检索结果-内蒙古大学图书馆

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Hailin Zhang Yujing Wang Qi Chen Ruiheng Chang Ting Zhang Ziming Miao Yingyan Hou Yang Ding Xupeng Miao Haonan Wang Bochen Pang Yuefeng Zhan Hao Sun Weiwei Deng Qi Zhang Fan Yang Xing Xie Mao Yang Bin Cui School of Computer Science & Key Lab of High Confidence Software Technologies Peking University and Microsoft Microsoft Microsoft and Aerospace Information Research Institute & Key Laboratory of Target Cognition and Application Technology Chinese Academy of Sciences Microsoft and Institute of Information Engineering Chinese Academy of Sciences Carnegie Mellon University National University of Singapore School of Computer Science & Key Lab of High Confidence Software Technologies Peking University and National Engineering Laboratory for Big Data Analysis and Applications Peking University

Embedding-based retrieval methods construct vector indices to search for document representations that are most similar to the query representations. They are widely used in document retrieval due to low latency and decent recall performance. Recent research indicates that deep retrieval solutions offer better model quality, but are hindered by unacceptable serving latency and the inability to support document updates. In this paper, we aim to enhance the vector index with end-to-end deep generative models, leveraging the differentiable advantages of deep retrieval models while maintaining desirable serving efficiency. We propose Model-enhanced Vector Index (MEVI), a differentiable model-enhanced index empowered by a twin-tower representation model. MEVI leverages a Residual Quantization (RQ) codebook to bridge the sequence-to-sequence deep retrieval and embedding-based models. To substantially reduce the inference time, instead of decoding the unique document ids in long sequential steps, we first generate some semantic virtual cluster ids of candidate documents in a small number of steps, and then leverage the well-adapted embedding vectors to further perform a fine-grained search for the relevant documents in the candidate virtual clusters. We empirically show that our model achieves better performance on the commonly used academic benchmarks MSMARCO Passage and Natural Questions, with comparable serving latency to dense retrieval solutions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

How are We Detecting Inconsistent Method Names? An Empirical Study from Code Review Perspective

引用

ACM Transactions on software engineering and Methodology 1000年

作者： Kisub Kim Xin Zhou Dongsun Kim Julia Lawall Kui Liu Tegawendé F. Bissyandé Jacques Klein Jaekwon Lee David Lo Singapore Management University Singapore Korea University Korea Inria France Huawei Software Engineering Application Technology Lab China University of Luxembourg Luxembourg Kangwon National University Korea

Proper naming of methods can make program code easier to understand, and thus enhance software maintainability. Yet, developers may use inconsistent names due to poor communication or a lack of familiarity with conventions within the software development lifecycle. To address this issue, much research effort has been invested into building automatic tools that can check for method name inconsistency and recommend consistent names. However, existing datasets generally do not provide precise details about why a method name was deemed improper and required to be changed. Such information can give useful hints on how to improve the recommendation of adequate method names. Accordingly, we construct a sample method-naming benchmark, ReName4J, by matching name changes with code reviews. We then present an empirical study on how state-of-the-art techniques perform in detecting or recommending consistent and inconsistent method names based on ReName4J. The main purpose of the study is to reveal a different perspective based on reviewed names rather than proposing a complete benchmark. We find that the existing techniques underperform on our review-driven benchmark, both in inconsistent checking and the recommendation. We further identify potential biases in the evaluation of existing techniques, which future research should consider thoroughly.

关键词： Method Name Recommendation Consistency Checking Code Review Empirical Study

来源：评论

学校读者我要写书评

暂无评论

Contextualizing Meta-Learning via Learning to Decompose

arXiv

引用

arXiv 2021年

作者： Ye, Han-Jia Zhou, Da-Wei Hong, Lanqing Li, Zhenguo Wei, Xiu-Shen Zhan, De-Chuan State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China Huawei Noah’s Ark Lab Canada The School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Ministry of Education Nanjing210096 China

Meta-learning has emerged as an efficient approach for constructing target models based on support sets. For example, the meta-learned embeddings enable the construction of target nearest-neighbor classifiers for specific tasks by pulling instances closer to their same-class neighbors. However, a single instance can be annotated from various latent attributes, making visually similar instances inside or across support sets have different labels and diverse relationships with others. Consequently, a uniform meta-learned strategy for inferring the target model from the support set fails to capture the instance-wise ambiguous similarity. To this end, we propose Learning to Decompose Network (LEADNET) to contextualize the meta-learned "support-to-target" strategy, leveraging the context of instances with one or mixed latent attributes in a support set. In particular, the comparison relationship between instances is decomposed w.r.t. multiple embedding spaces. LEADNET learns to automatically select the strategy associated with the right attribute via incorporating the change of comparison across contexts with polysemous embeddings. We demonstrate the superiority of LEADNET in various applications, including exploring multiple views of confusing data, out-of-distribution recognition, and few-shot image classification. Copyright © 2021, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Why Blockchain Needs Graph: A Survey on Studies, Scenarios, and Solutions

