Personalization in federated recommendation system using SVD++ with explainability

This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2022.

Bibliografiska uppgifter
Huvudupphovsmän:	Patwary, Kabbya Kantam, Jawad, Abid Mohammad, Abir, Md Tahmid Chowdhury, Khushbu, Yuma Tabassum
Övriga upphovsmän:	Alam, Md. Golam Rabiul
Materialtyp:	Lärdomsprov
Språk:	English
Publicerad:	Brac University 2022
Ämnen:	Federated learning SVD++ Responsible AI Explainable AI Artificial intelligence
Länkar:	http://hdl.handle.net/10361/17047

id	10361-17047
record_format	dspace
spelling	10361-170472022-07-31T21:01:38Z Personalization in federated recommendation system using SVD++ with explainability Patwary, Kabbya Kantam Jawad, Abid Mohammad Abir, Md Tahmid Chowdhury Khushbu, Yuma Tabassum Alam, Md. Golam Rabiul Department of Computer Science and Engineering, Brac University Federated learning SVD++ Responsible AI Explainable AI Artificial intelligence This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2022. Cataloged from PDF version of thesis. Includes bibliographical references (pages 25-26). Large-scale distributed Artificial Intelligence (AI) systems are getting more widespread as traditional AI applications require centralizing large amounts of data for training models, posing privacy and security risks. For this reason, the idea of Federated Learning (FL) has emerged where instead of sharing data, the edge devices send model parameters over the network to the global model. Though FL ensures privacy preservation, this system lacks personalization due to the heterogeneous data across the client devices. At the same time, the debate continues over the explainability of the FL model like other AI systems. This paper has implemented SVD++ for movie recommendations using the Movielens 10M dataset to increase personalization in the FL system. Later we have also inaugurated explainability to remove the black-box nature of the recommendation system. To our knowledge, implementing SDV++ for personalization in a federated learning setup has not been introduced before. Our trained model has achieved RMSE value of 0.8906. Finally, ensuring the principles of Responsible AI will make the FL recommendation system more fair and reliable. Kabbya Kantam Patwary Abid Mohammad Jawad Md Tahmid Chowdhury Abir Yuma Tabassum Khushbu B. Computer Science 2022-07-31T06:43:52Z 2022-07-31T06:43:52Z 2022 2022-01 Thesis ID 17301043 ID 17301062 ID 17201029 ID 17301012 http://hdl.handle.net/10361/17047 en Brac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 26 pages application/pdf Brac University
institution	Brac University
collection	Institutional Repository
language	English
topic	Federated learning SVD++ Responsible AI Explainable AI Artificial intelligence
spellingShingle	Federated learning SVD++ Responsible AI Explainable AI Artificial intelligence Patwary, Kabbya Kantam Jawad, Abid Mohammad Abir, Md Tahmid Chowdhury Khushbu, Yuma Tabassum Personalization in federated recommendation system using SVD++ with explainability
description	This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2022.
author2	Alam, Md. Golam Rabiul
author_facet	Alam, Md. Golam Rabiul Patwary, Kabbya Kantam Jawad, Abid Mohammad Abir, Md Tahmid Chowdhury Khushbu, Yuma Tabassum
format	Thesis
author	Patwary, Kabbya Kantam Jawad, Abid Mohammad Abir, Md Tahmid Chowdhury Khushbu, Yuma Tabassum
author_sort	Patwary, Kabbya Kantam
title	Personalization in federated recommendation system using SVD++ with explainability
title_short	Personalization in federated recommendation system using SVD++ with explainability
title_full	Personalization in federated recommendation system using SVD++ with explainability
title_fullStr	Personalization in federated recommendation system using SVD++ with explainability
title_full_unstemmed	Personalization in federated recommendation system using SVD++ with explainability
title_sort	personalization in federated recommendation system using svd++ with explainability
publisher	Brac University
publishDate	2022
url	http://hdl.handle.net/10361/17047
work_keys_str_mv	AT patwarykabbyakantam personalizationinfederatedrecommendationsystemusingsvdwithexplainability AT jawadabidmohammad personalizationinfederatedrecommendationsystemusingsvdwithexplainability AT abirmdtahmidchowdhury personalizationinfederatedrecommendationsystemusingsvdwithexplainability AT khushbuyumatabassum personalizationinfederatedrecommendationsystemusingsvdwithexplainability
_version_	1814306836460863488

Personalization in federated recommendation system using SVD++ with explainability

Liknande verk