Filters








69,423 Hits in 4.4 sec

Neural content-aware collaborative filtering for cold-start music recommendation [article]

Paul Magron, Cédric Févotte
2022 arXiv   pre-print
These approaches inherently face the cold-start problem, as they cannot recommend novel songs with no listening history.  ...  Experimental results show that the proposed method reaches state-of-the-art results for a cold-start music recommendation task.  ...  model can also be used for a traditional collaborative filtering task which does not suffer from the cold-start problem.  ... 
arXiv:2102.12369v3 fatcat:ysyk7nlqtbabdaa6hs25jfu3zy

Embedded Collaborative Filtering for "Cold Start" Prediction [article]

Yubo Zhou, Ali Nadaf
2017 arXiv   pre-print
"Cold Start" problem using only implicit data.  ...  We show that the ECF approach outperforms other popular and state-of-the-art approaches in "Cold Start" scenarios.  ...  For this setting, we combined dimensionality reduction method with Collaborative Filtering (CF) to enhance the performance of the recommendation system in the "Cold Start" scenarios.  ... 
arXiv:1704.02552v1 fatcat:lpmmbqb7q5ajrc36xbzhpur5k4

Social collaborative filtering for cold-start recommendations

Suvash Sedhain, Scott Sanner, Darius Braziunas, Lexing Xie, Jordan Christensen
2014 Proceedings of the 8th ACM Conference on Recommender systems - RecSys '14  
We formalize neighborhood-based methods for cold-start collaborative filtering in a generalized matrix algebra framework that does not require purchase data for target users when their side information  ...  These results demonstrate the substantial predictive power of social network content, and its significant utility in a challenging problem -recommendation for cold-start users.  ...  CONCLUSION We defined a novel social collaborative filtering framework that generalizes standard item-based collaborative filtering to the cold-start recommendation setting.  ... 
doi:10.1145/2645710.2645772 dblp:conf/recsys/SedhainSBXC14 fatcat:bsenkieinjgmli33hca7sdmbxi

Handling Cold-Start Collaborative Filtering with Reinforcement Learning [article]

Hima Varsha Dureddy, Zachary Kaden
2018 arXiv   pre-print
A major challenge in recommender systems is handling new users, whom are also called cold-start users.  ...  We propose learning interview questions using Deep Q Networks to create user profiles to make better recommendations to cold-start users.  ...  Methodology We propose a novel interview based method to address the cold-start problem in collaborative filtering.  ... 
arXiv:1806.06192v1 fatcat:xebbewm7uffjzkpa2wgqgeyliu

Wasserstein Collaborative Filtering for Item Cold-start Recommendation [article]

Yitong Meng, Guangyong Chen, Benben Liao, Jun Guo, Weiwen Liu
2019 arXiv   pre-print
The item cold-start problem seriously limits the recommendation performance of Collaborative Filtering (CF) methods when new items have either none or very little interactions.  ...  In this paper, we apply the Wasserstein distance to address the item cold-start problem.  ...  Instead of finding a common latent space of user-item interactions and item contents, we propose a Wasserstein Collaborative Filtering (WCF) approach to address the item cold-start problem.  ... 
arXiv:1909.04266v1 fatcat:pfpesfppezbtjhrqonsaz3fdte

Budget-Constrained Item Cold-Start Handling in Collaborative Filtering Recommenders via Optimal Design [article]

Oren Anava, Shahar Golan, Nadav Golbandi, Zohar Karnin, Ronny Lempel, Oleg Rokhlenko, Oren Somekh
2016 arXiv   pre-print
The lack of historical ratings results in the user and the item cold-start problems. The latter is the main focus of this work.  ...  It is well known that collaborative filtering (CF) based recommender systems provide better modeling of users and items associated with considerable rating history.  ...  One of the most common and effective recommendation techniques is Collaborative filtering (CF).  ... 
arXiv:1406.2431v3 fatcat:fj6wdku57ve5zhelhxznqx4g6u

CRUC: Cold-start Recommendations Using Collaborative Filtering in Internet of Things

Daqiang Zhang, Qin Zou, Haoyi Xiong
2011 Energy Procedia  
To this end, we propose CRUC scheme - Cold-start Recommendations Using Collaborative Filtering in IoT, involving formulation, filtering and prediction steps.  ...  Experimental results show that CRUC efficiently solves the cold-start problem in IoT.  ...  Acknowledgements This work is supported by the National Natural Science Foundation of China (Grant Nos. 61103185, 61003247 and 61073118), the Start-up Foundation of Nanjing Normal University (Grant No.  ... 
doi:10.1016/j.egypro.2011.11.497 fatcat:owy6m76eqvddzd4ksnza3bah6i

A Theoretical Analysis of Two-Stage Recommendation for Cold-Start Collaborative Filtering [article]

Xiaoxue Zhao, Jun Wang
2016 arXiv   pre-print
In this paper, we present a theoretical framework for tackling the cold-start collaborative filtering problem, where unknown targets (items or users) keep coming to the system, and there is a limited number  ...  Conclusion and Future Work In this paper, we presented a novel two-stage recommendation process to address the cold-start problems, with an item cold-start problem as a working example.  ...  Related Work and Discussion Collaborative Filtering Our work can be considered part of CF research [39] .  ... 
arXiv:1601.04745v1 fatcat:pswvl2noyjembokkare4kjzioq

