检索结果-南通市图书馆

A survey on causal inference for recommendation

The Innovation 2024年第2期5卷 130-144页

作者： Huishi Luo fuzhen zhuang Ruobing Xie Hengshu Zhu Deqing Wang Zhulin An Yongjun Xu Institute of Artificial Intelligence Beihang UniversityBeijing 100191China Zhongguancun Laboratory Beijing 100094China WeChat Search Application Department TencentBeijing 100080China The Career Science Laboratory BOSS ZhipinBeijing 100028China SKLSDE School of Computer ScienceBeihang UniversityBeijing 100191China Institute of Computing Technology Chinese Academy of SciencesBeijing 100190China

Causal inference has recently garnered significant interest among recommender system(RS)researchers due to its ability to dissect cause-and-effect relationships and its broad applicability across multiple *** offers a framework to model the causality in RSs such as confounding effects and deal with counterfactual problems such as offline policy evaluation and data *** there are already some valuable surveys on causal recommendations,they typically classify approaches based on the practical issues faced in RS,a classification that may disperse and fragment the uni-fied causal *** RS researchers’unfamiliarity with causality,it is necessary yet challenging to comprehensively review relevant studies from a coherent causal theoretical perspective,thereby facilitating a deeper integration of causal inference in *** survey provides a systematic review of up-to-date papers in this area from a causal theory standpoint and traces the evolutionary development of RS methods within the same causal ***,we introduce the fundamental concepts of causal inference as the basis of the following ***,we propose a novel theory-driven taxonomy,categorizing existing methods based on the causal theory employed,namely those based on the potential outcome framework,the structural causal model,and general *** review then delves into the technical details of how existing methods apply causal inference to address particular recommender ***,we highlight some promising directions for future research in this *** papers and open-source resources will be progressively available at https://***/Chrissie-Law/Causal-Inference-forRecommendation.

关键词： survey details causal

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

基于集合效用边际贡献学习的可解释薪酬预测算法

引用

计算机研究与发展 2024年第5期61卷 1276-1289页

作者：孙莹章玉婷庄福振祝恒书何清熊辉香港科技大学(广州)人工智能学域广州511458 中国科学院计算技术研究所专项技术研究中心北京100190 北京航空航天大学人工智能研究院北京100191 BOSS直聘职业科学实验室北京100028 中国科学院智能信息处理重点实验室(中国科学院计算技术研究所) 北京100190 中国科学院大学北京101408

知识技能对薪酬影响作用视为一种多变量影响下高维元素集合的效用建模问题.深度神经网络为解决复杂问题提供了新的机遇,但针对知识导向的细粒度薪酬预测问题,仍缺乏能够对复杂变量影响下的集合效用进行准确、可解释建模的神经网络结构.... 详细信息

知识技能对薪酬影响作用视为一种多变量影响下高维元素集合的效用建模问题.深度神经网络为解决复杂问题提供了新的机遇,但针对知识导向的细粒度薪酬预测问题,仍缺乏能够对复杂变量影响下的集合效用进行准确、可解释建模的神经网络结构.为此,提出一种基于边际贡献的增量式集合效用网络(marginal contribution-based incremental set utility network,MCISUN)来拟合元素加入时的效用增量,从而灵活且可解释地建模集合效用.区别于以往基于池化层的排列不变性建模算法,MCISUN构建顺序敏感的中间结果,利用集合的排列不变性实现数据增强,有效提升模型数据效率及泛化性.最后,大规模真实薪酬数据上的实验结果表明所提模型在基于技能的薪酬预测任务上比最先进的(state-of-the-art,SOTA)模型效果提升超过30%.同时,定性实验证明模型能够为技能设置合理的贡献值且发现技能间的关联.

关键词：集合效用建模边际贡献薪酬预测神经网络可解释性

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

面向企业信用风险评估的多视角异质图神经网络方法

引用

计算机研究与发展 2024年第8期61卷 1957-1967页

作者：魏少朋梁婷赵宇庄福振任福继西南财经大学工商管理学院成都611130 西南财经大学会计学院成都611130 金融智能与金融工程四川省重点实验室(西南财经大学) 成都611130 北京航空航天大学人工智能研究院北京100191 电子科技大学计算机科学与工程学院(网络空间安全学院) 成都611731

企业信用风险评估是一个重要且具有挑战的问题.由于金融市场中存在大量的异质关联关系,使得异质图神经网络天然适合建模企业信用风险.然而,现有大部分研究不能充分捕捉到复杂金融网络中企业的综合信用风险.针对此问题,提出了一个面向企... 详细信息

企业信用风险评估是一个重要且具有挑战的问题.由于金融市场中存在大量的异质关联关系,使得异质图神经网络天然适合建模企业信用风险.然而,现有大部分研究不能充分捕捉到复杂金融网络中企业的综合信用风险.针对此问题,提出了一个面向企业信用风险评估的多视角异质图神经网络方法——CRGNN.该方法包含自身风险编码器以及传染风险编码器,其中自身风险编码器建模基于企业特征信息的自身风险,传染风险编码器由新提出的分层异质图Transformer网络和分层异质图特征注意力网络2个子模块组成.这2个模块分别挖掘基于企业不同邻居视角的传染风险和基于不同特征维度视角的传染风险.为了充分利用异质关系信息,2个模块都采用了分层机制.在企业破产预测数据集SMEsD和企业信用评估数据集ECAD上进行了大量的实验,AUC指标相比最优基线模型分别提高了3.98个百分点和3.47个百分点.

