检索结果-内蒙古大学图书馆

Mitigating Confounding Bias in Practical Recommender Systems With Partially Inaccessible Exposure Status

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2024年第2期46卷 957-974页

作者： Cao, Tianwei Xu, Qianqian Yang, Zhiyong Huang, Qingming Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing 101408 Peoples R China Chinese Acad Sci Inst Comp Technol Key Lab Intelligent Informat Proc Beijing 100190 Peoples R China Univ Chinese Acad Sci Key Lab Big Data Min & Knowledge Management BDKM Beijing 101408 Peoples R China Peng Cheng Lab Shenzhen 518055 Peoples R China

To improve user experience, recommender systems have been widely used on many online platforms. In these systems, recommendation models are typically learned from positive/negative feedback that are collected automatically. Notably, recommender systems are a little different from general supervised learning tasks. In recommender systems, there are some factors (e.g., previous recommendation models or operation strategies of a online platform) that determine which items can be exposed to each individual user. Normally, the previous exposure results are not only relevant to the instances' features (i.e., user or item), but also affect their feedback ratings, thus leading to confounding bias in the recommendation models. To mitigate this bias, researchers have already provided a variety of strategies. However, there are still two issues that are underappreciated: 1) previous debiased RS approaches cannot effectively capture recommendation-specific, exposure-specific and their common knowledge simultaneously;2) the true exposure results of the user-item pairs are partially inaccessible, so there would be some noises if we use their observability to approximate it as existing approaches. Motivated by this, we develop a novel debiasing recommendation approach. More specifically, we first propose a mutual information-based counterfactual learning framework based on the causal relationship among the instance features, exposure status, and ratings. This framework can 1) capture recommendation-specific, exposure-specific and their common knowledge by explicitly modeling the relationship among the causal factors, and 2) achieve robustness towards partially inaccessible exposure results by a pairwise learning strategy. Under such a framework, we implement an optimizable loss function with theoretical analysis. By minimizing this loss, we expect to obtain an unbiased recommendation model that reflects the users' real interests. Meanwhile, we also prove that our loss function has

关键词： Recommender system collaborative filtering confounding bias debias counterfactual learning

来源：评论

学校读者我要写书评

暂无评论

How does green credit affect carbon emissions in China? A theoretical analysis framework and empirical study

引用

ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH 2022年第39期29卷 59712-59726页

作者： Hu, Yi Zheng, Jiayu Univ Chinese Acad Sci Sch Econ & Management Zhongguancun South Yitiao Rd Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management 80 Zhongguancun East Rd Beijing 100190 Peoples R China

As an important part of China's green finance, green credit is regarded as an important tool to promote China's transformation to a low-carbon economy. In order to clarify the mechanism of green credit on carbon emissions, this paper puts forward a theoretical analysis framework including "functional attributes - micro subject response - key influencing factors" from the macro and micro perspectives. We select the panel data of 30 provinces in China from 2005 to 2019 for an empirical test and identify the action paths of green credit on carbon emission based on the mediating effect model. Further, we consider the special mechanism of "signal formation" and test it based on the dynamic panel threshold model. The results show that: (1) China's green credit mainly inhibits carbon emissions through three paths: industrial structure, energy structure and energy intensity. (2) There is a signal formation mechanism for the impact of green credit on carbon emissions, which mainly acts on the two action paths of industrial structure and energy intensity. (3) The signal formation mechanism is heterogeneous in each province. According to the empirical results, we divide the provinces into three echelons and propose corresponding suggestions.

关键词： Green credit Carbon emissions Theoretical analysis framework Mediating effect model Dynamic panel threshold model

来源：评论

学校读者我要写书评

暂无评论

CSL-CTEA: a systematic method for evaluating novel intelligent cognitive assessment tools

引用

HEALTH INFORMATION SCIENCE AND SYSTEMS 2025年第1期13卷 1-17页

作者： Li, Aihua Chen, Sifan Liu, Jianbing Chen, Ting Shi, Yong Cent Univ Finance & Econ Sch Management Sci & Engn Beijing 102206 Peoples R China Beijing Acad Sci & Technol Res Inst Smart Aging Beijing 100050 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China Univ Nebraska Omaha Coll Informat Sci & Technol Omaha NE 68182 USA

