24,835 Hits in 3.3 sec

Learning Recommender Systems from Multi-Behavior Data [article]

Chen Gao, Xiangnan He, Dahua Gan, Xiangning Chen, Fuli Feng, Yong Li, Tat-Seng Chua, Depeng Jin
2018 arXiv   pre-print
To fully exploit the signal in the data of multiple types of behaviors, we perform a joint optimization based on the multi-task learning framework, where the optimization on a behavior is treated as a  ...  Extensive experiments on two real-world datasets demonstrate that NMTR significantly outperforms state-of-the-art recommender systems that are designed to learn from both single-behavior data and multi-behavior  ...  Briefly, our method combines the recent advance of neural collaborative filtering with multi-task learning to effectively learn from multiple types of user behaviors.  ... 
arXiv:1809.08161v3 fatcat:6qje73dawnhfvejda2j6bh3hjm

Filtering Out Unfair Recommendations for Trust Model in Ubiquitous Environments [chapter]

Weiwei Yuan, Donghai Guan, Sungyoung Lee, Young-Koo Lee, Heejo Lee
2006 Lecture Notes in Computer Science  
Incremental learning based neural network is used to dispose the context in order to find doubtful recommendations.  ...  This approach has distinct advantages when dealing with randomly given irresponsible recommendations, individual unfair recommendations as well as unfair recommendations flooding.  ...  Training of Cascade-Correlation Architecture We use incremental learning based neural network, the Cascade-Correlation architecture in particular, to learn each recommender's rule on recommendation giving  ... 
doi:10.1007/11961635_27 fatcat:67usuonehvfbjbolxzdwxenr3y

Finding Reliable Recommendations for Trust Model [chapter]

Weiwei Yuan, Donghai Guan, Sungyoung Lee, Youngkoo Lee, Andrey Gavrilov
2006 Lecture Notes in Computer Science  
The incremental learning based neural network used in our approach also enables to filter out the unfair recommendations with limited information about the recommenders.  ...  Incremental learning based neural network is used to dispose the context in order to detect doubtful recommendations.  ...  The reason is that to judge the validity of recommendations, each recommender's current behavior should be compared with his past behaviors.  ... 
doi:10.1007/11912873_39 fatcat:46xbzlaktzgklktbhe3pcqsdsi

ARGO: Modeling Heterogeneity in E-commerce Recommendation [article]

Daqing Wu, Xiao Luo, Zeyu Ma, Chong Chen, Minghua Deng, Jinwen Ma
2021 arXiv   pre-print
Meanwhile, shopping process has also changed incrementally from one behavior (purchase) to multiple behaviors (such as view, carting and purchase).  ...  Second (inter-heterogeneity), each item can transfer an item-specific percentage of score from low-level behavior to high-level behavior for the gradual relationship among multiple behaviors.  ...  leverage multiple user behaviors for recommender systems [4] .  ... 
arXiv:2109.05789v2 fatcat:t4bwlrlbirh3rlkcgdaqxgy22e

DCM Bandits: Learning to Rank with Multiple Clicks [article]

Sumeet Katariya, Branislav Kveton, Csaba Szepesvári, Zheng Wen
2016 arXiv   pre-print
This work presents the first practical and regret-optimal online algorithm for learning to rank with multiple clicks in a cascade-like click model.  ...  We propose DCM bandits, an online learning variant of the DCM where the goal is to maximize the probability of recommending satisfactory items, such as web pages.  ...  The DCM is a generalization of the cascade model where the user may click on multiple items. At time t, our learning agent recommends to the user a list of K items.  ... 
arXiv:1602.03146v2 fatcat:yixxwteyn5ha5ayfugrf62juta

Cascading: Association Augmented Sequential Recommendation [article]

Xu Chen and Kenan Cui and Ya Zhang and Yanfeng Wang
2019 arXiv   pre-print
The two parts are connected into an end-to-end network with cascading style, which guarantees that representations for item associations and sequential relationships are learned simultaneously and make  ...  Recently, recommendation according to sequential user behaviors has shown promising results in many application scenarios.  ...  in cascading style for sequential user behavior.  ... 
arXiv:1910.07792v1 fatcat:anckr553fnckrenspenxquli2m

Cascading Bandits: Learning to Rank in the Cascade Model [article]

Branislav Kveton, Csaba Szepesvari, Zheng Wen, Azin Ashkan
2015 arXiv   pre-print
In this paper, we propose cascading bandits, a learning variant of the cascade model where the objective is to identify K most attractive items.  ...  The user examines this list, from the first web page to the last, and chooses the first attractive page. This model of user behavior is known as the cascade model.  ...  In this paper, we propose an online learning variant of the cascade model, which we refer to as cascading bandits.  ... 
arXiv:1502.02763v2 fatcat:o2kila5lx5afpfmqe4en4eg5ia

Thought and Behavior Contagion in Capital Markets [chapter]

David Hirshleifer, Siew Hong Teoh
2009 Handbook of Financial Markets: Dynamics and Evolution  
Social influence is central to how information and investor sentiment are transmitted, so thought and behavior contagion should be incorporated into the theory of capital markets.  ...  We review here evidence concerning how these activities cause beliefs and behaviors to spread, affect financial decisions, and affect market prices; and theoretical models of social influence and its effects  ...  However, in settings with multiple dimensions of uncertainty, quasi-cascading behavior can occur in which individuals trade in opposition to their information signals.  ... 
doi:10.1016/b978-012374258-2.50005-1 fatcat:muqitjwxmnhhvd4ej5wvusr24y

