Muutke küpsiste eelistusi

E-raamat: Graph Neural Networks: Foundations, Frontiers, and Applications

Edited by , Edited by , Edited by , Edited by
  • Formaat: PDF+DRM
  • Ilmumisaeg: 03-Jan-2022
  • Kirjastus: Springer Verlag, Singapore
  • Keel: eng
  • ISBN-13: 9789811660542
Teised raamatud teemal:
  • Formaat - PDF+DRM
  • Hind: 86,44 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Lisa ostukorvi
  • Lisa soovinimekirja
  • See e-raamat on mõeldud ainult isiklikuks kasutamiseks. E-raamatuid ei saa tagastada.
Graph Neural Networks: Foundations, Frontiers, and ApplicationsSuurem pilt
  • Formaat: PDF+DRM
  • Ilmumisaeg: 03-Jan-2022
  • Kirjastus: Springer Verlag, Singapore
  • Keel: eng
  • ISBN-13: 9789811660542
Teised raamatud teemal:

DRM piirangud

  • Kopeerimine (copy/paste):

    ei ole lubatud

  • Printimine:

    ei ole lubatud

  • Kasutamine:

    Digitaalõiguste kaitse (DRM)
    Kirjastus on väljastanud selle e-raamatu krüpteeritud kujul, mis tähendab, et selle lugemiseks peate installeerima spetsiaalse tarkvara. Samuti peate looma endale  Adobe ID Rohkem infot siin. E-raamatut saab lugeda 1 kasutaja ning alla laadida kuni 6'de seadmesse (kõik autoriseeritud sama Adobe ID-ga).

    Vajalik tarkvara
    Mobiilsetes seadmetes (telefon või tahvelarvuti) lugemiseks peate installeerima selle tasuta rakenduse: PocketBook Reader (iOS / Android)

    PC või Mac seadmes lugemiseks peate installima Adobe Digital Editionsi (Seeon tasuta rakendus spetsiaalselt e-raamatute lugemiseks. Seda ei tohi segamini ajada Adober Reader'iga, mis tõenäoliselt on juba teie arvutisse installeeritud )

    Seda e-raamatut ei saa lugeda Amazon Kindle's. 

Deep Learning models are at the core of artificial intelligence research today. It is well known that deep learning techniques are disruptive for Euclidean data, such as images or sequence data, and not immediately applicable to graph-structured data such as text. This gap has driven a wave of research for deep learning on graphs, including graph representation learning, graph generation, and graph classification. The new neural network architectures on graph-structured data (graph neural networks, GNNs in short) have performed remarkably on these tasks, demonstrated by applications in social networks, bioinformatics, and medical informatics.  Despite these successes, GNNs still face many challenges ranging from the foundational methodologies to the theoretical understandings of the power of the graph representation learning.

This book provides a comprehensive introduction of GNNs. It first discusses the goals of graph representation learning and then reviews the history, current developments, and future directions of GNNs. The second part presents and reviews fundamental methods and theories concerning GNNs while the third part describes various frontiers that are built on the GNNs. The book concludes with an overview of recent developments in a number of applications using GNNs.

This book is suitable for a wide audience including undergraduate and graduate students, postdoctoral researchers, professors and lecturers, as well as industrial and government practitioners who are new to this area or who already have some basic background but want to learn more about advanced and promising techniques and applications.

