東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Advanced Operators for Graph Neural Networks.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Advanced Operators for Graph Neural Networks./
作者:	Ma, Yao.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	133 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-03, Section: B.
Contained By:	Dissertations Abstracts International83-03B.
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28647653
ISBN:	9798538131518

Advanced Operators for Graph Neural Networks.
Ma, Yao.

Advanced Operators for Graph Neural Networks. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 133 p.

Source: Dissertations Abstracts International, Volume: 83-03, Section: B.

Thesis (Ph.D.)--Michigan State University, 2021.

This item must not be sold to any third party vendors.

Graphs, which encode pairwise relations between entities, are a kind of universal data structure for many real-world data, including social networks, transportation networks, and chemical molecules. Many important applications on these data can be treated as computational tasks on graphs. For example, friend recommendation in social networks can be regarded as a link prediction task and predicting properties of chemical compounds can be treated as a graph classification task. An essential step to facilitate these tasks is to learn vector representations either for nodes or the entire graphs. Given its great success of representation learning in images and text, deep learning offers great promise for graphs. However, compared to images and text, deep learning on graphs faces immense challenges. Graphs are irregular where nodes are unordered and each of them can have a distinct number of neighbors. Thus, traditional deep learning models cannot be directly applied to graphs, which calls for dedicated efforts for designing novel deep graph models. To help meet this pressing demand, we developed and investigated novel GNN algorithms to generalize deep learning techniques to graph-structured data. Two key operations in GNNs are the graph filtering operation, which aims to refine node representations; and the graph pooling operation, which aims to summarize node representations to obtain a graph representation. In this thesis, we provide deep understandings or develop novel algorithms for these two operations from new perspectives. For graph filtering operations, we propose a unified framework from the perspective of graph signal denoising, which demonstrates that most existing graph filtering operations are conducting feature smoothing. Then, we further investigate what information typical graph filtering operations can capture and how they can be understood beyond feature smoothing. For graph pooling operations, we study the procedure of pooling from the perspective of graph spectral theory and present a novel graph pooling operation. We also propose a technique to downsample nodes considering both mode importance and representativeness, which leads to a novel graph pooling operation.

ISBN: 9798538131518Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Deep learnining

Advanced Operators for Graph Neural Networks.
LDR:03231nmm a2200325 4500 001 2348615
005 20220912135618.5
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798538131518
035 $a (MiAaPQ)AAI28647653
035 $a AAI28647653
040 $a MiAaPQ $c MiAaPQ
100 1 $a Ma, Yao. $3 3182113
245 1 0 $a Advanced Operators for Graph Neural Networks.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 133 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-03, Section: B.
500 $a Advisor: Tang, Jiliang.
502 $a Thesis (Ph.D.)--Michigan State University, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a Graphs, which encode pairwise relations between entities, are a kind of universal data structure for many real-world data, including social networks, transportation networks, and chemical molecules. Many important applications on these data can be treated as computational tasks on graphs. For example, friend recommendation in social networks can be regarded as a link prediction task and predicting properties of chemical compounds can be treated as a graph classification task. An essential step to facilitate these tasks is to learn vector representations either for nodes or the entire graphs. Given its great success of representation learning in images and text, deep learning offers great promise for graphs. However, compared to images and text, deep learning on graphs faces immense challenges. Graphs are irregular where nodes are unordered and each of them can have a distinct number of neighbors. Thus, traditional deep learning models cannot be directly applied to graphs, which calls for dedicated efforts for designing novel deep graph models. To help meet this pressing demand, we developed and investigated novel GNN algorithms to generalize deep learning techniques to graph-structured data. Two key operations in GNNs are the graph filtering operation, which aims to refine node representations; and the graph pooling operation, which aims to summarize node representations to obtain a graph representation. In this thesis, we provide deep understandings or develop novel algorithms for these two operations from new perspectives. For graph filtering operations, we propose a unified framework from the perspective of graph signal denoising, which demonstrates that most existing graph filtering operations are conducting feature smoothing. Then, we further investigate what information typical graph filtering operations can capture and how they can be understood beyond feature smoothing. For graph pooling operations, we study the procedure of pooling from the perspective of graph spectral theory and present a novel graph pooling operation. We also propose a technique to downsample nodes considering both mode importance and representativeness, which leads to a novel graph pooling operation.
590 $a School code: 0128.
650 4 $a Computer science. $3 523869
650 4 $a Accuracy. $3 3559958
650 4 $a Noise. $3 598816
650 4 $a Datasets. $3 3541416
650 4 $a Neighborhoods. $3 993475
650 4 $a Experiments. $3 525909
650 4 $a Neural networks. $3 677449
650 4 $a Classification. $3 595585
653 $a Deep learnining
653 $a Graphs
653 $a Neural networks
690 $a 0984
710 2 $a Michigan State University. $b Computer Science - Doctor of Philosophy. $3 2104328
773 0 $t Dissertations Abstracts International $g 83-03B.
790 $a 0128
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28647653