Cascade Ranking for Operational E-commerce Search

Shichen Liu, Fei Xiao, Wenwu Ou, Luo Si
2017 Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '17  
Effectiveness of e-commerce search involves multiple types of user behaviors such as click and purchase, while most existing cascade ranking in search only models the click behavior.  ...  Valuable prior research has been conducted for learning to efficiently rank like the cascade ranking (learning) model, which uses a sequence of ranking functions to progressively filter some items and  ...  RELATED WORK Machine learning algorithms such as learning to rank have been successfully used in many ranking problems with a set of available items such as Web search, feed ranking, recommendation and  ... 
doi:10.1145/3097983.3098011 dblp:conf/kdd/LiuXOS17 fatcat:5o4hsiua5ncg7ginwbkn2dmk4u

Cascading Bandits for Large-Scale Recommendation Problems [article]

Shi Zong, Hao Ni, Kenny Sung, Nan Rosemary Ke, Zheng Wen, and Branislav Kveton
2016 arXiv   pre-print
In this work, we study cascading bandits, an online learning variant of the cascade model where the goal is to recommend K most attractive items from a large set of L candidate items.  ...  This type of user behavior can be modeled by the cascade model.  ...  [13] proposed a generalization of cascading bandits to multiple clicks, by proposing a learning variant of the dependent click model [12] .  ... 
arXiv:1603.05359v2 fatcat:nbu2h56i5rb4dniquheqtpcjzq

Climbing the Branches of a Family Tree: Diagnosis of Fragile X Syndrome

Jeannie Visootsak, Heather Hipp, Heather Clark, Elizabeth Berry-Kravis, Tovi Anderson, Dawn Laney
2014 Journal of Pediatrics  
Conclusions-Our study confirms that taking a detailed family history after diagnosis of a proband with FXS is likely to identify multiple family members with FMR1 mutations.  ...  Objective-To determine the average number of family members who are diagnosed with a Fragile X Mental Retardation-1 (FMR1) mutation after a proband receives the initial diagnosis of Fragile X syndrome  ...  Acknowledgments We would like to thank the Fragile X Association of Georgia for their support of individuals with Fragile X syndrome and their families.  ... 
doi:10.1016/j.jpeds.2014.01.051 pmid:24612903 pmcid:PMC4035419 fatcat:t773ynmpwbg7nklw2u22oeswxa

DyDiff-VAE: A Dynamic Variational Framework for Information Diffusion Prediction [article]

Ruijie Wang, Zijie Huang, Shengzhong Liu, Huajie Shao, Dongxin Liu, Jinyang Li, Tianshi Wang, Dachun Sun, Shuochao Yao, Tarek Abdelzaher
2021 arXiv   pre-print
(ii) We propose a dual attentive decoder to estimate the propagation likelihood by integrating information from both the initial cascade content and the forwarding user sequence.  ...  Moreover, it has the lowest run-time compared with recurrent neural network based models.  ...  With advances in representation learning and deep learning, recent works [19, 34, 40, [43] [44] [45] 50] design end-to-end frameworks to automatically learn diffusion patterns from data.  ... 
arXiv:2106.03251v1 fatcat:forh47cfcnhb3dlk44wq4mqr2u

Multiplex Behavioral Relation Learning for Recommendation via Memory Augmented Transformer Network

Lianghao Xia, Chao Huang, Yong Xu, Peng Dai, Bo Zhang, Liefeng Bo
2020 Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval  
To tackle the above challenge, this work proposes a Memory-Augmented Transformer Networks (MATN), to enable the recommendation with multiplex behavioral relational information, and joint modeling of type-specific  ...  In our MATN framework, we first develop a transformer-based multi-behavior relation encoder, to make the learned interaction representations be reflective of the cross-type behavior relations.  ...  Recommendation with Multi-Behavior Learning: • NMTR [7] : It is a multi-task recommendation model which considers the behavior correlations in a cascaded manner. • DIPN [8] : This model utilizes bi-directional  ... 
doi:10.1145/3397271.3401445 dblp:conf/sigir/XiaHXDZB20 fatcat:vn6dqjgycfhtfixke6g4m554ie

Information Diffusion Prediction with Latent Factor Disentanglement [article]

Haoran Wang, Cheng Yang
2020 arXiv   pre-print
To address this problem, we propose to employ the idea of disentangled representation learning, which aims to extract multiple latent factors representing different aspects of the data, for modeling the  ...  In recent years, deep learning based methods, especially those based on recurrent neural networks (RNNs), have achieved promising results on this task by treating infected users as sequential data.  ...  In the field of recommendation systems, a few works are proposed to learn disentangled item representations [35] .  ... 
arXiv:2012.08828v1 fatcat:jfkv4avsczdhjhe6smrw7u3kxa

Full-scale Cascade Dynamics Prediction with a Local-First Approach [article]

Tao Wu, Leiting Chen, Xingping Xian, Yuxiao Guo
2015 arXiv   pre-print
Here we propose a unified framework, FScaleCP, to solve the problem. Given history cascades, we first model the local spreading behaviors as a classification problem.  ...  Through data-driven learning, we recognize the common patterns by measuring the driving mechanisms of cascade dynamics.  ...  The authors also wish to thank the anonymous reviewers for their thorough review and highly appreciate their useful comments and suggestions.  ... 
arXiv:1512.08455v1 fatcat:djsu2sbpy5gafoulq3jufnik3a
« Previous Showing results 1 — 15 out of 24,835 results