关键词：图神经网络信用风险评估传染风险深度学习金融科技

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Combat data shift in few-shot learning with knowledge graph

引用

Frontiers of Computer Science 2023年第1期17卷 101-111页

作者： Yongchun ZHU fuzhen zhuang Xiangliang ZHANG Zhiyuan QI Zhiping SHI Juan CAO Qing HE Key Lab of Intelligent Information Processing of Chinese Academy of Sciences(CAS) Institute of Computing TechnologyCASBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China Institute of Artificial Intelligence Beihang UniversityBeijing 100191China Xiamen Institute of Data Intelligence Xiamen 361021China Computer Science and Engineering University of Notre DameIN 46556USA University of California San Diego La JollaCA 92093USA College of Information Engineering&Academy for Multidisciplinary Studies Capital Normal UniversityBeijing 100089China

Many few-shot learning approaches have been designed under the meta-learning framework, which learns from a variety of learning tasks and generalizes to new tasks. These meta-learning approaches achieve the expected performance in the scenario where all samples are drawn from the same distributions (i.i.d. observations). However, in real-world applications, few-shot learning paradigm often suffers from data shift, i.e., samples in different tasks, even in the same task, could be drawn from various data distributions. Most existing few-shot learning approaches are not designed with the consideration of data shift, and thus show downgraded performance when data distribution shifts. However, it is non-trivial to address the data shift problem in few-shot learning, due to the limited number of labeled samples in each task. Targeting at addressing this problem, we propose a novel metric-based meta-learning framework to extract task-specific representations and task-shared representations with the help of knowledge graph. The data shift within/between tasks can thus be combated by the combination of task-shared and task-specific representations. The proposed model is evaluated on popular benchmarks and two constructed new challenging datasets. The evaluation results demonstrate its remarkable performance.

关键词： few-shot data shift knowledge graph

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Inductive transfer learning for unlabeled target-domain via hybrid regularization

引用

Chinese Science Bulletin 2009年第11期54卷 2470-2478页

作者： zhuang fuzhen LUO Ping HE Qing SHI ZhongZhi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Hewlett Packard Labs China Beijing 100084 China Graduate University of Chinese Academy of Sciences Beijing 100190 China

Recent years have witnessed an increasing interest in transfer learning. This paper deals with the classification problem that the target-domain with a different distribution from the source-domain is totally unlabeled, and aims to build an inductive model for unseen data. Firstly, we analyze the problem of class ratio drift in the previous work of transductive transfer learning, and propose to use a normalization method to move towards the desired class ratio. Furthermore, we develop a hybrid regularization framework for inductive transfer learning. It considers three factors, including the distribution geometry of the target-domain by manifold regularization, the entropy value of prediction probability by entropy regularization, and the class prior by expectation regularization. This framework is used to adapt the inductive model learnt from the source-domain to the target-domain. Finally, the experiments on the real-world text data show the effectiveness of our inductive method of transfer learning. Meanwhile, it can handle unseen test points.

关键词：归纳学习正规化标签杂交归一化法预测概率文字资料归纳法

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Bayesian dual neural networks for recommendation

引用

Frontiers of Computer Science 2019年第6期13卷 1255-1265页

作者： Jia HE fuzhen zhuang Yanchi LIU Qing HE Fen LIN Key Lab of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China Rutgers University Newark 07102USA Search Product Center WeChat Search Application DepartmentTencentBeijing 100080China

Most traditional collaborative filtering(CF)methods only use the user-item rating matrix to make recommendations,which usually suffer from cold-start and sparsity *** address these problems,on the one hand,some CF methods are proposed to incorporate auxiliary information such as user/item profiles;on the other hand,deep neural networks,which have powerful ability in learning effective representations,have achieved great success in recommender ***,these neural network based recommendation methods rarely consider the uncertainty of weights in the network and only obtain point estimates of the ***,they maybe lack of calibrated probabilistic predictions and make overly confident *** this end,we propose a new Bayesian dual neural network framework,named BDNet,to incorporate auxiliary information for ***,we design two neural networks,one is to learn a common low dimensional space for users and items from the rating matrix,and another one is to project the attributes of users and items into another shared latent *** that,the outputs of these two neural networks are combined to produce the final ***,we introduce the uncertainty to all weights which are represented by probability distributions in our neural networks to make calibrated probabilistic *** experiments on real-world data sets are conducted to demonstrate the superiority of our model over various kinds of competitors.