Terminologies xxxi
1 Basic concepts of Graphs xxxi
2 Machine Learning on Graphs xxxii
3 Graph Neural Networks xxxii
Notations xxxv
Part I Introduction
1 Representation Learning
3(14)
Liang Zhao
Lingfei Wu
Peng Cui
Jian Pei
1.1 Representation Learning: An Introduction
3(2)
1.2 Representation Learning in Different Areas
5(9)
1.2.1 Representation Learning for Image Processing
5(3)
1.2.2 Representation Learning for Speech Recognition
8(2)
1.2.3 Representation Learning for Natural Language Processing
10(3)
1.2.4 Representation Learning for Networks
13(1)
1.3 Summary
14(3)
2 Graph Representation Learning
17(10)
Peng Cui
Lingfei Wu
Jian Pei
Liang Zhao
Xiao Wang
2.1 Graph Representation Learning: An Introduction
17(2)
2.2 Traditional Graph Embedding
19(1)
2.3 Modem Graph Embedding
20(5)
2.3.1 Structure-Property Preserving Graph Representation Learning
20(3)
2.3.2 Graph Representation Learning with Side Information
23(1)
2.3.3 Advanced Information Preserving Graph Representation Learning
24(1)
2.4 Graph Neural Networks
25(1)
2.5 Summary
26(1)
3 Graph Neural Networks
27(14)
Lingfei Wu
Peng Cui
Jian Pei
Liang Zhao
Le Song
3.1 Graph Neural Networks: An Introduction
28(1)
3.2 Graph Neural Networks: Overview
29(7)
3.2.1 Graph Neural Networks: Foundations
29(2)
3.2.2 Graph Neural Networks: Frontiers
31(2)
3.2.3 Graph Neural Networks: Applications
33(2)
3.2.4 Graph Neural Networks: Organization
35(1)
3.3 Summary
36(5)
Part II Foundations of Graph Neural Networks
4 Graph Neural Networks for Node Classification
41(22)
Jian Tang
Renjie Liao
4.1 Background and Problem Definition
41(1)
4.2 Supervised Graph Neural Networks
42(12)
4.2.1 General Framework of Graph Neural Networks
43(1)
4.2.2 Graph Convolutional Networks
44(2)
4.2.3 Graph Attention Networks
46(2)
4.2.4 Neural Message Passing Networks
48(1)
4.2.5 Continuous Graph Neural Networks
48(3)
4.2.6 Multi-Scale Spectral Graph Convolutional Networks
51(3)
4.3 Unsupervised Graph Neural Networks
54(5)
4.3.1 Variational Graph Auto-Encoders
54(3)
4.3.2 Deep Graph Infomax
57(2)
4.4 Over-smoothing Problem
59(2)
4.5 Summary
61(2)
5 The Expressive Power of Graph Neural Networks
63(36)
Pan Li
Jure Leskovec
5.1 Introduction
63(4)
5.2 Graph Representation Learning and Problem Formulation
67(3)
5.3 The Power of Message Passing Graph Neural Networks
70(7)
5.3.1 Preliminaries: Neural Networks for Sets
70(1)
5.3.2 Message Passing Graph Neural Networks
71(1)
5.3.3 The Expressive Power of MP-GNN
72(3)
5.3.4 MP-GNN with the Power of the 1-WL Test
75(2)
5.4 Graph Neural Networks Architectures that are more Powerful than 1-WL Test
77(20)
5.4.1 Limitations of MP-GNN
77(2)
5.4.2 Injecting Random Attributes
79(7)
5.4.3 Injecting Deterministic Distance Attributes
86(6)
5.4.4 Higher-order Graph Neural Networks
92(5)
5.5 Summary
97(2)
6 Graph Neural Networks: Scalability
99(22)
Hehuan Ma
Yu Rong
Junzhou Huang
6.1 Introduction
100(1)
6.2 Preliminary
101(1)
6.3 Sampling Paradigms
101(14)
6.3.1 Node-wise Sampling
103(3)
6.3.2 Layer-wise Sampling
106(5)
6.3.3 Graph-wise Sampling
111(4)
6.4 Applications of Large-scale Graph Neural Networks on Recommendation Systems
115(3)
6.4.1 Item-item Recommendation
