检索结果-内蒙古大学图书馆

CLDG: Contrastive Learning on Dynamic Graphs

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xu, Yiming Shi, Bin Ma, Teng Dong, Bo Zhou, Haoyi Zheng, Qinghua Department of Computer Science and Technology Xi’an Jiaotong University China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University China Department of Distance Education Xi’an Jiaotong University China School of Software Beihang University China Advanced Innovation Center for Big Data and Brain Computing Beihang University China

关键词： Contrastive Learning

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

New entanglement-assisted quantum codes from negacyclic codes

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chen, Xiaojing Lu, Xingbo Zhu, Shixin Jiang, Wan Wang, Xindi School of Internet Anhui University Anhui Hefei230039 China School of Mathematics Hefei University of Technology Anhui Hefei230601 China Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei University of Technology Anhui Hefei230601 China School of Computer and Information Hefei University of Technology Anhui Hefei230601 China

The theory of entanglement-assisted quantum error-correcting codes (EAQECCs) is a generalization of the standard stabilizer quantum error-correcting codes, which can be possibly constructed from any classical codes by relaxing the duality condition and utilizing preshared entanglement between the sender and receiver. In this paper, a new family of EAQECCs is constructed from negacyclic codes of length n = q2a+1, where q is an odd prime power, a = m22+1 and m is an odd integer. Some new entanglement-assisted quantum maximum distance separable (EAQMDS) codes are obtained in the sense that their parameters are not covered by the previously known ones. Copyright © 2023, The Authors. All rights reserved.

关键词： Quantum entanglement

Median query research in wireless sensor networks

学校读者我要写书评

暂无评论

Tien Tzu Hsueh Pao/Acta Electronica Sinica 2010年第2A期38卷 133-137页

作者： Wu, Zhong-Bo Zhang, Hui Chen, Hong Information School Renmin University of China Beijing 100872 China Key Laboratory of Data Engineering and Knowledge Engineering Ministry of Education Beijing 100872 China School of Mathematics and Computer Science Xiangfan University Xiangfan Hubei 441053 China

Poor quality and harsh condition can result in faulty and outlier data in sampling data of sensor nodes. So we need median query to reflect average level of monitoring region. First, we put forward HMA algorithm. Second, we extend HMA algorithm and put forward HFMA algorithm. In HFMA, We only need collect data inside filter and aggregate influence coefficient during sampling period. Base station can compute median result according to the sample data inside filter and influence coefficient aggregation value. Experimental results have shown that HFMA outperforms Naive algorithm and HMA algorithm and can prolong the lifetime of sensor network.

关键词： Sensor nodes

Discriminative Additive Scale Loss for Deep Imbalanced Classification and Embedding

学校读者我要写书评

暂无评论

Discriminative Additive Scale Loss for Deep Imbalanced Class...

IEEE International Conference on data Mining (ICDM)

作者： Zhao Zhang Weiming Jiang Yang Wang Qiaolin Ye Mingbo Zhao Mingliang Xu Meng Wang School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) & Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China AI team Shanghai Shizhuang Information Technology Co. Ltd Shanghai China College of Information Science and Technology Nanjing Forestry University Nanjing China School of Information Science and Technology Donghua University Shanghai China School of Information Engineering Zhengzhou University Zhengzhou China

ISBN: (纸本)9781665423991

Real-world data in emerging applications may suffer from highly-skewed class imbalanced distribution, however how to deal with this kind of problem appropriately through deep learning needs further investigation. In this paper, we mainly propose a novel cross-entropy based loss function, referred to as Additive Scale Loss (ASL), for deep representation learning and imbalanced classification. To deal with the class imbalanced problem, ASL aims at increasing the loss in case of misclassification, which can avoid the superimposed loss values caused by the large amount of easily classified data in the unbalanced database to dominate the loss value of misclassified data. Moreover, in real-world applications, one data source may be used for multiple scenarios, such as classification and embedding learning, however training two separable models to handle these problems is costly, especially in deep learning area. To tackle this issue, we present and integrate a discriminative inter-class separation term into ASL, and propose a discriminative ASL (D-ASL), which can not only improve the classification performance, but also obtain discriminative representations simultaneously. The discriminative inter-class separation term is general, and can be easily integrated to other loss functions, such as CE and FL, as the byproducts. Finally, a new deep convolutional neural network equipped with D-ASL and a fully-connected (FC) layer is proposed, which can classify the imbalanced image data and obtain the discriminative representations at the same time. Extensive experimental results verified the superior performance of our method.

关键词： Deep learning Training Representation learning Additives databases Soft sensors Conferences

JC5A: Service Delay Minimization for Aerial MEC-assisted Industrial Cyber-Physical Systems

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Sun, Geng Wu, Jiaxu Sun, Zemin He, Long Wang, Jiacheng Niyato, Dusit Jamalipour, Abbas Mao, Shiwen College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore School of Electrical and Computer Engineering The University of Sydney SydneyNSW2006 Australia Department of Electrical and Computer Engineering Auburn University Auburn United States

In the era of the sixth generation (6G) and industrial Internet of Things (IIoT), an industrial cyber-physical system (ICPS) drives the proliferation of sensor devices and computing-intensive tasks. To address the limited resources of IIoT sensor devices, unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) has emerged as a promising solution, providing flexible and cost-effective services in close proximity of IIoT sensor devices (ISDs). However, leveraging aerial MEC to meet the delay-sensitive and computation-intensive requirements of the ISDs could face several challenges, including the limited communication, computation and caching (3C) resources, stringent offloading requirements for 3C services, and constrained on-board energy of UAVs. To address these issues, we first present a collaborative aerial MEC-assisted ICPS architecture by incorporating the computing capabilities of the macro base station (MBS) and UAVs. We then formulate a service delay minimization optimization problem (SDMOP). Since the SDMOP is proved to be an NP-hard problem, we propose a joint computation offloading, caching, communication resource allocation, computation resource allocation, and UAV trajectory control approach (JC5A). Specifically, JC5A consists of a block successive upper bound minimization method of multipliers (BSUMM) for computation offloading and service caching, a convex optimization-based method for communication and computation resource allocation, and a successive convex approximation (SCA)-based method for UAV trajectory control. Moreover, we theoretically prove the convergence and polynomial complexity of JC5A. Simulation results demonstrate that the proposed approach can achieve superior system performance compared to the benchmark approaches and algorithms. Copyright © 2024, The Authors. All rights reserved.

