國立虎尾科技大學 |

Study of Deep Neural Networks on Graph Data in a Generative Learning Regime.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Study of Deep Neural Networks on Graph Data in a Generative Learning Regime./
Author:	Jiang, Chao.
Description:	1 online resource (90 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 84-05, Section: B.
Contained By:	Dissertations Abstracts International84-05B.
Subject:	Neurons. -
Online resource:	click for full text (PQDT)
ISBN:	9798352976197

Study of Deep Neural Networks on Graph Data in a Generative Learning Regime.
Jiang, Chao.

Study of Deep Neural Networks on Graph Data in a Generative Learning Regime. - 1 online resource (90 pages)

Source: Dissertations Abstracts International, Volume: 84-05, Section: B.

Thesis (Ph.D.)--Auburn University, 2022.

Includes bibliographical references

Graph-formatted data is ubiquitous among different domains from social networks and academic citation networks to drug-target interactions and others. Graph neural networks (GNNs) have achieved outstanding performance in applying node classification, link pre- diction, and node clustering, etc. However, there are two common questions asked by researchers.First, how to get a considerable amount of labeled high quality data? Data quality is crucial in training deep neural network models. However, most of the current works in this area have focused on improving a model's performance with the assumption that the preprocessed data are clean. Our first result is about improving data quality by removing noise information. Here we build a real knowledge graph from data sets LitCovid and Pubtator. The multiple types of biomedical associations of the real knowledge graphs, including the COVID-19-related ones, are based upon the co-occurring biomedical entities retrieved from recent literature. However, the applications derived from these raw graphs (e.g., association predictions amongst genes, drugs, and diseases) have a high probability of false-positive predictions as the co-occurrences in literature do not always mean a true biomedical association between two entities. We proposed a framework that utilized generative-based deep neural networks to generate a graph that can distinguish the unknown associations in the raw training graph. Two Generative Adversarial Network models, NetGAN and CELL, were adopted for the edge classification (i.e., link prediction), leveraging unlabeled link information based on the real knowledge graph. The performance of link prediction, especially in the extreme case of training data versus test data at a ratio of 1:9, demonstrated that the promised method still achieved favorable results (AUCROC > 0.8 for synthetic and 0.7 for real dataset) despite the limited amount of testing data available.Second, what is the decision-making process of GNNs as it often remains a black box? In addition, many of the models are vulnerable to adversarial attacks. Our second result focuses on the study of the robustness of GNNs. Recent studies revealed that the GNNs are vulnerable to adversarial attacks, where feeding GNNs with poisoned data at training time can lead them to yield devastative test accuracy. However, the prior studies mainly posit that the adversaries can access freely and manipulate the original graph while obtaining such access could be too costly in practice. To fill this gap, we propose a novel attacking paradigm, named Generative Adversarial Fake Node Camouflaging(GAFNC), with its crux laying in crafting a set of fake nodes in a generative-adversarial regime. These nodes carry camouflaged malicious features and can poison the victim GNN by passing their harmful messages to the original graph via learned topological structures. These messages can maximize the devastation of classification accuracy (i.e., global attack) or enforce the victim GNN to misclassify a targeted node set into prescribed classes (i.e., target attack).

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798352976197Subjects--Topical Terms:

581309
Neurons.
Index Terms--Genre/Form:

554714
Electronic books.

Study of Deep Neural Networks on Graph Data in a Generative Learning Regime.
LDR:04328ntm a22003377 4500 001 1141690
005 20240414211446.5
006 m o d
007 cr mn ---uuuuu
008 250605s2022 xx obm 000 0 eng d
020 $a 9798352976197
035 $a (MiAaPQ)AAI29756110
035 $a (MiAaPQ)Auburn104158415
035 $a AAI29756110
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Jiang, Chao. $3 1182349
245 1 0 $a Study of Deep Neural Networks on Graph Data in a Generative Learning Regime.
264 0 $c 2022
300 $a 1 online resource (90 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 84-05, Section: B.
500 $a Advisor: Chapman, Richard.
502 $a Thesis (Ph.D.)--Auburn University, 2022.
504 $a Includes bibliographical references
520 $a Graph-formatted data is ubiquitous among different domains from social networks and academic citation networks to drug-target interactions and others. Graph neural networks (GNNs) have achieved outstanding performance in applying node classification, link pre- diction, and node clustering, etc. However, there are two common questions asked by researchers.First, how to get a considerable amount of labeled high quality data? Data quality is crucial in training deep neural network models. However, most of the current works in this area have focused on improving a model's performance with the assumption that the preprocessed data are clean. Our first result is about improving data quality by removing noise information. Here we build a real knowledge graph from data sets LitCovid and Pubtator. The multiple types of biomedical associations of the real knowledge graphs, including the COVID-19-related ones, are based upon the co-occurring biomedical entities retrieved from recent literature. However, the applications derived from these raw graphs (e.g., association predictions amongst genes, drugs, and diseases) have a high probability of false-positive predictions as the co-occurrences in literature do not always mean a true biomedical association between two entities. We proposed a framework that utilized generative-based deep neural networks to generate a graph that can distinguish the unknown associations in the raw training graph. Two Generative Adversarial Network models, NetGAN and CELL, were adopted for the edge classification (i.e., link prediction), leveraging unlabeled link information based on the real knowledge graph. The performance of link prediction, especially in the extreme case of training data versus test data at a ratio of 1:9, demonstrated that the promised method still achieved favorable results (AUCROC > 0.8 for synthetic and 0.7 for real dataset) despite the limited amount of testing data available.Second, what is the decision-making process of GNNs as it often remains a black box? In addition, many of the models are vulnerable to adversarial attacks. Our second result focuses on the study of the robustness of GNNs. Recent studies revealed that the GNNs are vulnerable to adversarial attacks, where feeding GNNs with poisoned data at training time can lead them to yield devastative test accuracy. However, the prior studies mainly posit that the adversaries can access freely and manipulate the original graph while obtaining such access could be too costly in practice. To fill this gap, we propose a novel attacking paradigm, named Generative Adversarial Fake Node Camouflaging(GAFNC), with its crux laying in crafting a set of fake nodes in a generative-adversarial regime. These nodes carry camouflaged malicious features and can poison the victim GNN by passing their harmful messages to the original graph via learned topological structures. These messages can maximize the devastation of classification accuracy (i.e., global attack) or enforce the victim GNN to misclassify a targeted node set into prescribed classes (i.e., target attack).
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Neurons. $3 581309
650 4 $a Motivation. $3 655186
650 4 $a Deep learning. $3 1127428
650 4 $a Poisoning. $3 903016
650 4 $a Graph representations. $3 1465474
650 4 $a Optimization. $3 669174
650 4 $a Decision making. $3 528319
650 4 $a Neural networks. $3 1011215
650 4 $a Design. $3 595500
650 4 $a Coronaviruses. $3 668915
650 4 $a COVID-19. $3 1335291
655 7 $a Electronic books. $2 local $3 554714
690 $a 0389
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Auburn University. $3 1189563
773 0 $t Dissertations Abstracts International $g 84-05B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29756110 $z click for full text (PQDT)