With the intensification of global population aging, the incidence of cognitive disorders such as dementia continues to rise. The Mini-Mental State Examination (MMSE) and other alternative tools can help doctors detect subtle changes in cognitive function at an early stage. These assessment tools can make a diagnosis before symptoms become severe, providing opportunities for early intervention, which is crucial for delaying disease progression and improving the quality of life of patients. However, traditional cognitive assessment methods are overly complex and affected by various factors. With the development of artificial intelligence technology, many new assessment tools are constantly being developed and improved. How to evaluate the effectiveness of intelligent electronic cognitive assessment tools is particularly important. We have proposed the Correlation and Supervised Learning-based Cognitive Tool Effectiveness Assessment Method (CSL-CTEA) to evaluate the effectiveness of intelligent electronic cognitive assessment tools, including: (1) experimental design and data collection based on traditional scales and intelligent electronic assessment tools, (2) consistency and correlation tests;(3) accuracy analysis of assessment results based on supervised learning. We used CSL-CTEA to explore the effectiveness of a certain electronic assessment. This intelligent electronic cognitive assessment tool includes voice tests, orientation tests, and picture recognition tests to assess cognitive abilities from multiple perspectives. The results show that the electronic assessment is in good agreement with traditional cognitive assessment methods. The various indicators of the electronic assessment can explain the changes in MMSE scores to some extent. The study also found that the electronic assessment performs well in determining whether the subject is at cognitive risk. To some extent, the electronic assessment can replace traditional cognitive assessment methods such as

关键词： Cognitive assessment MMSE Electronic assessment Regression Random Forest

来源：评论

学校读者我要写书评

暂无评论

Review and research frontier analysis of low carbon economy - Based on bibliometric methods 10

Review and research frontier analysis of low carbon economy ...

引用

10th International Conference on Information Technology and Quantitative management, ITQM 2023

作者： Yao, Tongsheng Shi, Yong Chen, Ming School of Economics and Management University of Chinese Academy Sciences Beijing100190 China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China School of Management and Economics Beijing Institute of Technology Beijing100081 China

Research in the carbon field has experienced rapid growth in recent years and has attracted widespread academic attention. This paper conducts a comprehensive analysis of the carbon field using bibliometric methods. By collecting a large number of academic publications related to carbon and utilizing bibliometric indicators, We performed statistical and descriptive analyses on the development trends, research areas, research institutions, and authors in the field of carbon economy literature. Additionally, we employed co-citation analysis and keyword co-occurrence analysis to identify the current research focuses in the carbon field and explore the temporal changes in research hotspots. Ultimately, we analyzed the future development trends of the carbon field, providing valuable insights for scholars to conduct further research in this field. These research findings are of great significance in promoting the development and application of the carbon economy field. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the Tenth International Conference on Information Technology and Quantitative management.

关键词： Carbon

来源：评论

学校读者我要写书评

暂无评论

Robust multi-view learning with the bounded LINEX loss

引用

NEUROCOMPUTING 2023年 518卷 384-400页

作者： Tang, Jingjing He, Hao Fu, Saiji Tian, Yingjie Kou, Gang Xu, Shan Southwestern Univ Finance & Econ Fac Business Adm Sch Business Adm Chengdu 611130 Peoples R China Southwestern Univ Finance & Econ Inst Big Data Chengdu 611130 Peoples R China Beijing Univ Posts & Telecommun Sch Econ & Management Beijing 100876 Peoples R China Univ Chinese Acad Sci Sch Econ & Management Beijing 100190 Peoples R China Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China

Multi-view learning, as a promising direction, emphasizes the consensus principle and the complemen-tarity principle to boost the performance. By exploiting view-consistency or view-discrepancy among dif-ferent views, numerous successful multi-view support vector machine models have been proposed. However, existing methods face two challenges. Firstly, most multi-view support vector machine models only consider the consensus principle, but ignore the complementarity principle. How to build a novel model with both principles has not been fully considered. Secondly, most multi-view support vector machine models neglect the robustness when the multi-view dataset is contaminated by the noisy sam-ples, error-prone samples and view-inconsistent samples. Considering that the bounded linear -exponential (BLINEX) loss function possesses elegant merits, i.e., asymmetry and boundedness, develop-ing a robust BLINEX-based model is worth exploring. Therefore, in this paper, we propose a BLINEX-based multi-view learning method called MVASY-BX, which explores the consensus and complementarity information with a between-view co-regularization term and importance weights of two views respec-tively. The mixed BLINEX loss is designed to make the model robust to noisy samples, view -inconsistent samples and error-prone samples. We solve linear and nonlinear MVASY-BX through the stochastic sub-gradient descent algorithm and the alternating direction method of multipliers respec-tively. Furthermore, we analyze the generalization error bound via Rademacher complexity. The compre-hensive experiments confirm that our proposed model is more competitive than other benchmark methods.(c) 2022 Elsevier B.V. All rights reserved.