116(1)
6.4.2 User-item Recommendation
116(2)
6.5 Future Directions
118(3)
7 Interpretability in Graph Neural Networks
121(28)
Ninghao Liu
Qizhang Feng
Xia Hu
7.1 Background: Interpretability in Deep Models
121(7)
7.1.1 Definition of Interpretability and Interpretation
122(1)
7.1.2 The Value of Interpretation
123(1)
7.1.3 Traditional Interpretation Methods
124(3)
7.1.4 Opportunities and Challenges
127(1)
7.2 Explanation Methods for Graph Neural Networks
128(10)
7.2.1 Background
128(2)
7.2.2 Approximation-Based Explanation
130(4)
7.2.3 Relevance-Propagation Based Explanation
134(1)
7.2.4 Perturbation-Based Approaches
135(2)
7.2.5 Generative Explanation
137(1)
7.3 Interpretable Modeling on Graph Neural Networks
138(5)
7.3.1 GNN-Based Attention Models
138(3)
7.3.2 Disentangled Representation Learning on Graphs
141(2)
7.4 Evaluation of Graph Neural Networks Explanations
143(3)
7.4.1 Benchmark Datasets
143(2)
7.4.2 Evaluation Metrics
145(1)
7.5 Future Directions
146(3)
8 Graph Neural Networks: Adversarial Robustness
149(30)
Stephan Gunnemann
8.1 Motivation
149(3)
8.2 Limitations of Graph Neural Networks: Adversarial Examples
152(8)
8.2.1 Categorization of Adversarial Attacks
152(4)
8.2.2 The Effect of Perturbations and Some Insights
156(3)
8.2.3 Discussion and Future Directions
159(1)
8.3 Provable Robustness: Certificates for Graph Neural Networks
160(5)
8.3.1 Model-Specific Certificates
160(3)
8.3.2 Model-Agnostic Certificates
163(2)
8.3.3 Advanced Certification and Discussion
165(1)
8.4 Improving Robustness of Graph Neural Networks
165(7)
8.4.1 Improving the Graph
166(1)
8.4.2 Improving the Training Procedure
167(3)
8.4.3 Improving the Graph Neural Networks' Architecture
170(1)
8.4.4 Discussion and Future Directions
171(1)
8.5 Proper Evaluation in the View of Robustness
172(3)
8.6 Summary
175(4)
Part III Frontiers of Graph Neural Networks
9 Graph Neural Networks: Graph Classification
179(16)
Christopher Morris
9.1 Introduction
179(1)
9.2 Graph neural networks for graph classification: Classic works and modern architectures
180(6)
9.2.1 Spatial approaches
181(3)
9.2.2 Spectral approaches
184(2)
9.3 Pooling layers: Learning graph-level outputs from node-level outputs
186(3)
9.3.1 Attention-based pooling layers
187(1)
9.3.2 Cluster-based pooling layers
187(1)
9.3.3 Other pooling layers
188(1)
9.4 Limitations of graph neural networks and higher-order layers for graph classification
189(2)
9.4.1 Overcoming limitations
190(1)
9.5 Applications of graph neural networks for graph classification
191(1)
9.6 Benchmark Datasets
192(1)
9.7 Summary
192(3)
10 Graph Neural Networks: Link Prediction
195(30)
Muhan Zhang
10.1 Introduction
195(2)
10.2 Traditional Link Prediction Methods
197(6)
10.2.1 Heuristic Methods
197(3)
10.2.2 Latent-Feature Methods
200(3)
10.2.3 Content-Based Methods
203(1)
10.3 GNN Methods for Link Prediction
203(8)
10.3.1 Node-Based Methods
203(3)
10.3.2 Subgraph-Based Methods
206(3)
10.3.3 Comparing Node-Based Methods and Subgraph-Based Methods
209(2)
10.4 Theory for Link Prediction
211(9)
10.4.1 y-Decaying Heuristic Theory
211(6)
10.4.2 Labeling Trick
217(3)
10.5 Future Directions
220(5)
