learning method to filter out noisy data from enhanced instances. KE-PN is further equipped with an auxiliary event type relationship classification module, which injects the relationship information into representations of event prototypes. Extensive experiments on three benchmark datasets, i.e., FewEvent, MAVEN, and ACE2005 demonstrate the state-of-the-art performance of KE-PN. © 2022 Association for Computational Linguistics.

关键词： Classification (of information)

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：