关键词： collaborative filtering Bayesian neural network hybrid recommendation algorithm

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Parallel Web Mining System Based on Cloud Platform

引用

ZTE Communications 2012年第4期10卷 45-53页

作者： Shengmei Luo Qing He Lixia Liu Xiang Ao Ning Li fuzhen zhuang Pre-Research department of ZTE Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Graduate University of Chinese Academy of Sciences

Traditional machine-learning algorithms are struggling to handle the exceedingly large amount of data being generated by the internet. In real-world applications, there is an urgent need for machine-learning algorithms to be able to handle large-scale, high-dimensional text data. Cloud computing involves the delivery of computing and storage as a service to a heterogeneous community of recipients, Recently, it has aroused much interest in industry and academia. Most previous works on cloud platforms only focus on the parallel algorithms for structured data. In this paper, we focus on the parallel implementation of web-mining algorithms and develop a parallel web-mining system that includes parallel web crawler; parallel text extract, transform and load （ETL） and modeling; and parallel text mining and application subsystems. The complete system enables variable real-world web-mining applications for mass data.

关键词： web mining large scale high volume high dimension cloudcomputing

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Potential Off-Grid User Prediction System Based on Spark

引用

ZTE Communications 2019年第2期17卷 26-37页

作者： LI Xuebing SUN Ying zhuang fuzhen HE Jia ZHANG Zhao ZHU Shijun HE Qing Institute of Computing Technology Chinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China College of Information Science and Engineering Yanshan UniversityQinhuangdaoHebei 066004China ZTE Corporation ShenzhenGuangdong 518057China

With the increasingly fierce competition among communication operators,it is more and more important to make an accurate prediction of potential off grid *** solve the above problem,it is inevitable to consider the effectiveness of learning algo rithms,the efficiency of data processing,and other ***,in this paper,we,from the practical application point of view,propose a potential customer off grid predic tion system based on Spark,including data pre processing,feature selection,model build ing,and effective ***,in the research of off grid system,we use the Spark parallel framework to improve the gcForest algorithm which is a novel decision tree ensemble *** new parallel gcForest algorithm can be used to solve practical problems,such as the off grid prediction *** on two real world datasets demonstrate that the proposed prediction system can handle large scale data for the off grid user prediction problem and the proposed parallel gcForest can achieve satisfying per formance.

关键词： data mining off grid prediction Spark parallel computing deep forest

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

易变数据流的系统资源配置方法

引用

智能系统学报 2019年第6期14卷 1278-1285页

作者：王春凯庄福振史忠植中国再保险(集团)股份有限公司博士后科研工作站北京100033 中国科学院计算技术研究所北京100190

大规模数据流管理系统往往由上层的关系查询系统和下层的流处理系统组成。当用户提交查询请求时,往往需要根据数据流的流速和分布情况动态配置系统参数。然而,由于数据流的易变性,频繁改变参数配置会降低系统性能。针对该问题,提出了Ori... 详细信息

大规模数据流管理系统往往由上层的关系查询系统和下层的流处理系统组成。当用户提交查询请求时,往往需要根据数据流的流速和分布情况动态配置系统参数。然而,由于数据流的易变性,频繁改变参数配置会降低系统性能。针对该问题,提出了OrientStream+框架。设定以用户自定义查询延迟阈值为间隔片段的微批量数据流传输机制;并利用多级别管道缓存,对相同配置的数据流进行批量处理;然后按照数据流的时间戳计算出精准查询结果;引入基于异常检测的增量学习模型,用于提高OrientStream+的预测精度。最后,在Storm上实现了该资源配置框架,并进行了大量的实验。实验结果表明,OrientStream+框架可进一步降低系统的处理延迟并提高系统的吞吐率。

关键词：大规模数据流管理系统易变数据流增量学习模型预测参数配置微批处理系统性能异常检测

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

基于集成局部性特征学习的推荐算法

引用

计算机科学与探索 2018年第6期12卷 851-858页

作者：庄福振罗丹何清中国科学院计算技术研究所智能信息处理重点实验室北京100190 中国科学院大学北京100049

以往的协同过滤方法大部分采用基于矩阵分解的方法来学习用户和商品的隐性特征表示,但是基于矩阵分解的方法没有完全利用评分信息,导致不好的效果。近年来,深度学习已经在自然语言处理、语音识别以及图像分类等领域被证明可以很好地进... 详细信息

以往的协同过滤方法大部分采用基于矩阵分解的方法来学习用户和商品的隐性特征表示,但是基于矩阵分解的方法没有完全利用评分信息,导致不好的效果。近年来,深度学习已经在自然语言处理、语音识别以及图像分类等领域被证明可以很好地进行表示学习。而且在用户对商品的评分矩阵中,不仅只有评分信息,还有隐含的倾向性排序信息。更进一步,针对整个评分矩阵进行特征表示学习的时候,不能满足用户聚类以及商品类别的局部结构特性。因此,提出了一种基于集成局部性特征学习的推荐算法。在该算法中,利用随机选择的锚点得到局部矩阵,然后在局部矩阵上利用自动编码机进行学习得到子模型,同时定义一种(用户,商品)二元组来考虑评分信息的排序关系。在两组数据上进行了实验,结果表明该算法显著优于经典的基于矩阵分解的推荐算法,并且该算法将深度学习用于推荐系统中,效果比LCR(local collaborative ranking)优越。

关键词：推荐系统深度学习自动编码机排序学习局部结构

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：