6,959 Hits in 3.9 sec

Task-adaptive Neural Process for User Cold-Start Recommendation [article]

Xixun Lin, Jia Wu, Chuan Zhou, Shirui Pan, Yanan Cao, Bin Wang
2021 arXiv   pre-print
User cold-start recommendation is a long-standing challenge for recommender systems due to the fact that only a few interactions of cold-start users can be exploited.  ...  In this paper, we develop a novel meta-learning recommender called task-adaptive neural process (TaNP).  ...  TASK-ADAPTIVE NEURAL PROCESS In this section, we first describe how to handle user cold recommendation from the view of NP.  ... 
arXiv:2103.06137v1 fatcat:cxkie6g4lfattkmrjf2ajjau3e

MAMO: Memory-Augmented Meta-Optimization for Cold-start Recommendation [article]

Manqing Dong and Feng Yuan and Lina Yao and Xiwei Xu and Liming Zhu
2020 arXiv   pre-print
A common challenge for most current recommender systems is the cold-start problem.  ...  And we adopt a meta-optimization approach for optimizing the proposed method. We test the model on two widely used recommendation datasets and consider four cold-start situations.  ...  cold-start user.  ... 
arXiv:2007.03183v1 fatcat:cg7gn5an6rcsvfjel3arno2mim

Learning to Learn a Cold-start Sequential Recommender [article]

Xiaowen Huang, Jitao Sang, Jian Yu, Changsheng Xu
2021 arXiv   pre-print
We propose a meta-learning based cold-start sequential recommendation framework called metaCSR, including three main components: Diffusion Representer for learning better user/item embedding through information  ...  The cold-start recommendation is an urgent problem in contemporary online applications. It aims to provide users whose behaviors are literally sparse with as accurate recommendations as possible.  ...  adapt to unseen new users' recommendation tasks.  ... 
arXiv:2110.09083v1 fatcat:kmnlo5ji3zbdriknkrnrr5vl7a

A Multi-Strategy based Pre-Training Method for Cold-Start Recommendation [article]

Bowen Hao, Hongzhi Yin, Jing Zhang, Cuiping Li, Hong Chen
2022 arXiv   pre-print
Cold-start problem is a fundamental challenge for recommendation tasks.  ...  The recent self-supervised learning (SSL) on Graph Neural Networks (GNNs) model, PT-GNN, pre-trains the GNN model to reconstruct the cold-start embeddings and has shown great potential for cold-start recommendation  ...  However, the GNN models for recommendation can not thoroughly solve the cold-start problem, as the embeddings of the cold-start users/items aren't explicitly optimized, and the cold-start neighbors have  ... 
arXiv:2112.02275v4 fatcat:57pgrrsqtfa67e7miotkkeczh4

MetaKG: Meta-learning on Knowledge Graph for Cold-start Recommendation [article]

Yuntao Du, Xinjun Zhu, Lu Chen, Ziquan Fang, Yunjun Gao
2022 arXiv   pre-print
' preference and entities' knowledge for cold-start recommendations.  ...  However, most of them ignore the cold-start problems (i.e., user cold-start and item cold-start) of recommendation analytics, which restricts their performance in scenarios when involving new users or  ...  For testing data, users and items are partitioned into three scenarios: User Cold-start (UC), (i.e. recommending old items for new users); Item Cold-start (IC), (i.e., recommending new items for old users  ... 
arXiv:2202.03851v1 fatcat:ue5s7yvno5bnzi5mj5widt2obq

Eliciting Auxiliary Information for Cold Start User Recommendation: A Survey

Nor Aniza Abdullah, Rasheed Abubakar Rasheed, Mohd Hairul Nizam Md. Nasir, Md Mujibur Rahman
2021 Applied Sciences  
Existing studies that reviewed and examined cold start in recommender systems have not explained the process of deriving and obtaining the auxiliary information needed for cold start recommendation.  ...  The key challenges of the process for obtaining the auxiliary information involve: (1) two separate recommendation processes of conversion from pure cold start to warm start before eliciting the auxiliary  ...  the process of converting a cold start recommendation process to a warm start.  ... 
doi:10.3390/app11209608 fatcat:foxbu3gt4fdxhdxuhijtufkyiu

CMML: Contextual Modulation Meta Learning for Cold-Start Recommendation [article]

Xidong Feng, Chen Chen, Dong Li, Mengchen Zhao, Jianye Hao, Jun Wang
2021 arXiv   pre-print
Practical recommender systems experience a cold-start problem when observed user-item interactions in the history are insufficient.  ...  task-level context, and a contextual modulation network, which can modulate the recommendation model to adapt effectively.  ...  MELU [19] introduces the MAML framework into user-specific cold-start recommendation problems, in which it transforms the cold start recommendation problem for new coming users/items as new coming tasks  ... 
arXiv:2108.10511v4 fatcat:qgsmmstb6nalze7xdcrevaz5qq

