检索结果-内蒙古大学图书馆

30th ACM International Conference on Information and knowledge management (CIKM)

作者： Ma, Zhengyi Dou, Zhicheng Xu, Wei Zhang, Xinyu Jiang, Hao Cao, Zhao Wen, Ji-Rong Renmin Univ China Gaoling Sch Artificial Intelligence Beijing Peoples R China Huawei Distributed & Parallel Software Lab Beijing Peoples R China Beijing Key Lab Big Data Management & Anal Method Beijing Peoples R China MOE Key Lab Data Engn & Knowledge Engn Beijing Peoples R China

ISBN: (纸本)9781450384469

Designing pre-training objectives that more closely resemble the downstream tasks for pre-trained language models can lead to better performance at the fine-tuning stage, especially in the ad-hoc retrieval area. Existing pre-training approaches tailored for IR tried to incorporate weak supervised signals, such as query-likelihood based sampling, to construct pseudo query-document pairs from the raw textual corpus. However, these signals rely heavily on the sampling method. For example, the query likelihood model may lead to much noise in the constructed pre-training data. In this paper, we propose to leverage the large-scale hyperlinks and anchor texts to pre-train the language model for ad-hoc retrieval. Since the anchor texts are created by webmasters and can usually summarize the target document, it can help to build more accurate and reliable pre-training samples than a specific algorithm. Considering different views of the downstream ad-hoc retrieval, we devise four pre-training tasks based on the hyperlinks. We then pre-train the Transformer model to predict the pair-wise preference, jointly with the Masked Language Model objective. Experimental results on two large-scale ad-hoc retrieval datasets show the significant improvement of our model compared with the existing methods.

关键词： Ad-hoc Retrieval Pre-training Hyperlinks Anchor Texts

来源：评论

学校读者我要写书评

暂无评论

General Two-Stage Network Systems Based on Stackelberg Game

SSRN

引用

SSRN 2023年

作者： Zhang, Linyan Zhang, Jian Guo, Chuanyin School of Economics and Management Beijing Information Science & Technology University Beijing100192 China Research Center for Knowledge Management Beijing100192 China Beijing Key Lab of Green Development Decision Based on Big Data Beijing100192 China

Noncooperative approach is a key technique for modeling network systems. In general, there are two types of noncooperative network models in the literature. One is the bilevel model based on Stackelberg game, which is often transformed into a parametric linear program. The other is the leader-follower model, which uses only Stackelberg game concept, which may yield an infeasible solution. The current study shows that the bilevel model can be solved by using two linear models, without having to resort to solving heuristic parametric linear models. Furthermore, the global optimal solution is guaranteed for the nonlinear bilevel model. We prove the equivalence between the bilevel technique and our two linear-model approach. We further improve the existing leader-follower models, and as well the newly developed approaches are extended to general two-stage structures. The newly developed approaches are illustrated with a numerical data set and a real-world case. © 2023, The Authors. All rights reserved.

关键词： Linear programming

来源：评论

学校读者我要写书评

暂无评论

Robust high-dimensional regression for data with anomalous responses

引用

ANNALS OF THE INSTITUTE OF STATISTICAL MATHEMATICS 2021年第4期73卷 703-736页

作者： Ren, Mingyang Zhang, Sanguo Zhang, Qingzhao Univ Chinese Acad Sci Sch Math Sci Beijing 100049 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100049 Peoples R China Xiamen Univ Dept Stat Wang Yanan Inst Studies Econ MOE Key Lab EconSch Econ Xiamen 361005 Peoples R China Xiamen Univ Fujian Key Lab Stat Xiamen 361005 Peoples R China

The accuracy of response variables is crucially important to train regression models. In some situations, including the high-dimensional case, response observations tend to be inaccurate, which would lead to biased estimators by directly fitting a conventional model. For analyzing data with anomalous responses in the high-dimensional case, in this work, we adopt gamma-divergence to conduct variable selection and estimation methods. The proposed method possesses good robustness to anomalous responses, and the proportion of abnormal data does not need to be modeled. It is implemented by an efficient coordinate descent algorithm. In the setting where the dimensionalitypcan grow exponentially fast with the sample sizen, we rigorously establish variable selection consistency and estimation bounds. Numerical simulations and an application on real data are presented to demonstrate the performance of the proposed method.

关键词： Anomalous responses Robust gamma-divergence High-dimensional data

来源：评论

学校读者我要写书评

暂无评论

Meta-learning approaches for learning-to-learn in deep learning: A survey

引用

NEUROCOMPUTING 2022年 494卷 203-223页

作者： Tian, Yingjie Zhao, Xiaoxi Huang, Wei Univ Chinese Acad Sci Sch Econ & Management 80 Zhongguancun East Rd Beijing 100190 Peoples R China Univ Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci 80 Zhongguancun East Rd Beijing 100190 Peoples R China Univ Chinese Acad Sci Key Lab Big Data Min & Knowledge Management 80 Zhongguancun East Rd Beijing 100190 Peoples R China Southern Univ Sci & Technol Coll Business Shenzhen 518055 Peoples R China Xi An Jiao Tong Univ Sch Management Xian 710049 Shaanxi Peoples R China