关键词： Multi -view learning Support vector machine BLINEX loss function Consensus and complementary information Robustness

来源：评论

学校读者我要写书评

暂无评论

Deep image matting with cross-layer contextual information propagation

引用

NEURAL COMPUTING & APPLICATIONS 2024年第12期36卷 6809-6825页

作者： Zhou, Fenfen Tian, Yingjie Zhu, Siyu Beijing Union Univ Beijing Key Lab Informat Serv Engn Beijing 100101 Peoples R China Beijing Union Univ Coll Robot Beijing 100027 Peoples R China UCAS Sch Econ & Management Beijing 100190 Peoples R China Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China Beijing Informat Sci & Technol Univ Comp Sch Beijing 100192 Peoples R China

Natural image matting focuses on accurately estimating the opacity of the foreground object in an arbitrary background. Recently, deep learning-based approaches made significant progress in the matting task benefit from their powerful learning ability for semantic features. However, artifacts, blurry structures, and miscalculated pixels still often appear in some difficult regions with background interference and complex details. To address the above issues, we propose a cross-layer contextual information propagation mechanism (CCIP) that can explicitly model the long-range correlations between global and unknown regions. Specifically, we first calculate region affinity at high-level features with rich structure and semantic information;then reconstruct the adjacent low-level features by propagating information from the global region to the unknown region under the guidance of the affinity matrix;finally, transfer the reconstructed information to the corresponding decoder stage to further improve the feature distinctiveness. In addition, we design a simple and effective supervision strategy in a deep-to-shallow manner to gradually optimize the edges and details of the foreground object. We conducted extensive experiments on the common dataset Composition-1k, the *** benchmark, and some real-world images. Compared with previous methods, the proposed method achieves competitive performance on the Composition-1k dataset (30.3 on SAD, 6.8 on MSE, 13.3 on Grad, and 26.7 on Con) and *** benchmark (17 on average SAD rank and 16.8 on average Grad rank), while simultaneously yielding high-quality matting results on real-world images.

关键词： Natural image matting Contextual information propagation Long-range correlation Supervision strategy

来源：评论

学校读者我要写书评

暂无评论

Lower Bounds of Uniform Stability in Gradient-Based Bilevel Algorithms for Hyperparameter Optimization 38

Lower Bounds of Uniform Stability in Gradient-Based Bilevel ...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Wang, Rongzhen Zheng, Chenyu Wu, Guoqiang Min, Xu Zhang, Xiaolu Zhou, Jun Li, Chongxuan Gaoling School of Artificial Intelligence Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods China School of Software Shandong University China Ant Group China

Gradient-based bilevel programming leverages unrolling differentiation (UD) or implicit function theorem (IFT) to solve hyperparameter optimization (HO) problems, and is proven effective and scalable in practice. To understand the generalization behavior, existing works establish upper bounds on the uniform stability of these algorithms, while their tightness is still unclear. To this end, this paper attempts to establish stability lower bounds for UD-based and IFT-based algorithms. A central technical challenge arises from the dependency of each outer-level update on the concurrent stage of inner optimization in bilevel programming. To address this problem, we introduce lower-bounded expansion properties to characterize the instability in update rules which can serve as general tools for lower-bound analysis. These properties guarantee the hyperparameter divergence at the outer level and the Lipschitz constant of inner output at the inner level in the context of HO. Guided by these insights, we construct a quadratic example that yields tight lower bounds for the UD-based algorithm and meaningful bounds for a representative IFT-based algorithm. Our tight result indicates that uniform stability has reached its limit in stability analysis for the UD-based algorithm. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sparse Learning for Neural Networks with A Generalized Sparse Regularization 9th

Sparse Learning for Neural Networks with A Generalized Spars...