10.5.1 Accelerating Subgraph-Based Methods
220(1)
10.5.2 Designing More Powerful Labeling Tricks
221(1)
10.5.3 Understanding When to Use One-Hot Features
222(3)
11 Graph Neural Networks: Graph Generation
225(26)
Renjie Liao
11.1 Introduction
225(1)
11.2 Classic Graph Generative Models
226(3)
11.2.1 Erdos-Renyi Model
226(2)
11.2.2 Stochastic Block Model
228(1)
11.3 Deep Graph Generative Models
229(21)
11.3.1 Representing Graphs
230(1)
11.3.2 Variational Auto-Encoder Methods
230(6)
11.3.3 Deep Autoregressive Methods
236(8)
11.3.4 Generative Adversarial Methods
244(6)
11.4 Summary
250(1)
12 Graph Neural Networks: Graph Transformation
251(26)
Xiaojie Guo
Shiyu Wang
Liang Zhao
12.1 Problem Formulation of Graph Transformation
252(1)
12.2 Node-level Transformation
253(3)
12.2.1 Definition of Node-level Transformation
253(1)
12.2.2 Interaction Networks
253(1)
12.2.3 Spatio-Temporal Convolution Recurrent Neural Networks
254(2)
12.3 Edge-level Transformation
256(5)
12.3.1 Definition of Edge-level Transformation
256(1)
12.3.2 Graph Transformation Generative Adversarial Networks
257(2)
12.3.3 Multi-scale Graph Transformation Networks
259(1)
12.3.4 Graph Transformation Policy Networks
260(1)
12.4 Node-Edge Co-Transformation
261(10)
12.4.1 Definition of Node-Edge Co-Transformation
261(5)
12.4.2 Editing-based Node-Edge Co-Transformation
266(5)
12.5 Other Graph-based Transformations
271(4)
12.5.1 Sequence-to-Graph Transformation
271(1)
12.5.2 Graph-to-Sequence Transformation
272(1)
12.5.3 Context-to-Graph Transformation
273(2)
12.6 Summary
275(2)
13 Graph Neural Networks: Graph Matching
277(20)
Xiang Ling
Lingfei Wu
Chunming Wu
Shouling Ji
13.1 Introduction
278(1)
13.2 Graph Matching Learning
279(9)
13.2.1 Problem Definition
280(2)
13.2.2 Deep Learning based Models
282(2)
13.2.3 Graph Neural Network based Models
284(4)
13.3 Graph Similarity Learning
288(7)
13.3.1 Problem Definition
288(2)
13.3.2 Graph-Graph Regression Tasks
290(3)
13.3.3 Graph-Graph Classification Tasks
293(2)
13.4 Summary
295(2)
14 Graph Neural Networks: Graph Structure Learning
297(26)
Yu Chen
Lingfei Wu
14.1 Introduction
297(2)
14.2 Traditional Graph Structure Learning
299(4)
14.2.1 Unsupervised Graph Structure Learning
299(2)
14.2.2 Supervised Graph Structure Learning
301(2)
14.3 Graph Structure Learning for Graph Neural Networks
303(16)
14.3.1 Joint Graph Structure and Representation Learning
304(13)
14.3.2 Connections to Other Problems
317(2)
14.4 Future Directions
319(1)
14.4.1 Robust Graph Structure Learning
319(1)
14.4.2 Scalable Graph Structure Learning
320(1)
14.4.3 Graph Structure Learning for Heterogeneous Graphs
320(1)
14.5 Summary
320(3)
15 Dynamic Graph Neural Networks
323(28)
Seyed Mehran Kazemi
15.1 Introduction
323(2)
15.2 Background and Notation
325(6)
15.2.1 Graph Neural Networks
325(2)
15.2.2 Sequence Models
327(3)
15.2.3 Encoder-Decoder Framework and Model Training
330(1)
15.3 Categories of Dynamic Graphs
331(4)
15.3.1 Discrete vs. Continues
331(2)
15.3.2 Types of Evolution
333(1)
15.3.3 Prediction Problems, Interpolation, and Extrapolation
334(1)
15.4 Modeling Dynamic Graphs with Graph Neural Networks
335(8)
15.4.1 Conversion to Static Graphs