SSRN

引用

SSRN 2023年

作者： Song, Jie Zhang, Pengyi Qu, Qiang Bai, Yongjie Gu, Yu Yu, Ge Software College Northeastern University Shenyang110819 China Shenzhen Institute of Advanced Technology Chinese Academy of Science Shenzhen518055 China Blockchain Lab Huawei Cloud Tech Co. Ltd Shenzhen518101 China School of Computer Science and Engineering Northeastern University Shenyang110819 China

The popularity of blockchain platforms and their applications in industry and academia keeps rising. The multifarious requirements stimulate another technique, graph data and algorithms, to join the blockchains;thus, studies, scenarios, and solutions about graph-related blockchains have emerged. State-of-the-art studies have reported on ``blockchain + graph'' solutions, but few of them natively integrate graph computing into a blockchain. Here, the ``graph integration'' means processing on-chain graph data, which contains blockchain information, in a real-time, distributed, and consensual manner. Aiming to answer why a blockchain needs graphs, and why a Graph-integrated Blockchain Platform (GiBP for short) is necessary and challengeable, we analyze literature about blockchain and graph, as well as use cases on the application-oriented and graph-related scenarios collected from practical blockchain projects. We draw the findings for three graph-related blockchain scenarios: graph algorithms for blockchains, graph data in blockchains, and graph applications on blockchains. Based on these findings, we explain why a GiBP is inevitable, the challenges of a GiBP, and the GiBPs’ main functions and features people expect. We also propose the prospection of a GiBP for future research. © 2023, The Authors. All rights reserved.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Finding Simplex Items in Data Streams

Finding Simplex Items in Data Streams

引用

International Conference on Data engineering

作者： Zhuochen Fan Jiarui Guo Xiaodong Li Tong Yang Yikai Zhao Yuhan Wu Bin Cui Yanwei Xu Steve Uhlig Gong Zhang School of Computer Science and National Engineering Laboratory for Big Data Analysis Technology and Application Peking University Beijing China Peng Cheng Laboratory Shenzhen China Theory Lab Central Research Institute 2012 Labs Huawei Technologies Co. Ltd. Hong Kong SAR China School of Electronic Engineering and Computer Science Queen Mary University of London London UK

In this paper, we propose a new type of item in data streams, called simplex items. Simplex items have frequencies in consecutive p windows that can be approximated by a polynomial of degree at most k, where k = 0, 1, 2. These low-order representable simplex items have a wide range of potential applications. For example, when k = 1, we can leverage these items whose frequency has obvious linear increase or decrease to speed up the running time of a class of machine learning models and detect network attacks such as distributed denial-of-service (DDoS), etc. To find k-degree simplex items in real time, we propose a novel sketch, namely X-Sketch, to accurately record simplex items in a compact space. The key idea of X-Sketch is to effectively filter out non-simplex items with less memory overhead, and then monitor the remaining potential simplex items and keep those items with more consecutive windows. We conduct extensive experiments, and the experimental results show that the F1 Score of X-Sketch is on average 68.6%, 57.9%, and 42.2% higher than the baseline solution for k = 0, 1, 2, respectively. Finally, we also provide a case study that applies X-Sketch to "accelerate" the two machine learning models through end-to-end experiments. We have released our source code at GitHub.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Globally optimal consensus maximization for robust visual inertial localization in point and line map

Globally optimal consensus maximization for robust visual in...

