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

Towards Expressive and Scalable Deep Representation Learning for Graphs.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Towards Expressive and Scalable Deep Representation Learning for Graphs./
作者:	Ying, Rex Zhitao.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	176 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-09, Section: B.
Contained By:	Dissertations Abstracts International83-09B.
標題:	Collaboration. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28971829
ISBN:	9798780652397

Towards Expressive and Scalable Deep Representation Learning for Graphs.
Ying, Rex Zhitao.

Towards Expressive and Scalable Deep Representation Learning for Graphs. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 176 p.

Source: Dissertations Abstracts International, Volume: 83-09, Section: B.

Thesis (Ph.D.)--Stanford University, 2021.

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

The ubiquity of graph structures in sciences and industry necessitates effective and scalable machine learning models capable of capturing the underlying inductive biases of the relational data. However, traditional representation learning algorithms on graph structure faces many limitations. Firstly, traditional methods including matrix factorization and distributed embeddings cannot scale to large real-world graphs with billions of nodes and edges due to their sizes of parameter space. Secondly, they lack expressiveness compared to recent advances of deep learning architectures. Lastly, they fail in inductive scenarios where they required to make prediction on nodes unseen during training. Finally, interpretation of what model learns from data is elusive to domain experts.In this thesis I present a series of work that pioneers the use of graph neural networks (GNNs) to tackle the challenges of representation learning on graphs in the aspects of explainability, scalability, and expressiveness. In the first part, I demonstrate my framework of GraphSAGE as a general but powerful overarching graph neural network framework. To tackle the challenge of model interpretability with the new GraphSAGE framework, I further introduce an extension model to obtain meaningful explanations from the trained graph neural network model. Under the framework of GraphSAGE, the second part presents a series of works that improves the expressive power of GNNs through the use of hierarchical structure, geometric embedding space, as well as multi-hop attention. These GNN-based architectures achieved unprecedented performance improvement over traditional methods on tasks in a variety of contexts, such as graph classification for molecules, hierarchical knowledge graphs and large-scale citation networks.In the third part, I further demonstrate a variety of applications of GNNs. Based on GraphSAGE, I developed PinSAGE, the first deployed GNN model that scales to billion-sized graphs. PinSAGE is deployed at Pinterest, to make recommendations for billions of users at Pinterest. In the area of grahics and simulations, we apply expressive architectures to accurately predict the physics of different materials and allow generalization to unseen dynamic systems. Finally, I discuss BiDyn, a dynamic GNN model for abuse detection before concluding the thesis.

ISBN: 9798780652397Subjects--Topical Terms:

3556296
Collaboration.

Towards Expressive and Scalable Deep Representation Learning for Graphs.
LDR:03407nmm a2200313 4500 001 2349908
005 20221010063654.5
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798780652397
035 $a (MiAaPQ)AAI28971829
035 $a (MiAaPQ)STANFORDqh673zw4863
035 $a AAI28971829
040 $a MiAaPQ $c MiAaPQ
100 1 $a Ying, Rex Zhitao. $3 3689334
245 1 0 $a Towards Expressive and Scalable Deep Representation Learning for Graphs.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 176 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-09, Section: B.
500 $a Advisor: Leskovec, Jure;Re, Christopher;Yamins, Daniel.
502 $a Thesis (Ph.D.)--Stanford University, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a The ubiquity of graph structures in sciences and industry necessitates effective and scalable machine learning models capable of capturing the underlying inductive biases of the relational data. However, traditional representation learning algorithms on graph structure faces many limitations. Firstly, traditional methods including matrix factorization and distributed embeddings cannot scale to large real-world graphs with billions of nodes and edges due to their sizes of parameter space. Secondly, they lack expressiveness compared to recent advances of deep learning architectures. Lastly, they fail in inductive scenarios where they required to make prediction on nodes unseen during training. Finally, interpretation of what model learns from data is elusive to domain experts.In this thesis I present a series of work that pioneers the use of graph neural networks (GNNs) to tackle the challenges of representation learning on graphs in the aspects of explainability, scalability, and expressiveness. In the first part, I demonstrate my framework of GraphSAGE as a general but powerful overarching graph neural network framework. To tackle the challenge of model interpretability with the new GraphSAGE framework, I further introduce an extension model to obtain meaningful explanations from the trained graph neural network model. Under the framework of GraphSAGE, the second part presents a series of works that improves the expressive power of GNNs through the use of hierarchical structure, geometric embedding space, as well as multi-hop attention. These GNN-based architectures achieved unprecedented performance improvement over traditional methods on tasks in a variety of contexts, such as graph classification for molecules, hierarchical knowledge graphs and large-scale citation networks.In the third part, I further demonstrate a variety of applications of GNNs. Based on GraphSAGE, I developed PinSAGE, the first deployed GNN model that scales to billion-sized graphs. PinSAGE is deployed at Pinterest, to make recommendations for billions of users at Pinterest. In the area of grahics and simulations, we apply expressive architectures to accurately predict the physics of different materials and allow generalization to unseen dynamic systems. Finally, I discuss BiDyn, a dynamic GNN model for abuse detection before concluding the thesis.
590 $a School code: 0212.
650 4 $a Collaboration. $3 3556296
650 4 $a Performance evaluation. $3 3562292
650 4 $a Graph representations. $3 3560730
650 4 $a Neural networks. $3 677449
650 4 $a Artificial intelligence. $3 516317
690 $a 0800
690 $a 0505
710 2 $a Stanford University. $3 754827
773 0 $t Dissertations Abstracts International $g 83-09B.
790 $a 0212
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28971829