335(2)
15.4.2 Graph Neural Networks for DTDGs
337(3)
15.4.3 Graph Neural Networks for CTDGs
340(3)
15.5 Applications
343(5)
15.5.1 Skeleton-based Human Activity Recognition
343(2)
15.5.2 Traffic Forecasting
345(1)
15.5.3 Temporal Knowledge Graph Completion
346(2)
15.6 Summary
348(3)
16 Heterogeneous Graph Neural Networks
351(20)
Chuan Shi
16.1 Introduction to HGNNs
351(5)
16.1.1 Basic Concepts of Heterogeneous Graphs
353(1)
16.1.2 Challenges of HG Embedding
354(1)
16.1.3 Brief Overview of Current Development
355(1)
16.2 Shallow Models
356(4)
16.2.1 Decomposition-based Methods
357(1)
16.2.2 Random Walk-based Methods
358(2)
16.3 Deep Models
360(6)
16.3.1 Message Passing-based Methods (HGNNs)
360(3)
16.3.2 Encoder-decoder-based Methods
363(1)
16.3.3 Adversarial-based Methods
364(2)
16.4 Review
366(1)
16.5 Future Directions
367(4)
16.5.1 Structures and Properties Preservation
367(1)
16.5.2 Deeper Exploration
367(1)
16.5.3 Reliability
368(1)
16.5.4 Applications
369(2)
17 Graph Neural Networks: AutoML
371(20)
Kaixiong Zhou
Zirui Liu
Keyu Duan
Xia Hu
17.1 Background
372(4)
17.1.1 Notations of AutoGNN
373(2)
17.1.2 Problem Definition of AutoGNN
375(1)
17.1.3 Challenges in AutoGNN
375(1)
17.2 Search Space
376(6)
17.2.1 Architecture Search Space
377(3)
17.2.2 Training Hyperparameter Search Space
380(1)
17.2.3 Efficient Search Space
381(1)
17.3 Search Algorithms
382(5)
17.3.1 Random Search
382(1)
17.3.2 Evolutionary Search
382(1)
17.3.3 Reinforcement Learning Based Search
383(2)
17.3.4 Differentiable Search
385(1)
17.3.5 Efficient Performance Estimation
386(1)
17.4 Future Directions
387(4)
18 Graph Neural Networks: Self-supervised Learning
391(32)
Yu Wang
Wei Jin
Tyler Derr
18.1 Introduction
392(1)
18.2 Self-supervised Learning
393(2)
18.3 Applying SSL to Graph Neural Networks: Categorizing Training Strategies, Loss Functions and Pretext Tasks
395(8)
18.3.1 Training Strategies
396(3)
18.3.2 Loss Functions
399(3)
18.3.3 Pretext Tasks
402(1)
18.4 Node-level SSL Pretext Tasks
403(5)
18.4.1 Structure-based Pretext Tasks
403(1)
18.4.2 Feature-based Pretext Tasks
404(2)
18.4.3 Hybrid Pretext Tasks
406(2)
18.5 Graph-level SSL Pretext Tasks
408(9)
18.5.1 Structure-based Pretext Tasks
408(5)
18.5.2 Feature-based Pretext Tasks
413(1)
18.5.3 Hybrid Pretext Tasks
414(3)
18.6 Node-graph-level SSL Pretext Tasks
417(1)
18.7 Discussion
418(1)
18.8 Summary
419(4)
Part IV Broad and Emerging Applications with Graph Neural Networks
19 Graph Neural Networks in Modern Recommender Systems
423(24)
Yunfei Chu
Jiangchao Yao
Chang Zhou
Hongxia Yang
19.1 Graph Neural Networks for Recommender System in Practice
423(8)
19.1.1 Introduction
423(5)
19.1.2 Classic Approaches to Predict User-Item Preference
428(1)
19.1.3 Item Recommendation in user-item Recommender Systems: a Bipartite Graph Perspective
429(2)
19.2 Case Study 1: Dynamic Graph Neural Networks Learning
431(7)
19.2.1 Dynamic Sequential Graph
431(1)
19.2.2 DSGL: Dynamic Sequential Graph Learning
432(3)
19.2.3 Model Prediction
435(1)
19.2.4 Experiments and Discussions
436(2)
19.3 Case Study 2: Device-Cloud Collaborative Learning for Graph Neural Networks
438(6)
19.3.1 The proposed framework
