Filters








56,292 Hits in 5.1 sec

Learning to rank for hybrid recommendation

Jiankai Sun, Shuaiqiang Wang, Byron J. Gao, Jun Ma
2012 Proceedings of the 21st ACM international conference on Information and knowledge management - CIKM '12  
In this paper, we propose LRHR, the first attempt that adapts learning to rank to hybrid recommender systems.  ...  Finally, LRHR adopts RankSVM, a pairwise learning to rank algorithm, to generate recommendation lists of items for users.  ...  Learning to rank for hybrid recommendation. Existing hybrid recommender systems are not ranking-based. Existing learning to rank for recommendation methods do not use valuable content information.  ... 
doi:10.1145/2396761.2398610 dblp:conf/cikm/SunWGM12 fatcat:je6gcoyunba53arzkm3ks4ydki

Top-N recommendations from implicit feedback leveraging linked open data

Vito Claudio Ostuni, Tommaso Di Noia, Eugenio Di Sciascio, Roberto Mirizzi
2013 Proceedings of the 7th ACM conference on Recommender systems - RecSys '13  
We leverage DBpedia, a well-known knowledge base in the LOD (Linked Open Data) compass, to extract semantic path-based features and to eventually compute recommendations using a learning to rank algorithm  ...  In this paper we present SPrank, a novel hybrid recommendation algorithm able to compute top-N item recommendations from implicit feedback exploiting the information available in the so called Web of Data  ...  This allows us to evaluate our learning to rank algorithm against a basic not ranking-oriented semantic recommender.  ... 
doi:10.1145/2507157.2507172 dblp:conf/recsys/OstuniNSM13 fatcat:uxejdjxyu5a3zhswdtpatzatnu

Hybrid Collaborative Recommendation via Semi-AutoEncoder [article]

Shuai Zhang, Lina Yao, Xiwei Xu, Sen Wang, Liming Zhu
2017 arXiv   pre-print
We generalize it into a hybrid collaborative filtering model for rating prediction as well as personalized top-n recommendations.  ...  The first category aims to use AutoEncoder to learn salient feature representations and integrate them into traditional recommendation models. For example, Li et al.  ...  -SLIM [8] , SLIM is a state-of-the-art top-n recommendation model. We optimize the objective function in a Bayesian personalized ranking criterion. We set the learning rate to 0.05.  ... 
arXiv:1706.04453v2 fatcat:eifj6pzsxzahfpxv3plwrxhebu

Plugin of Recommendation Based on a Hybrid Method for the Ranking of Documents in the E-Learning Platforms [chapter]

Hicham Moutachaouik, Hassan Douzi, Abdelaziz Marzak, Hicham Behja, Brahim Ouhbi
2012 Lecture Notes in Computer Science  
This system includes a new hybrid method to rank documents web, in order to propose to the Webmaster (or admin) of platform e-learning the best available documents based of the historical to research done  ...  It is, actually a meta-search engine on the web, integrated into the e-learning platform to keep surfing traces of the learner during his searching.  ...  of web usage mining and the rank produce recommendations for improving the services arning to guide and facilitate learning of learners.  ... 
doi:10.1007/978-3-642-31254-0_67 fatcat:sgqsltwvkjaq7one6wrfy2nmmy

Learning Resource Recommendation: An Orchestration of Content-Based Filtering, Word Semantic Similarity and Page Ranking [chapter]

Nguyen Ngoc Chan, Azim Roussanaly, Anne Boyer
2014 Lecture Notes in Computer Science  
Page ranking is applied to identify the importance of each resource according to its relations to others. Finally, a hybrid approach that orchestrates these techniques has been proposed.  ...  In this paper, we present an approach that combines three recommendation technologies: content-based filtering, word semantic similarity and page ranking to make resource recommendations.  ...  Learning Resource Recommendation In this section, we present in detail approach to recommend learning resources for an active user.  ... 
doi:10.1007/978-3-319-11200-8_23 fatcat:yfxcra3tfrarbgcbel67i3udhy

Design and Analysis of a Cluster-Based Intelligent Hybrid Recommendation System for E-Learning Applications

S. Bhaskaran, Raja Marappan, B. Santhi
2021 Mathematics  
Recently, different recommendation techniques in e-learning have been designed that are helpful to both the learners and the educators in a wide variety of e-learning systems.  ...  For the sample dataset considered, a significant difference was observed in the standard deviation σ and mean μ of parameters, in terms of the Recall (List, User) and Ranking Score (User) measures, compared  ...  Acknowledgments: The authors would like to acknowledge the support rendered by the Management of SASTRA Deemed University in providing financial support.  ... 
doi:10.3390/math9020197 fatcat:gdguyd6v5vhc3pcinjqjv5u7re

ParsRec: A Novel Meta-Learning Approach to Recommending Bibliographic Reference Parsers [article]

Dominika Tkaczyk, Rohit Gupta, Riccardo Cinti, Joeran Beel
2018 arXiv   pre-print
We propose two approaches to meta-learning recommendations. The first approach learns the best parser for an entire reference string.  ...  We propose ParsRec, a meta-learning based recommender-system that recommends the potentially most effective parser for a given reference string.  ...  The meta-learning set was used for training of the meta-learning recommenders. All parsers were applied to the meta-learning set and evaluated.  ... 
arXiv:1811.10369v1 fatcat:4m7yzfx6znbsrijjbyeftr5ozq

An Adversarial Deep Hybrid Model for Text-Aware Recommendation with Convolutional Neural Networks

