Show simple item record

A Deep Reinforcement Learning Approach for Influence Maximization in Dynamic Non-Progressive Social Networks

dc.rights.licenseCC-BY-NC-ND
dc.contributor.advisorWang, Shihan
dc.contributor.authorHui, Yunming
dc.date.accessioned2024-07-02T12:30:36Z
dc.date.available2024-07-02T12:30:36Z
dc.date.issued2024
dc.identifier.urihttps://studenttheses.uu.nl/handle/20.500.12932/46570
dc.description.sponsorshipUtrecht University
dc.language.isoEN
dc.subjectInfluence maximization is pivotal in network analysis, identifying crit-ical individuals for optimal information spread. This thesis introduces a novel dynamic non-progressive diffusion model, extending traditional ap-proaches to address real-world scenarios that evolve over time. To tackle the challenges of dynamic influence maximization, this thesis proposes an innovative framework that integrates dynamic graph embedding with re-inforcement learning. Experimental evaluations reveal the effecti
dc.titleA Deep Reinforcement Learning Approach for Influence Maximization in Dynamic Non-Progressive Social Networks
dc.type.contentMaster Thesis
dc.rights.accessrightsOpen Access
dc.subject.courseuuComputing Science
dc.thesis.id22572


Files in this item

Thumbnail
Name:
Master_Thesis.pdf
Size:
6.572Mb
Format:
PDF
View/Open

This item appears in the following Collection(s)

Show simple item record