438(4)
19.3.2 Experiments and Discussions
442(2)
19.4 Future Directions
444(3)
20 Graph Neural Networks in Computer Vision
447(16)
Siliang Tang
Wenqiao Zhang
Zongshen Mu
Kai Shen
Juncheng Li
Jiacheng Li
Lingfei Wu
20.1 Introduction
448(1)
20.2 Representing Vision as Graphs
448(3)
20.2.1 Visual Node representation
448(2)
20.2.2 Visual Edge representation
450(1)
20.3 Case Study 1: Image
451(3)
20.3.1 Object Detection
451(2)
20.3.2 Image Classification
453(1)
20.4 Case Study 2: Video
454(3)
20.4.1 Video Action Recognition
454(2)
20.4.2 Temporal Action Localization
456(1)
20.5 Other Related Work: Cross-media
457(3)
20.5.1 Visual Caption
457(1)
20.5.2 Visual Question Answering
458(1)
20.5.3 Cross-Media Retrieval
459(1)
20.6 Frontiers for Graph Neural Networks on Computer Vision
460(2)
20.6.1 Advanced Graph Neural Networks for Computer Vision
460(1)
20.6.2 Broader Area of Graph Neural Networks on Computer Vision
461(1)
20.7 Summary
462(1)
21 Graph Neural Networks in Natural Language Processing
463(20)
Bang Liu
Lingfei Wu
21.1 Introduction
463(3)
21.2 Modeling Text as Graphs
466(4)
21.2.1 Graph Representations in Natural Language Processing
466(2)
21.2.2 Tackling Natural Language Processing Tasks from a Graph Perspective
468(2)
21.3 Case Study 1: Graph-based Text Clustering and Matching
470(5)
21.3.1 Graph-based Clustering for Hot Events Discovery and Organization
470(3)
21.3.2 Long Document Matching with Graph Decomposition and Convolution
473(2)
21.4 Case Study 2: Graph-based Multi-Hop Reading Comprehension
475(4)
21.5 Future Directions
479(1)
21.6 Conclusions
480(3)
22 Graph Neural Networks in Program Analysis
483(16)
Miltiadis Allamanis
22.1 Introduction
483(1)
22.2 Machine Learning in Program Analysis
484(2)
22.3 A Graph Represention of Programs
486(3)
22.4 Graph Neural Networks for Program Graphs
489(2)
22.5 Case Study 1: Detecting Variable Misuse Bugs
491(2)
22.6 Case Study 2: Predicting Types in Dynamically Typed Languages
493(2)
22.7 Future Directions
495(4)
23 Graph Neural Networks in Software Mining
499(18)
Collin McMillan
23.1 Introduction
499(1)
23.2 Modeling Software as a Graph
500(3)
23.2.1 Macro versus Micro Representations
501(2)
23.2.2 Combining the Macro- and Micro-level
503(1)
23.3 Relevant Software Mining Tasks
503(1)
23.4 Example Software Mining Task: Source Code Summarization
504(8)
23.4.1 Primer GNN-based Code Summarization
505(5)
23.4.2 Directions for Improvement
510(2)
23.5 Summary
512(5)
24 GNN-based Biomedical Knowledge Graph Mining in Drug Development
517(24)
Chang Su
Yu Hou
Fei Wang
24.1 Introduction
517(1)
24.2 Existing Biomedical Knowledge Graphs
518(5)
24.3 Inference on Knowledge Graphs
523(5)
24.3.1 Conventional KG inference techniques
523(1)
24.3.2 GNN-based KG inference techniques
524(4)
24.4 KG-based hypothesis generation in computational drug development
528(3)
24.4.1 A machine learning framework for KG-based drug repurposing
529(1)
24.4.2 Application of KG-based drug repurposing in COVID-19
530(1)
24.5 Future directions
531(10)
24.5.1 KG quality control
532(1)
24.5.2 Scalable inference
533(1)
24.5.3 Coupling KGs with other biomedical data
533(8)