引用

2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Yanmei Jiao Yue Wang Bo Fu Qimeng Tan Lei Chen Minhang Wang Shoudong Huang Rong Xiong State Key Laboratory of Industrial Control and Technology Zhejiang University Hangzhou P.R. China Beijing Key Laboratory of Intelligent Space Robotic System Technology and Applications Beijing Institute of Spacecraft System Engineering Beijing P.R. China Minhang Wang is with the Application Lab Huawei Incorporated Company P.R. China Shoudong Huang is with the Center for Autonomous Systems (CAS) the University of Technology Sydney Australia

ISBN: (数字)9781728162126

ISBN: (纸本)9781728162133

Map based visual inertial localization is a crucial step to reduce the drift in state estimation of mobile robots. The underlying problem for localization is to estimate the pose from a set of 3D-2D feature correspondences, of which the main challenge is the presence of outliers, especially in changing environment. In this paper, we propose a robust solution based on efficient global optimization of the consensus maximization problem, which is insensitive to high percentage of outliers. We first introduce translation invariant measurements (TIMs) for both points and lines to decouple the consensus maximization problem into rotation and translation subproblems, allowing for a two-stage solver with reduced search space. Then we show that (i) the rotation can be estimated by minimizing TIMs using only 1-dimensional branch-and-bound (BnB), (ii) the translation can be estimated by running 1-dimensional search for each of the three axes with prioritized progressive voting. Compared with the popular randomized solver, our solver achieves deterministic global convergence without requiring an initial value. Furthermore, ours is exponentially faster compared with existing BnB based methods. Finally, our experiments on both simulation and real-world datasets demonstrate that the proposed method gives accurate pose estimation even in the presence of 90% outliers (only 2 inliers).

关键词： Location awareness Visualization Pose estimation Search problems State estimation Optimization Rotation measurement

来源：评论

学校读者我要写书评

暂无评论

Visual Tuning

arXiv

引用

arXiv 2023年

作者： Yu, Bruce X.B. Chang, Jianlong Wang, Haixin Liu, Lingbo Wang, Shijie Wang, Zhiyu Lin, Junfan Xie, Lingxi Li, Haojie Lin, Zhouchen Tian, Qi Chen, Chang Wen Zhejiang University University of Illinois Urbana-Champaign Institute Zhejiang University China Huawei China National Engineering Research Center for Software Engineering Peking University China Peng Cheng Laboratory China College of Computer Science and Engineering Shandong University of Science and Technology China National Key Lab of General AI School of Intelligence Science and Technology Peking University China Department of Computing The Hong Kong Polytechnic University Hong Kong

Fine-tuning visual models has been widely shown promising performance on many downstream visual tasks. With the surprising development of pre-trained visual foundation models, visual tuning jumped out of the standard modus operandi that fine-tunes the whole pre-trained model or just the fully connected layer. Instead, recent advances can achieve superior performance than full-tuning the whole pre-trained parameters by updating far fewer parameters, enabling edge devices and downstream applications to reuse the increasingly large foundation models deployed on the cloud. With the aim of helping researchers get the full picture and future directions of visual tuning, this survey characterizes a large and thoughtful selection of recent works, providing a systematic and comprehensive overview of existing work and models. Specifically, it provides a detailed background of visual tuning and categorizes recent visual tuning techniques into five groups: fine-tuning, prompt tuning, adapter tuning, parameter tuning, and remapping tuning. Meanwhile, it offers some exciting research directions for prospective pre-training and various interactions in visual tuning. Copyright © 2023, The Authors. All rights reserved.

关键词： Vision

来源：评论

学校读者我要写书评

暂无评论

City-Scale Localization with Telco Big Data 16

City-Scale Localization with Telco Big Data

引用

Proceedings of the 25th ACM International on Conference on Information and Knowledge Management

作者： Fangzhou Zhu Chen Luo Mingxuan Yuan Yijian Zhu Zhengqing Zhang Tao Gu Ke Deng Weixiong Rao Jia Zeng School of Computer Science and Technology Soochow University Suzhou China Huawei Noah's Ark Lab Hong Kong Hong Kong Hong Kong China United Network Communications Corporation Limited Shanghai Branch Shanghai China Computer Science RMIT University Melbourne Australia School of Software Engineering Tongji University China Shanghai China

ISBN: (纸本)9781450340731

It is still challenging in telecommunication (telco) industry to accurately locate mobile devices (MDs) at city-scale using the measurement report (MR) data, which measure parameters of radio signal strengths when MDs connect with base stations (BSs) in telco networks for making/receiving calls or mobile broadband (MBB) services. In this paper, we find that the widely-used location based services (LBSs) have accumulated lots of over-the-top (OTT) global positioning system (GPS) data in telco networks, which can be automatically used as training labels for learning accurate MR-based positioning systems. Benefiting from these telco big data, we deploy a context-aware coarse-to-fine regression (CCR) model in Spark/Hadoop-based telco big data platform for city-scale localization of MDs with two novel contributions. First, we design map-matching and interpolation algorithms to encode contextual information of road networks. Second, we build a two-layer regression model to capture coarse-to-fine contextual features in a short time window for improved localization performance. In our experiments, we collect 108 GPS-associated MR records in the centroid of Shanghai city with 12 x 11 square kilometers for 30 days, and measure four important properties of real-world MR data related to localization errors: stability, sensitivity, uncertainty and missing values. The proposed CCR works well under different properties of MR data and achieves a mean error of 110m and a median error of $80m$, outperforming the state-of-art range-based and fingerprinting localization methods.