关键词： Convex optimization

Prompt Tuning Pushes Farther, Contrastive Learning Pulls Closer: A Two-Stage Approach to Mitigate Social Biases

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Yingji Du, Mengnan Wang, Xin Wang, Ying College of Computer Science and Technology Jilin University Changchun China Department of Data Science New Jersey Institute of Technology Newark United States School of Artificial Intelligence Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China

As the representation capability of Pre-trained Language Models (PLMs) improve, there is growing concern that they will inherit social biases from unprocessed corpora. Most previous debiasing techniques used Counterfactual data Augmentation (CDA) to balance the training corpus. However, CDA slightly modifies the original corpus, limiting the representation distance between different demographic groups to a narrow range. As a result, the debiasing model easily fits the differences between counterfactual pairs, which affects its debiasing performance with limited text resources. In this paper, we propose an adversarial training-inspired two-stage debiasing model using Contrastive learning with Continuous Prompt Augmentation (named CCPA) to mitigate social biases in PLMs’ encoding. In the first stage, we propose a data augmentation method based on continuous prompt tuning to push farther the representation distance between sample pairs along different demographic groups. In the second stage, we utilize contrastive learning to pull closer the representation distance between the augmented sample pairs and then fine-tune PLMs’ parameters to get debiased encoding. Our approach guides the model to achieve stronger debiasing performance by adding difficulty to the training process. Extensive experiments show that CCPA outperforms baselines in terms of debiasing performance. Meanwhile, experimental results on the GLUE benchmark show that CCPA retains the language modeling capability of PLMs. Copyright © 2023, The Authors. All rights reserved.

关键词： Encoding (symbols)

An Empirical Study on Information Extraction using Large Language Models

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Han, Ridong Yang, Chaohao Peng, Tao Tiwari, Prayag Wan, Xiang Liu, Lu Wang, Benyou College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China College of Software Jilin University China Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China School of Data Science The Chinese University of Hong Kong Shenzhen China School of Information Technology Halmstad University Sweden

Human-like large language models (LLMs), especially the most powerful and popular ones in OpenAI’s GPT family, have proven to be very helpful for many natural language processing (NLP) related tasks. Therefore, various attempts have been made to apply LLMs to information extraction (IE), which is a fundamental NLP task that involves extracting information from unstructured plain text. To demonstrate the latest representative progress in LLMs’ information extraction ability, we assess the information extraction ability of GPT-4 (the latest version of GPT at the time of writing this paper) from four perspectives: Performance, Evaluation Criteria, Robustness, and Error Types. Our results suggest a visible performance gap between GPT-4 and state-of-the-art (SOTA) IE methods. To alleviate this problem, considering the LLMs’ human-like characteristics, we propose and analyze the effects of a series of simple prompt-based methods, which can be generalized to other LLMs and NLP tasks. Rich experiments show our methods’ effectiveness and some of their remaining issues in improving GPT-4’s information extraction ability. Copyright © 2023, The Authors. All rights reserved.

关键词： Information retrieval

Adaptive structure-constrained robust latent low-rank coding for image recovery

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zhang, Zhao Wang, Lei Li, Sheng Wang, Yang Zhang, Zheng Zha, Zhengjun Wang, Meng School of Computer Science and Technology Soochow University Suzhou215006 China Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei University of Technology School of Computer Science and Information Engineering Hefei University of Technology Hefei China Department of Computer Science University of Georgia 549 Boyd GSRC AthensGA30602 Shenzhen China School of Information Science and Technology University of Science and Technology of China Hefei China

In this paper, we propose a robust representation learning model called Adaptive Structure-constrained Low-Rank Coding (AS-LRC) for the latent representation of data. To recover the underlying subspaces more accurately, AS-LRC seamlessly integrates an adaptive weighting based block-diagonal structure-constrained low-rank representation and the group sparse salient feature extraction into a unified framework. Specifically, AS-LRC performs the latent decomposition of given data into a low-rank reconstruction by a block-diagonal codes matrix, a group sparse locality-adaptive salient feature part and a sparse error part. To enforce the block-diagonal structures adaptive to different real datasets for the low-rank recovery, AS-LRC clearly computes an auto-weighting matrix based on the locality-adaptive features and multiplies by the low-rank coefficients for direct minimization at the same time. This encourages the codes to be block-diagonal and can avoid the tricky issue of choosing optimal neighborhood size or kernel width for the weight assignment, suffered in most local geometrical structures-preserving low-rank coding methods. In addition, our AS-LRC selects the L2,1-norm on the projection for extracting group sparse features rather than learning low-rank features by Nuclear-norm regularization, which can make learnt features robust to noise and outliers in samples, and can also make the feature coding process efficient. Extensive visualizations and numerical results demonstrate the effectiveness of our AS-LRC for image representation and recovery. Copyright © 2019, The Authors. All rights reserved.

关键词： Recovery