Xiaolin Zheng, Disheng Dong
2019 Applied Sciences  
Furthermore, we propose an adversarial training framework to learn the hybrid recommendation model, where a generator model is built to learn the distribution over the pairwise ranking pairs while training  ...  The standard matrix factorization methods for recommender systems suffer from data sparsity and cold-start problems.  ...  Second, with the aim of reflecting the ranking nature of top-N recommendation, we propose an adversarial learning framework to capture the pair-wise ranking distribution over user-item interactions in  ... 
doi:10.3390/app10010156 fatcat:yp7k3zyt5fau7kp4ki6kbz3aau

Collaborative factorization for recommender systems

Chaosheng Fan, Yanyan Lan, Jiafeng Guo, Zuoquan Lin, Xueqi Cheng
2013 Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval - SIGIR '13  
Recommender system has become an effective tool for information filtering, which usually provides the most useful items to users by a top-k ranking list.  ...  To overcome the above problems, we propose a new framework for recommender systems, called collaborative factorization.  ...  There are also some work trying to combine the two techniques to enhance recommendation, such as re-ranking model and hybrid model [4, 12] . For example, Koren et al.  ... 
doi:10.1145/2484028.2484176 dblp:conf/sigir/FanLGLC13 fatcat:bcum75gs2zgfddoct6l3y7scwu

Personalized Service Recommendation With Mashup Group Preference in Heterogeneous Information Network

Fenfang Xie, Liang Chen, Dongding Lin, Zibin Zheng, Xiaola Lin
2019 IEEE Access  
Finally, we recommend a list of personalized ranking services for mashup developers.  ...  Next, we introduce group preference to capture the rich interactions among mashups and apply a group preference-based Bayesian personalized ranking algorithm to learn the model.  ...  It uses a Bayesian personalized ranking algorithm to learn the weights of meta paths, and recommends a set of services for mashup creation [17] .  ... 
doi:10.1109/access.2019.2894822 fatcat:3c2ijwlfv5arzd6apwkmushs3u

Model Size Reduction Using Frequency Based Double Hashing for Recommender Systems [article]

Caojin Zhang, Yicun Liu, Yuanpu Xie, Sofia Ira Ktena, Alykhan Tejani, Akshay Gupta, Pranay Kumar Myana, Deepak Dilipkumar, Suvadip Paul, Ikuhiro Ihara, Prasang Upadhyaya, Ferenc Huszar (+1 others)
2020 arXiv   pre-print
In this paper, we propose a hybrid hashing method to combine frequency hashing and double hashing techniques for model size reduction, without compromising performance.  ...  Deep Neural Networks (DNNs) with sparse input features have been widely used in recommender systems in industry. These models have large memory requirements and need a huge amount of training data.  ...  We, thus, propose a hybrid layer to combine frequency hashing with double hashing for sparse input feature embedding, which addresses the pain point of model size in deep learning-based recommender systems  ... 
arXiv:2007.14523v1 fatcat:oh7xmkcu5jdgdk6uacpo2aiyle

A Hybrid Approach for Paper Recommendation

Ying KANG, Aiqin HOU, Zimin ZHAO, Daguang GAN
2021 IEICE transactions on information and systems  
In this paper, we construct a graphical form of citation relations to identify relevant papers and design a hybrid recommendation model that combines both citationand content-based approaches to measure  ...  Due to the lack of user profiles in public digital libraries, most existing methods for paper recommendation are through paper similarity measurements based on citations or contents, and still suffer from  ...  Hybrid Similarity We compute hybrid similarity sim i to rank candidate recommended papers RP(t) through a hybrid approach by combing citation similarity and content similarity, as follows: sim i = sim  ... 
doi:10.1587/transinf.2020bdp0008 fatcat:kjob3rxaung3xm7k4r4tgm24ly

Tag-Aware Personalized Recommendation Using a Hybrid Deep Model

Zhenghua Xu, Thomas Lukasiewicz, Cheng Chen, Yishu Miao, Xiangwu Meng
2017 Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence  
To ensure the scalability in practice, we further propose to improve this model's training efficiency by using hybrid deep learning and negative sampling.  ...  hybrid deep learning and negative sampling can dramatically enhance the model's training efficiency (hundreds of times quicker), while maintaining similar (and sometimes even better) training quality  ...  used to rank a personalized recommendation list for the given user u.  ... 
doi:10.24963/ijcai.2017/446 dblp:conf/ijcai/XuLCMM17 fatcat:t3swnssa3zbupfios6durr5gcq

Hybrid Deep-Semantic Matrix Factorization for Tag-Aware Personalized Recommendation [article]

Zhenghua Xu, Cheng Chen, Thomas Lukasiewicz, Yishu Miao
2017 arXiv   pre-print
recommendation by integrating the techniques of deep-semantic modeling, hybrid learning, and matrix factorization.  ...  Matrix factorization has now become a dominant solution for personalized recommendation on the Social Web.  ...  The intuitions of using the hybrid learning signal are: (i) minimizing reconstruction errors can learn better representations for both users and items; (ii) deepsemantic matrix factorization offers a learning  ... 
arXiv:1708.03797v1 fatcat:hm6ck7qbibfrdp7jwjnjwk7npa

Deep Learning and Collaborative Filtering-Based Methods for Students' Performance Prediction and Course Recommendation

Jinyang Liu, Chuantao Yin, Yuhang Li, Honglu Sun, Hong Zhou, Yinghui Ye
2021 Wireless Communications and Mobile Computing  
Then, for the courses in the list, we use a hybrid prediction model to predict the student's performance in each course, that is, ranking prediction.  ...  In order to help students solve this problem, this paper proposed a hybrid prediction model based on deep learning and collaborative filtering.  ...  Deep learning can also be used for personalized recommendation modules to recommend more relevant content to educators.  ... 
doi:10.1155/2021/2157343 fatcat:mbj6tghe4fhfhdyzneda36wi2y
« Previous Showing results 1 — 15 out of 56,292 results