Multi-Feature Discrete Collaborative Filtering for Fast Cold-start Recommendation [article]

Yang Xu, Lei Zhu, Zhiyong Cheng, Jingjing Li, Jiande Sun
2020 arXiv   pre-print
In this paper, we propose a fast cold-start recommendation method, called Multi-Feature Discrete Collaborative Filtering (MFDCF), to solve these problems.  ...  When the interaction history or the content feature is unavailable (the cold-start problem), their performance will be seriously deteriorated. 2) Existing methods learn the hash codes with relaxed optimization  ...  In this paper, we propose a fast cold-start recommendation method, called Multi-Feature Discrete Collaborative Filtering (MFDCF) to alleviate these problems.  ... 
arXiv:2003.10719v1 fatcat:7rpxit4r2jcc3dapnne4rqejfe

Combating the Cold Start User Problem in Model Based Collaborative Filtering [article]

Sampoorna Biswas, Laks V.S. Lakshmanan, Senjuti Basu Ray
2017 arXiv   pre-print
For tackling the well known cold-start user problem in model-based recommender systems, one approach is to recommend a few items to a cold-start user and use the feedback to learn a profile.  ...  We formalize the cold-start user problem by asking what are the b best items we should recommend to a cold-start user, in order to learn her profile most accurately, where b, a given budget, is typically  ...  Cold Start Problem in CF. e cold-start problem in CF-based recommender systems has been addressed using di erent approaches in prior work.  ... 
arXiv:1703.00397v1 fatcat:gedmnhxqc5hsbpc26suqomas6y

Multi-Feature Discrete Collaborative Filtering for Fast Cold-Start Recommendation

Yang Xu, Lei Zhu, Zhiyong Cheng, Jingjing Li, Jiande Sun
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
In this paper, we propose a fast cold-start recommendation method, called Multi-Feature Discrete Collaborative Filtering (MFDCF), to solve these problems.  ...  When the interaction history or the content feature is unavailable (the cold-start problem), their performance will be seriously deteriorated. 2) Existing methods learn the hash codes with relaxed optimization  ...  In this paper, we propose a fast cold-start recommendation method, called Multi-Feature Discrete Collaborative Filtering (MFDCF) to alleviate these problems.  ... 
doi:10.1609/aaai.v34i01.5360 fatcat:qj6plzj54jbgvohqngb352gyay

Collaborative Filtering Recommender System: Comparative Survey on Cold-Start Issue

S. Vairachilai
2018 Indian Journal of Science and Technology  
Objectives: To analyze the issue of cold-start (user cold-start and item cold-start) in Collaborative Filtering Recommender System (CFRS) and to compare its solution with various approaches are summarized  ...  Although the collaborative filtering recommender system successful, it undergoes a major issue such as  ...  The new user cold-start problem and new item cold-start problem is a very big challenge in the collaborative filtering recommender system.  ... 
doi:10.17485/ijst/2018/v11i20/116392 fatcat:2rav5q432jhulpxrsalsp5fkau

Cold-Start Management with Cross-Domain Collaborative Filtering and Tags [chapter]

Manuel Enrich, Matthias Braunhofer, Francesco Ricci
2013 Lecture Notes in Business Information Processing  
We show that the proposed techniques can effectively deal with the considered cold-start situation, given that the tags used in the two domains overlap.  ...  In this paper we deal with such a cold-start situation exploiting cross-domain recommendation techniques, i.e., we suggest items to a user in one target domain by using ratings of other users in a, completely  ...  Related Work As shown by [7] , cross-domain recommendation techniques can tackle cold-start problems in collaborative filtering.  ... 
doi:10.1007/978-3-642-39878-0_10 fatcat:7ixsnawqancwxc2pihniyhi62a

Trust-Based Collaborative Filtering: Tackling the Cold Start Problem Using Regular Equivalence [article]

Tomislav Duricic, Emanuel Lacic, Dominik Kowald, Elisabeth Lex
2018 arXiv   pre-print
User-based Collaborative Filtering (CF) is one of the most popular approaches to create recommender systems.  ...  CF, however, suffers from data sparsity and the cold-start problem since users often rate only a small fraction of available items.  ...  (CF) algorithm for cold-start users.  ... 
arXiv:1807.06839v1 fatcat:kkfhyzcu45cfnmhd7am5me4spu

Discrete Deep Learning Based Collaborative Filtering Approach for Cold Start Problem

Archana Kalidindi, Prasanthi Yavanamandha, Anusha Kunuku
2019 International Journal of Intelligent Engineering and Systems  
The recommendation system uses the most popular techniques namely Collaborative Filtering (CF) and Deep Learning Neural Network (DLNN) approach.  ...  The Cold-Start (CS) problem and the recommendation efficiency are considered as crucial challenges and affected the efficiency of the most popular techniques.  ...  In future, the recommendation of Netflix Price data will be improved with other deep learning techniques to reduce the problem of cold start in effective way. 𝑙 ( 1 )Figure. 1 A 11 Figure. 1 A graphic  ... 
doi:10.22266/ijies2019.0630.08 fatcat:sicavnlfy5dxfdpcuvfg34igmm
« Previous Showing results 1 — 15 out of 69,423 results