James Le

Abstract

Artificial neural networks (ANNs) have recently received increasing attention as powerful modeling tools to improve the performance of recommendation systems. Meta-learning, on the other hand, is a paradigm that has re-surged in popularity within the broader machine learning community over the past several years. In this thesis, we will explore the intersection of these two domains and work on developing methods for integrating meta-learning to design more accurate and flexible recommendation systems.

In the present work, we propose a meta-learning framework for the design of collaborative filtering methods in recommendation systems, drawing from ideas, models, and solutions from modern approaches in both the meta-learning and recommendation system literature, applying them to recommendation tasks to obtain improved generalization performance.

Our proposed framework, MetaRec, includes and unifies the main state-of-the-art models in recommendation systems, extending them to be flexibly configured and efficiently operate with limited data. We empirically test the architectures created under our MetaRec framework on several recommendation benchmark datasets using a plethora of evaluation metrics and find that by taking a meta-learning approach to the collaborative filtering problem, we observe notable gains in predictive performance.

Library of Congress Subject Headings

Recommender systems (Information filtering); Machine learning; Neural networks (Computer science)

Publication Date

12-8-2020

Document Type

Thesis

Student Type

Graduate

Degree Name

Computer Science (MS)

Department, Program, or Center

Computer Science (GCCIS)

Advisor

Alexander Ororbia II

Advisor/Committee Member

Richard Zanibbi

Advisor/Committee Member

Christopher Homan

Campus

RIT – Main Campus

Plan Codes

COMPSCI-MS

Download

Share

COinS