Knowledge-Enhanced Graph Neural Networks for Sequential Recommendation

Baocheng Wang, Wentao Cai
2020 Information  
Traditional recommendation methods use only recurrent neural networks (RNNs) to process sequential data.  ...  for the corresponding attribute.  ...  Acknowledgments: The authors thank the editor and the anonymous reviewers for their valuable suggestions that have significantly improved this study.  ... 
doi:10.3390/info11080388 fatcat:iueconen5vadrazj64rqcs7w6y

Cold-start Sequential Recommendation via Meta Learner [article]

Yujia Zheng, Siyi Liu, Zekun Li, Shu Wu
2020 arXiv   pre-print
As there is generally no side information in the setting of sequential recommendation task, previous cold-start methods could not be applied when only user-item interactions are available.  ...  Mecos effectively extracts user preference from limited interactions and learns to match the target cold-start item with the potential user.  ...  (Li et al. 2019 ) formulate cold-start recommendation as a zero-shot learning task with user profiles.  ... 
arXiv:2012.05462v1 fatcat:s6m436yldna2zjgg6fpjikjngm

dTrust: A Simple Deep Learning Approach for Social Recommendation

Quang-Vinh Dang, Claudia-Lavinia Ignat
2017 2017 IEEE 3rd International Conference on Collaboration and Internet Computing (CIC)  
Experiments on real-world data sets showed that dTrust outperforms state-of-the-art in terms of Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) scores for both warmstart and cold-start problems  ...  Abstract-Rating prediction is a key task of e-commerce recommendation mechanisms.  ...  One of the major issues of recommender systems is the cold-start problem, i.e. dealing with new users or items.  ... 
doi:10.1109/cic.2017.00036 dblp:conf/coinco/DangI17 fatcat:rkw7lyewv5fuhneryrvgibwoyi

Solving Cold Start Problem in Recommendation with Attribute Graph Neural Networks [article]

Tieyun Qian, Yile Liang, Qing Li
2020 arXiv   pre-print
This leads to the capability of learning embeddings for cold start users/items.  ...  More importantly, for a cold start user/item that does not have any interactions, such methods are unable to learn the preference embedding of the user/item since there is no link to this user/item in  ...  Introduction Matrix completion is a well-known recommendation task aiming at predicting a user's ratings for those items which are not rated yet by the user.  ... 
arXiv:1912.12398v2 fatcat:kmsepe7jtrb7jhjsywz7lvgseu

Collaborative Filtering and Artificial Neural Network Based Recommendation System for Advanced Applications

Bharadwaja Krishnadev Mylavarapu
2018 Journal of Computer and Communications  
To make recommendation on items from the user for historical user rating several intelligent systems are using. The most common method is Recommendation systems.  ...  By using sequential active of users and product characteristics we have the capability to adapt the cold start product ratings with the applications of the state of the art CF model, time SVD++.  ...  system for cold start items.  ... 
doi:10.4236/jcc.2018.612001 fatcat:bvcdfob5vjg2zgoavhrospblhe

Simple and Efficient Computational Intelligence Strategies for Effective Collaborative Decisions

Emelia Opoku Aboagye, Rajesh Kumar
2019 Future Internet  
problem through explicit multi-task approach for optimal recommendation decision making.  ...  We approach scalability and cold start problems of collaborative recommendation in this paper.  ...  cold start problem of users and items [6, 7] .  ... 
doi:10.3390/fi11010024 fatcat:frdj5shurzdsvofeqnjqppohee

Self-supervised Graph Learning for Occasional Group Recommendation [article]

Bowen Hao, Hongzhi Yin, Jing Zhang, Cuiping Li, Hong Chen
2022 arXiv   pre-print
Despite the recent advances on Graph Neural Networks (GNNs) incorporate high-order collaborative signals to alleviate the problem, the high-order cold-start neighbors are not explicitly considered during  ...  We study the problem of recommending items to occasional groups (a.k.a. cold-start groups), where the occasional groups are formed ad-hoc and have few or no historical interacted items.  ...  cold-start groups/users/items.  ... 
arXiv:2112.02274v2 fatcat:c2ejeqzjtfa2hjetvqhuvnyudq

A Dynamic Meta-Learning Model for Time-Sensitive Cold-Start Recommendations [article]

Krishna Prasad Neupane, Ervine Zheng, Yu Kong, Qi Yu
2022 arXiv   pre-print
Making effective recommendations to these time-sensitive cold-start users is critical to maintain the user base of a recommender system.  ...  Experiments over real-world data help demonstrate the effectiveness of the proposed time-sensitive cold-start recommendation model.  ...  Trained meta parameter θ t , RNN parameter ω, recommendation time period t 1: Identify cold-start user set for t 2: for each user u in the set do Algorithm 2: Recommendation for time-specific cold-start  ... 
arXiv:2204.00970v1 fatcat:tykjxev2ojhdjj2lkvt7krm62q
« Previous Showing results 1 — 15 out of 6,959 results