关键词： regression models localization telco big data

来源：评论

学校读者我要写书评

暂无评论

Perceptive self-supervised learning network for noisy image watermark removal

arXiv

引用

arXiv 2024年

作者： Tian, Chunwei Zheng, Menghua Li, Bo Zhang, Yanning Zhang, Shichao Zhang, David School of Software Northwestern Polytechnical University Xi’an710129 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi’an710129 China School of Electronics and Information Northwestern Polytechnical University Xi’an710129 China School of Computer Science Northwestern Polytechnical University National Engineering Laboratory for Integrated AeroSpace-Ground-Ocean Big Data Application Technology Xi’an710129 China Guangxi Key Lab of Multisource Information Mining & Security College of Computer Science & Engineering Guangxi Normal University Guilin541004 China Shenzhen518172 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518172 China

Popular methods usually use a degradation model in a supervised way to learn a watermark removal model. However, it is true that reference images are difficult to obtain in the real world, as well as collected images by cameras suffer from noise. To overcome these drawbacks, we propose a perceptive self-supervised learning network for noisy image watermark removal (PSLNet) in this paper. PSLNet depends on a parallel network to remove noise and watermarks. The upper network uses task decomposition ideas to remove noise and watermarks in sequence. The lower network utilizes the degradation model idea to simultaneously remove noise and watermarks. Specifically, mentioned paired watermark images are obtained in a self-supervised way, and paired noisy images (i.e., noisy and reference images) are obtained in a supervised way. To enhance the clarity of obtained images, interacting two sub-networks and fusing obtained clean images are used to improve the effects of image watermark removal in terms of structural information and pixel enhancement. Taking into texture information account, a mixed loss uses obtained images and features to achieve a robust model of noisy image watermark removal. Comprehensive experiments show that our proposed method is very effective in comparison with popular convolutional neural networks (CNNs) for noisy image watermark removal. Codes can be obtained at https://***/hellloxiaotian/PSLNet. Copyright © 2024, The Authors. All rights reserved.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Model-enhanced Vector Index

arXiv

引用

arXiv 2023年

作者： Zhang, Hailin Wang, Yujing Chen, Qi Chang, Ruiheng Zhang, Ting Miao, Ziming Hou, Yingyan Ding, Yang Miao, Xupeng Wang, Haonan Pang, Bochen Zhan, Yuefeng Sun, Hao Deng, Weiwei Zhang, Qi Yang, Fan Xie, Xing Yang, Mao Cui, Bin School of Computer Science Key Lab of High Confidence Software Technologies Peking University China Microsoft United States Aerospace Information Research Institute Key Laboratory of Target Cognition and Application Technology Chinese Academy of Sciences China Institute of Information Engineering Chinese Academy of Sciences China Carnegie Mellon University United States National University of Singapore Singapore National Engineering Laboratory for Big Data Analysis and Applications Peking University China

Embedding-based retrieval methods construct vector indices to search for document representations that are most similar to the query representations. They are widely used in document retrieval due to low latency and decent recall performance. Recent research indicates that deep retrieval solutions offer better model quality, but are hindered by unacceptable serving latency and the inability to support document updates. In this paper, we aim to enhance the vector index with endto- end deep generative models, leveraging the differentiable advantages of deep retrieval models while maintaining desirable serving efficiency. We propose Modelenhanced Vector Index (MEVI), a differentiable model-enhanced index empowered by a twin-tower representation model. MEVI leverages a Residual Quantization (RQ) codebook to bridge the sequence-to-sequence deep retrieval and embeddingbased models. To substantially reduce the inference time, instead of decoding the unique document ids in long sequential steps, we first generate some semantic virtual cluster ids of candidate documents in a small number of steps, and then leverage the well-adapted embedding vectors to further perform a fine-grained search for the relevant documents in the candidate virtual clusters. We empirically show that our model achieves better performance on the commonly used academic benchmarks MSMARCO Passage and Natural Questions, with comparable serving latency to dense retrieval solutions. Copyright © 2023, The Authors. All rights reserved.

关键词： Embeddings

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：