Generalizing graph neural networks across graphs, time, and tasks

Graph-structured data are ubiquitous across numerous real-world contexts, encompassing social networks, commercial graphs, bibliographic networks, and biological systems. Delving into the analysis of these graphs can yield significant understanding pertaining to their corresponding application field...

Full description

Saved in:
Bibliographic Details
Main Author: WEN, Zhihao
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2023
Subjects:
GNN
Online Access:https://ink.library.smu.edu.sg/etd_coll/507
https://ink.library.smu.edu.sg/context/etd_coll/article/1505/viewcontent/GPIS_AY2019_PhD_WEN_Zhihao.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.etd_coll-1505
record_format dspace
spelling sg-smu-ink.etd_coll-15052023-10-03T06:33:15Z Generalizing graph neural networks across graphs, time, and tasks WEN, Zhihao Graph-structured data are ubiquitous across numerous real-world contexts, encompassing social networks, commercial graphs, bibliographic networks, and biological systems. Delving into the analysis of these graphs can yield significant understanding pertaining to their corresponding application fields.Graph representation learning offers a potent solution to graph analytics challenges by transforming a graph into a low-dimensional space while preserving its information to the greatest extent possible. This conversion into low-dimensional vectors enables the efficient computation of subsequent graph algorithms. The majority of prior research has concentrated on deriving node representations from a single, static graph. However, numerous real-world situations demand rapid generation of representations for previously unencountered nodes, novel edges, or entirely new graphs. This inductive capability is vital for highperformance machine learning systems that operate on ever-changing graphs and consistently encounter unfamiliar nodes. The inductive graph representation presents considerable difficulty when compared to the transductive setting, as it necessitates the alignment of new subgraphs containing previously unseen nodes with an already trained neural network. We further investigate inductive graph representation learning through three distinct angles: (1) Generalizing Graph Neural Networks (GNNs) across graphs, addressing semi-supervised node classification across multiple graphs; (2) Generalizing GNNs across time, focusing on temporal link prediction; and (3) Generalizing GNNs across tasks, tackling various low-resource text classification tasks. 2023-06-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/etd_coll/507 https://ink.library.smu.edu.sg/context/etd_coll/article/1505/viewcontent/GPIS_AY2019_PhD_WEN_Zhihao.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Dissertations and Theses Collection (Open Access) eng Institutional Knowledge at Singapore Management University GNN node classification link prediction inductive generalization meta-learning Hawkes-process contrastive pre-training Graphics and Human Computer Interfaces OS and Networks
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic GNN
node classification
link prediction
inductive
generalization
meta-learning
Hawkes-process
contrastive pre-training
Graphics and Human Computer Interfaces
OS and Networks
spellingShingle GNN
node classification
link prediction
inductive
generalization
meta-learning
Hawkes-process
contrastive pre-training
Graphics and Human Computer Interfaces
OS and Networks
WEN, Zhihao
Generalizing graph neural networks across graphs, time, and tasks
description Graph-structured data are ubiquitous across numerous real-world contexts, encompassing social networks, commercial graphs, bibliographic networks, and biological systems. Delving into the analysis of these graphs can yield significant understanding pertaining to their corresponding application fields.Graph representation learning offers a potent solution to graph analytics challenges by transforming a graph into a low-dimensional space while preserving its information to the greatest extent possible. This conversion into low-dimensional vectors enables the efficient computation of subsequent graph algorithms. The majority of prior research has concentrated on deriving node representations from a single, static graph. However, numerous real-world situations demand rapid generation of representations for previously unencountered nodes, novel edges, or entirely new graphs. This inductive capability is vital for highperformance machine learning systems that operate on ever-changing graphs and consistently encounter unfamiliar nodes. The inductive graph representation presents considerable difficulty when compared to the transductive setting, as it necessitates the alignment of new subgraphs containing previously unseen nodes with an already trained neural network. We further investigate inductive graph representation learning through three distinct angles: (1) Generalizing Graph Neural Networks (GNNs) across graphs, addressing semi-supervised node classification across multiple graphs; (2) Generalizing GNNs across time, focusing on temporal link prediction; and (3) Generalizing GNNs across tasks, tackling various low-resource text classification tasks.
format text
author WEN, Zhihao
author_facet WEN, Zhihao
author_sort WEN, Zhihao
title Generalizing graph neural networks across graphs, time, and tasks
title_short Generalizing graph neural networks across graphs, time, and tasks
title_full Generalizing graph neural networks across graphs, time, and tasks
title_fullStr Generalizing graph neural networks across graphs, time, and tasks
title_full_unstemmed Generalizing graph neural networks across graphs, time, and tasks
title_sort generalizing graph neural networks across graphs, time, and tasks
publisher Institutional Knowledge at Singapore Management University
publishDate 2023
url https://ink.library.smu.edu.sg/etd_coll/507
https://ink.library.smu.edu.sg/context/etd_coll/article/1505/viewcontent/GPIS_AY2019_PhD_WEN_Zhihao.pdf
_version_ 1779157209542819840