Filters








104,161 Hits in 4.5 sec

A Federated Recommender System for Online Learning Environments [chapter]

Lei Zhou, Sandy El Helou, Laurent Moccozet, Laurent Opprecht, Omar Benkacem, Christophe Salzmann, Denis Gillet
2012 Lecture Notes in Computer Science  
The paper describes the main aspects of the federated recommender system, including its adopted architecture, the common data model used to harvest the different learning platforms, the recommendation  ...  This paper presents a federated recommender system, which exploits data from different online learning platforms and delivers personalized recommendation.  ...  Proposed Federated Recommender System Common Data Model The federated recommender system exploits interaction data stored in different online learning platforms.  ... 
doi:10.1007/978-3-642-33642-3_10 fatcat:x2tfn4galjhdfidv6bxmgw4buu

A Novel Privacy-Preserved Recommender System Framework based on Federated Learning [article]

Jiangcheng Qin, Baisong Liu
2020 arXiv   pre-print
This paper proposed a novel privacy-preserved recommender system framework (PPRSF), through the application of federated learning paradigm, to enable the recommendation algorithm to be trained and carry  ...  Recommender System (RS) is currently an effective way to solve information overload.  ...  Figure 2 : 2 Privacy-preserved Recommender System based on Federated Learning Framework (PPRSF) with 4-layers Hierarchical Structure Figure 3 : 3 Centralized Cross-device Federated Learning Architecture  ... 
arXiv:2011.05614v1 fatcat:rpb227km3bb3dhr3hwjj6rgv5q

Federating Recommendations Using Differentially Private Prototypes [article]

Mónica Ribero, Jette Henderson, Sinead Williamson, Haris Vikalo
2020 arXiv   pre-print
We propose a new federated approach to learning global and local private models for recommendation without collecting raw data, user statistics, or information about personal preferences.  ...  Machine learning methods allow us to make recommendations to users in applications across fields including entertainment, dating, and commerce, by exploiting similarities in users' interaction patterns  ...  Conclusion We propose a novel, efficient framework to learn recommender systems in federated settings.  ... 
arXiv:2003.00602v1 fatcat:uow5bl2plvchfacvanqvzdq3g4

Multi-agent system for Knowledge-based recommendation of Learning Objects

Paula Andrea RODRÍGUEZ MARÍN, Néstor DUQUE, Demetrio OVALLE
2015 Advances in Distributed Computing and Artificial Intelligence Journal  
located LO ranked in the past with a score equal or greater than 4, scale of 1 to 5, where 5 indicates that LO like the student.  ...  Clustering techniques, learning objects, metadata, multiagent systems, and recommendation systems Learning Object (LO) is a content unit being used within virtual learning environments, which -once found  ...  It was also developed with the support of the grant from "Programa Nacional de Formación de Investigadores -COLCIENCIAS".  ... 
doi:10.14201/adcaij2015418089 fatcat:tn3y4czx6bh2rdlpg6ynhmorr4

FedeRank: User Controlled Feedback with Federated Recommender Systems [article]

Vito Walter Anelli, Yashar Deldjoo, Tommaso Di Noia, Antonio Ferrara, Fedelucio Narducci
2021 arXiv   pre-print
We present FedeRank (https://split.to/federank), a federated recommendation algorithm. The system learns a personal factorization model onto every device.  ...  Recommender systems have shown to be a successful representative of how data availability can ease our everyday digital life.  ...  All these clues suggest that the system learns how to rank items even without the need for the totality of ratings.  ... 
arXiv:2012.11328v3 fatcat:yqdftciknzdg5ksicth3yrj7y4

PipAttack: Poisoning Federated Recommender Systems forManipulating Item Promotion [article]

Shijie Zhang and Hongzhi Yin and Tong Chen and Zi Huang and Quoc Viet Hung Nguyen and Lizhen Cui
2021 arXiv   pre-print
Hence, a common practice is to subsume recommender systems under the decentralized federated learning paradigm, which enables all user devices to collaboratively learn a global recommender while retaining  ...  In this paper, we present a systematic approach to backdooring federated recommender systems for targeted item promotion.  ...  Base Recommender Federated learning is compatible with the majority of latent factor models.  ... 
arXiv:2110.10926v1 fatcat:gobgsvmhurd4hf4jb22mtacjzy

FEL: High Capacity Learning for Recommendation and Ranking via Federated Ensemble Learning [article]

Meisam Hejazinia, Dzmitry Huba, Ilias Leontiadis, Kiwan Maeng, Mani Malek, Luca Melis, Ilya Mironov, Milad Nasr, Kaikai Wang, Carole-Jean Wu
2022 arXiv   pre-print
We propose Federated Ensemble Learning (FEL) as a solution to tackle the large memory requirement of deep learning ranking and recommendation tasks.  ...  Our experiments demonstrate that FEL leads to 0.43-2.31% model quality improvement over traditional on-device federated learning - a significant improvement for ranking and recommendation system use cases  ...  Acknowledgement We would like to thank Milan Shen, Will Bullock, Hung Duong, and Kim Hazelwood for supporting the work.  ... 
arXiv:2206.03852v1 fatcat:dhcfj3jfrrh53doz3rryhgfwyi

FedAttack: Effective and Covert Poisoning Attack on Federated Recommendation via Hard Sampling

Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang, Xing Xie
2022 Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining  
Federated learning (FL) is a feasible technique to learn personalized recommendation models from decentralized user data.  ...  Unfortunately, federated recommender systems are vulnerable to poisoning attacks by malicious clients.  ...  Thus, federated learning-based systems are more vulnerable to poisoning attack than centralized learning [1] .  ... 
doi:10.1145/3534678.3539119 fatcat:qkz4j2rjqzg25nbnyiz3e3ujai

How to Put Users in Control of their Data in Federated Top-N Recommendation with Learning to Rank [article]

Vito Walter Anelli, Yashar Deldjoo, Tommaso Di Noia, Antonio Ferrara, Fedelucio Narducci
2020 arXiv   pre-print
The proposed approach implements pair-wise learning-to-rank optimization by following the Federated Learning principles, conceived originally to mitigate the privacy risks of traditional machine learning  ...  To address this issue, we present Federated Pair-wise Learning (FPL), an architecture in which users collaborate in training a central factorization model while controlling the amount of sensitive data  ...  BACKGROUND TECHNOLOGIES This section is devoted to introducing the fundamentals of the federated learning paradigm, the pair-wise learning to rank approach, and the factorization models.  ... 
arXiv:2008.07192v2 fatcat:cdc2idz225hqxb2jzga6hod7wm

Integral Multi-agent Model Recommendation of Learning Objects, for Students and Teachers [chapter]

Paula Rodríguez, Néstor Duque, Sara Rodríguez
2013 Advances in Intelligent Systems and Computing  
The objective is to have an integral multi-agent model that meets the needs of students and teachers, and in this way improve the teaching learning process.  ...  This paper proposes the integration of two multi-agent models focused on delivering, specific LO adapted to a student's profile; and delivering LO to teachers in order to assist them in creating courses  ...  Casali 2011, presents a recommendation system based on intelligent agents, which aims to return a ranked list of the most suitable LO according to a user profile.  ... 
doi:10.1007/978-3-319-00569-0_16 fatcat:jpnd5by745gjdfp5dgoimmuhva

FedFast: Going Beyond Average for Faster Training of Federated Recommender Systems

Khalil Muhammad, Qinqin Wang, Diarmuid O'Reilly-Morgan, Elias Tragos, Barry Smyth, Neil Hurley, James Geraci, Aonghus Lawlor
2020 Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining  
amenable to work with federated learning.  ...  SYSTEM OVERVIEW Our system, as illustrated in Figure 1 , conforms to a client-server architecture that is familiar to federated learning systems.  ... 
doi:10.1145/3394486.3403176 fatcat:unkrj4nso5bvnk37mq5ewgh6fq

Towards Communication Efficient and Fair Federated Personalized Sequential Recommendation [article]

Sichun Luo, Yuanzhang Xiao, Yang Liu, Congduan Li, Linqi Song
2022 arXiv   pre-print
Federated recommendations leverage the federated learning (FL) techniques to make privacy-preserving recommendations.  ...  Though recent success in the federated recommender system, several vital challenges remain to be addressed: (i) The majority of federated recommendation models only consider the model performance and the  ...  Shenzhen Municipality under Grants JSGG20201102162000001, InnoHK initiative, the Government of the HKSAR, Laboratory for AI-Powered Financial Technologies, the Hong Kong UGC Special Virtual Teaching and Learning  ... 
arXiv:2208.10692v2 fatcat:kr7giri7qbghnbm64ji5qyl3fm

Practical and Secure Federated Recommendation with Personalized Masks [article]

Liu Yang, Junxue Zhang, Di Chai, Leye Wang, Kun Guo, Kai Chen, Qiang Yang
2022 arXiv   pre-print
Current federated recommender systems mainly utilize cryptographic or obfuscation methods to protect the original ratings from leakage.  ...  In this paper, we proposed federated masked matrix factorization (FedMMF) to protect the data privacy in federated recommender systems without sacrificing efficiency and effectiveness.  ...  Federated Matrix Factorization With the development of federated learning, federated recommender system (FedRec) was proposed to address the privacy and data silo problems in the recommendation scenarios  ... 
arXiv:2109.02464v2 fatcat:ckwkk5mpfbbkxicioaztbslq6q

Towards Ranking in Folksonomies for Personalized Recommender Systems in E-Learning

Mojisola Anjorin, Christoph Rensing, Ralf Steinmetz
2011 International Semantic Web Conference  
Recommender systems offer the opportunity for users to no longer have to search for resources but rather have these resources offered to them considering their personal needs and contexts.  ...  This paper proposes a conceptual architecture describing how these semantics can be integrated in a personalized recommender system for learning purposes.  ...  The responsibility for the contents of this publication lies with the authors.  ... 
dblp:conf/semweb/AnjorinRS11 fatcat:nt4mdbyrgraglevcjxxgjxunvq

FedPOIRec: Privacy Preserving Federated POI Recommendation with Social Influence [article]

Vasileios Perifanis, George Drosatos, Giorgos Stamatelatos, Pavlos S. Efraimidis
2021 arXiv   pre-print
In this work, we present FedPOIRec, a privacy preserving federated learning approach enhanced with features from users' social circles for top-N POI recommendations.  ...  Second, the local recommenders get personalized by allowing users to exchange their learned parameters, enabling knowledge transfer among friends.  ...  Narducci, How to put users in control of their data in federated top-n recommendation with learning to rank, in: Proceedings of the 36th Annual ACM Symposium on Applied Computing, SAC ’21, Association  ... 
arXiv:2112.11134v1 fatcat:5v4scfks6bawlknkfru4nuxlcu
« Previous Showing results 1 — 15 out of 104,161 results