引用

9th International Conference on Information Technology and Quantitative management, ITQM 2022

作者： Tang, Anda Yao, Tongsheng Niu, Lingfeng Shi, Yong School of Mathematical Sciences University of Chinese Academy of Sciences Beijing100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China

Deep neural networks (DNNs) is very important and have achieved remarkable accuracies in tasks such as image processing. However, the success of DNNs heavily relies on excessive computation and parameter storage costs. To cut down the overheads, a wide range of regularization terms are proposed on netwok compression, which have their own scope of application though. To further reduce computation, structural sparsity learning is a matter of great concern where group sparse regularizations are blossoming in radiant splendour. However, the group sparse regularizations used in network compression is relatively scarce. A majority of structural compression only stem from 2,1 regularization. In addition, sparse regularization in structural network compression lacks unified form and theoretical guidance. Therefore, we focus our attention on a generalized sparse regularization in sparse learning of deep learning. We put a series of sparse regularization into a framework where some group sparse regularizations with different properties are introduced. The transformation of regularizations can be completed through the selection of hyper-parameters. In this case, we can use the optimization strategy for unification and theoretical guidance, and transform different sparse regularizations to adapt to different tasks. To our knowledge, it is the first work applying the generalized sparse regularization with novel group sparsity in compression of DNNs. The proposed p,q,r regularization can achieve both neuron-level and connection-level sparsity. And we give the analytical solutions for some specific (p,q, r) thus the compression can be achieved throughout the standard optimization process. We perform extensive experiments to illustrate the advantages and characteristics of our new method for further applications. © 2022 The Author(s).

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Improved credit risk prediction based on an integrated graph representation learning approach with graph transformation

引用

EUROPEAN JOURNAL OF OPERATIONAL RESEARCH 2024年第3期315卷 786-801页

作者： Shi, Yong Qu, Yi Chen, Zhensong Mi, Yunlong Wang, Yunong Univ Chinese Acad Sci Sch Econ & Management Beijing 100190 Peoples R China Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China Univ Nebraska Omaha Coll Informat Sci & Technol Omaha NE 68182 USA Capital Univ Econ & Business Sch Management & Engn Beijing 100070 Peoples R China Cent South Univ Sch Business Changsha 410083 Peoples R China

Accurate credit risk prediction effectively supports decision makings and risk prevention in quantitative management. The general paradigm of previous works usually conducts supervised classification with internal information (credit attributes) of instances, while recent studies have introduced external information like texts, images, relations, to improve predictive accuracy. However, how to improve forecasting without explicit external relations still needs to be explored. Motivated by this and also by the increasing popularity of Graph Neural Network (GNN) with its fast infiltration into other disciplines, we propose an integrated graph representation learning approach to realize improved credit risk prediction. It includes two stages: (i) treat instances as nodes and use kNN to extract and construct edges;(ii) implement GNN models to discriminate risk/default cases by node classification. In this way, both "unsupervised"graph transformation and "supervised"node classification have been integrated to formulate the hybrid kNN-GNN model, and experiments on widely -used credit datasets demonstrate its outperformance over direct classification by conventional machine learning techniques. Sensitivity of hyperparameter k indicating different graph sparsity is also analyzed to reveal its optimal selection. Furthermore, ensemble multi -graphs and introduce edge weights are examined to investigate possible advancements with some enhancements observed for both, providing feasible ways to extend the upper bound of this hybrid model's performances. Our findings exhibit valid improvements in credit risk prediction under the circumstance of only internal information available, and in depth present the future prospects of innovative integrations and applications of GNN methods in dealing with many other operational research tasks.

关键词： Decision support systems Credit risk prediction Graph representation learning Graph neural network Graph transformation

来源：评论

学校读者我要写书评

暂无评论

ICLEval: Evaluating In-Context Learning Ability of Large Language Models 31

ICLEval: Evaluating In-Context Learning Ability of Large Lan...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Chen, Wentong Lin, Yankai Zhou, ZhenHao Huang, HongYun Jia, Yantao Cao, Zhao Wen, Ji-Rong Gaoling School of Artificial Intelligence Renmin University of China China Huawei Poisson Lab China Beijing Key Laboratory of Big Data Management and Analysis Methods China School of Information Renmin University of China China

ISBN: (纸本)9798891761964

In-Context Learning (ICL) is a critical capability of Large Language Models (LLMs) as it empowers them to comprehend and reason across interconnected inputs. Evaluating the ICL ability of LLMs can enhance their utilization and deepen our understanding of how this ability is acquired at the training stage. However, existing evaluation frameworks primarily focus on language abilities and knowledge, often overlooking the assessment of ICL ability. In this work, we introduce the ICLEval benchmark to evaluate the ICL abilities of LLMs, which encompasses two key sub-abilities: exact copying and rule learning. Through the ICLEval benchmark, we demonstrate that ICL ability is universally present in different LLMs, and model size is not the sole determinant of ICL efficacy. Surprisingly, we observe that ICL abilities, particularly copying, develop early in the pretraining process and stabilize afterward. Our source codes and benchmark are released at https://***/RUCBM/ICLEval. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

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：