Compared to traditional machine learning, deep learning can learn deeper abstract data representation and understand scattered data properties. It has gained considerable attention for its extraordinary performances. However, existing deep learning algorithms perform poorly on new tasks. Meta-learning, known as learning to learn, is one of the effective techniques to overcome this issue. Meta-learning's generalization ability to unknown tasks is improved by employing prior knowledge to assist the learning of new tasks. There are mainly three types of meta-learning methods: metric-based, model-based, and optimization-based meta-learning. We investigate classical algorithms and recent meta-learning advances. Second, we survey meta-learning application in real world scenarios. Finally, we discuss present challenges and future research directions of meta-learning. CO 2022 Elsevier B.V. All rights reserved.

关键词： Meta-learning Learning to learn Application

来源：评论

学校读者我要写书评

暂无评论

Image Orientation Estimation Based On Deep Learning - A Survey

引用

Procedia Computer Science 2024年 242卷 1193-1197页

作者： Ruijie Xu Yong Shi Zhiquan Qi Research Center on Fictitious Economy and Data Science University of Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences Beijing 00190 China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing 101408 China School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China College of Information Science and Technology University of Nebraska Omaha 68182 USA

In the realm of visual tasks, the estimation of orientation plays a pivotal role yet often remains an understudied aspect in the gamut of image analysis research. This paper endeavors to address this deficiency by conducting a comprehensive review of methods for orientation estimation within 2D imaging contexts. We aim to provide researchers with an exhaustive overview and detailed analysis of the techniques utilized for orientation estimation, thereby enhancing their understanding of this complex field. We introduce an organized classification of orientation estimation methods, segmented into approaches based on classification algorithms and those based on regression models. This classification not only sheds light on the distinct methodologies but also scrutinizes their underlying assumptions, practical applications. Additionally, the study identifies and underscores emerging research opportunities that hold the potential to enrich the discourse and technical advancements in orientation estimation, thereby encouraging deeper academic investigation and technological development.

关键词： Classification-based Orientation Estimation Regression-based Orientation Estimation

来源：评论

学校读者我要写书评

暂无评论

COVID-19 Impact on Global Electricity Generation Structure-Based on Sustainable Development Perspective

引用

Procedia computer science 2022年 214卷 1206-1213页

作者： Shuyang Peng Xian Yang Haibo Lu Kun Guo School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China. Research Center on Fictitious Economy & Data Science Chinese Academy of Sciences Beijing 100190 China. Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China.

This paper has sorted out the general logic of the impact of COVID-19 on energy consumption. In the short term, the epidemic has forced governments to adopt different levels of lockdown measures. The total electricity consumption decreased and the share of renewable energy has increased. Based on the International Energy Agency's (IEA) data on electricity production and consumption, this paper analyzes the long-term effects: The COVID-19 pandemic does affect overall electricity demand and market structure in the short term, but in the long term, the impact of the pandemic is detrimental to the proportion of electricity generated from renewable sources. Increased, especially in hard-hit countries. The impact on countries with different levels of development is different, and countries with higher levels of economic development are better able to resist such exogenous shocks. The pandemic is still ongoing, how to steadily promote sustainable development? In this paper we suggest that to cope with climate change, to accomplish energy transformation and upgrading or even sustainable development, we should not only rely on reducing human activities, but give more support to countries with low development levels in realizing sustainable development.

关键词： COVID-19 Electricity generation Renewable energy

来源：评论

学校读者我要写书评

暂无评论

An ES-based model with contemporaneous and temporal aggregation for forecasting intermittent and lumpy retail demand

引用

Procedia Computer Science 2024年 242卷 264-271页

作者： Erjiang E Xin Tian Ye Tao Huiqiang Sun School of Management Guangxi Minzu University Nanning 530006 China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing 100190 China School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy Sciences Beijing 100190 China Beijing Haolinju CVS Co. Ltd. Beijing 100018 China Shenghe (Beijing) Technology Development Co. Ltd. Beijing 101399 China

The demand for products in the retail industry is often characterized by intermittent and volatile patterns. Specifically, at the SKU level, the demand exhibits intermittent and lumpy behavior, which presents challenges for accurate forecasting due to demand fluctuations and interval uncertainty. This study proposes an exponential smoothing (ES)-based model, called ES-C-T, that incorporates contemporaneous and temporal aggregation to forecast intermittent and lumpy retail demand. The ES-C-T model consists of three stages. Firstly, the ES model predicts the sales of each product by aggregating contemporaneously across all stores, and the resulting predictions are allocated to the SKU level using a weight vector. Secondly, the ES model forecasts the sales of each SKU by aggregating temporally within each store. Finally, the ES-C-T model derives a weight coefficient based on the predictions from the first and second stages, adjusts the initial predictions, and utilizes this as the final forecast. To validate the effectiveness of the ES-C-T model, sales data from a large Chinese convenience store chain are employed. The results demonstrate that the proposed ES-C-T model outperforms the benchmark model in terms of MAE, RMSE, and WRMSSE, effectively predicting retail sales for intermittent and lumpy demand.

