Please use this identifier to cite or link to this item:
https://scholarbank.nus.edu.sg/handle/10635/235016
Title: | TOWARDS LABEL-EFFICIENT DEEP LEARNING ON GRAPH-STRUCTURED DATA | Authors: | ZHOU KUANGQI | Keywords: | deep learning, graph learning, semi-supervised learning, active learning, deep graph neural networks, molecular property prediction | Issue Date: | 20-Jul-2022 | Citation: | ZHOU KUANGQI (2022-07-20). TOWARDS LABEL-EFFICIENT DEEP LEARNING ON GRAPH-STRUCTURED DATA. ScholarBank@NUS Repository. | Abstract: | Deep Learning (DL) has become a major tool in artificial intelligence. Modern DL models are mainly developed for regular-structured data like images. However, many real-world data do not have a regular structure, such as social networks. A good choice for representing these data is graph, a generic data structure that succinctly represents a set of objects and their relations. A key factor for DL to achieve high performance is abundant annotation. However, collecting sufficient annotation for graph-structured data can be quite difficult. In this thesis, we develop label-efficient DL methods that achieve superior performance with a few labels. First, we build very deep graph neural networks that can capture rich semantic information from unlabeled data. Second, we propose two novel active learning strategies for selecting the most valuable samples to label. | URI: | https://scholarbank.nus.edu.sg/handle/10635/235016 |
Appears in Collections: | Ph.D Theses (Open) |
Show full item record
Files in This Item:
File | Description | Size | Format | Access Settings | Version | |
---|---|---|---|---|---|---|
ZhouKQ.pdf | 4.62 MB | Adobe PDF | OPEN | None | View/Download |
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.