关键词： forecasting retailing intermittent demand lumpy demand aggregation

来源：评论

学校读者我要写书评

暂无评论

Information content and sentiment: the role of environmental disclosure in stock price crash risk

引用

International Review of Financial Analysis 2025年 104卷

作者： Long, Wen Ma, Ruiqi Guo, Man School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China Sino-Danish College University of Chinese Academy of Sciences Beijing 100190 China Research Center on Fictitious Economy & Data Science Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining & Knowledge Management Chinese Academy of Sciences Beijing 100190 China

Environmental disclosure is a topic of global importance. When negative environmental news emerges and is eventually revealed, it can influence investor decisions and lead to significant stock price movements, potentially resulting in stock price crashes. Therefore, using a sample of A-share listed companies on the Shanghai and Shenzhen Stock Exchanges from 2017 to 2022, we construct an environmental sentiment dictionary, establish an environmental disclosure content index system, and explore the influence mechanism of environmental disclosure on stock price crash risk. Findings show that increased environmental disclosure sentiment intensity can boost stock price crash risk, whereas greater environmental disclosure content can significantly reduce it. Furthermore, we identify a significant threshold effect related to the sentiment intensity of environmental disclosure. Notably, in environmental disclosure, sentiment tends to have a stronger impact than content. Mechanism analysis reveals that environmental disclosure content is influenced by external disclosure sources, the tone of internal annual reports, and internal control mechanisms. Meanwhile, environmental disclosure sentiment intensity is driven by earnings management and investor risk perception. This study develops a more comprehensive method for measuring environmental information disclosure and offers important insights for improving environmental management among listed companies. © 2025

关键词： Environmental information disclosure Sentiment analysis Stock price crash risk

来源：评论

学校读者我要写书评

暂无评论

Poisoning Attack Against Estimating From Pairwise Comparisons

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2022年第10期44卷 6393-6408页

作者： Ma, Ke Xu, Qianqian Zeng, Jinshan Cao, Xiaochun Huang, Qingming Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing 100049 Peoples R China Peng Cheng Lab Artificial Intelligence Res Ctr Shenzhen 518055 Guangdong Peoples R China Chinese Acad Sci Inst Comp Technol Key Lab Intelligent Informat Proc Beijing 100190 Peoples R China Jiangxi Normal Univ Sch Comp & Informat Engn Nanchang 330022 Jiangxi Peoples R China Chinese Acad Sci Inst Informat Engn State Key Lab Informat Secur SKLOIS Beijing 100093 Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing 100049 Peoples R China Univ Chinese Acad Sci Sch Econ & Management Key Lab Big Data Min & Knowledge Management Beijing 100049 Peoples R China

As pairwise ranking becomes broadly employed for elections, sports competitions, recommendation, information retrieval and so on, attackers have strong motivation and incentives to manipulate or disrupt the ranking list. They could inject malicious comparisons into the training data to fool the target ranking algorithm. Such a technique is called "poisoning attack" in regression and classification tasks. In this paper, to the best of our knowledge, we initiate the first systematic investigation of data poisoning attack on the pairwise ranking algorithms, which can be generally formalized as the dynamic and static games between the ranker and the attacker, and can be modeled as certain kinds of integer programming problems mathematically. To break the computational hurdle of the underlying integer programming problems, we reformulate them into the distributionally robust optimization (DRO) problems, which are computational tractable. Based on such DRO formulations, we propose two efficient poisoning attack algorithms and establish the associated theoretical guarantees including the existence of Nash equilibrium and the generalization ability bounds. The effectiveness of the suggested poisoning attack strategies is demonstrated by a series of toy simulations and several real data experiments. These experimental results show that the proposed methods can significantly reduce the performance of the ranker in the sense that the correlation between the true ranking list and the aggregated results with toxic data can be decreased dramatically.

关键词： Optimization Heuristic algorithms Sports Voting Uncertainty Games data models Adversarial learning poisoning attack pairwise comparison rank aggregation robust game distributionally robust optimization

来源：评论

学校读者我要写书评

暂无评论

A Review on the Construction of Business Intelligence System Based on Unstructured Image data

引用

Procedia Computer Science 2022年 199卷 392-398页

作者： Linzi Zhang Zhiquan Qi Fan Meng School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China Research Center on Fictitious Economy & Data Science Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China Department of Infomation Management Peking University Beijing 100871 China

Business Intelligence (BI) has been an emerging significant issue in modern government and corporate functions, which attracts the attention of both researchers and merchants. Using the raw data from customers, BI provides effective decision-making knowledge for various cooperate governance operations with the method of data Warehouse and data mining. As the explosive growth of data volume, it has evolved into using unstructured data including image and text in business intelligence system, from the initial descriptive analysis of computational statements. This paper will review the methods of storing and analyzing the unstructured image data used in the construction of BI system, including traditional image processing and novel deep learning methods. In each method, the specific algorithms and application scenarios will be summarized. Together, we will discuss the possible innovative progress of BI system construction and its future trends.

关键词： Business intelligence Unstructured image data big data fusion

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：