25 Graph Neural Networks in Predicting Protein Function and Interactions
541(16)
Anowarul Kabir
Amarda Shehu
25.1 From Protein Interactions to Function: An Introduction
541(6)
25.1.1 Enter Stage Left: Protein-Protein Interaction Networks
542(1)
25.1.2 Problem Formulation(s), Assumptions, and Noise: A Historical Perspective
543(1)
25.1.3 Shallow Machine Learning Models over the Years
543(1)
25.1.4 Enter Stage Right: Graph Neural Networks
544(3)
25.2 Highlighted Case Studies
547(8)
25.2.1 Case Study 1: Prediction of Protein-Protein and Protein-Drug Interactions: The Link Prediction Problem
547(2)
25.2.2 Case Study 2: Prediction of Protein Function and Functionally-important Residues
549(4)
25.2.3 Case Study 3: From Representation Learning to Multirelational Link Prediction in Biological Networks with Graph Autoencoders
553(2)
25.3 Future Directions
555(2)
26 Graph Neural Networks in Anomaly Detection
557(22)
Shen Wang
Philip S. Yu
26.1 Introduction
557(4)
26.2 Issues
561(3)
26.2.1 Data-specific issues
561(2)
26.2.2 Task-specific Issues
563(1)
26.2.3 Model-specific Issues
563(1)
26.3 Pipeline
564(4)
26.3.1 Graph Construction and Transformation
564(1)
26.3.2 Graph Representation Learning
565(2)
26.3.3 Prediction
567(1)
26.4 Taxonomy
568(1)
26.5 Case Studies
568(9)
26.5.1 Case Study 1: Graph Embeddings for Malicious Accounts Detection
569(1)
26.5.2 Case Study 2: Hierarchical Attention Mechanism based Cash-out User Detection
570(2)
26.5.3 Case Study 3: Attentional Heterogeneous Graph Neural Networks for Malicious Program Detection
572(1)
26.5.4 Case Study 4: Graph Matching Framework to Learn the Program Representation and Similarity Metric via Graph Neural Networks for Unknown Malicious Program Detection
573(2)
26.5.5 Case Study 5: Anomaly Detection in Dynamic Graph Using Attention-based Temporal GCN
575(1)
26.5.6 Case Study 6: GCN-based Anti-Spam for Spam Review Detection
576(1)
26.6 Future Directions
577(2)
27 Graph Neural Networks in Urban Intelligence
579(16)
Yanhua Li
Xun Zhou
Menghai Pan
27.1 Graph Neural Networks for Urban Intelligence
580(15)
27.1.1 Introduction
580(1)
27.1.2 Application scenarios in urban intelligence
581(3)
27.1.3 Representing urban systems as graphs
584(2)
27.1.4 Case Study 1: Graph Neural Networksin urban configuration and transportation
586(3)
27.1.5 Case Study 2: Graph Neural Networks in urban anomaly and event detection
589(1)
27.1.6 Case Study 3: Graph Neural Networks in urban human behavior inference
590(2)
27.1.7 Future Directions
592(3)
References 595
Dr. Lingfei Wu is a Principal Scientist at JD.COM Silicon Valley Research Center, leading a team of 30+ machine learning/natural language processing scientists and software engineers to build intelligent e-commerce personalization system. He earned his Ph.D. degree in computer science from the College of William and Mary in 2016. Previously, he was a research staff member at IBM Thomas J. Watson Research Center and led a 10+ research scientist team for developing novel Graph Neural Networks methods and systems, which leads to the #1 AI Challenge Project in IBM Research and multiple IBM Awards including three-time Outstanding Technical  Achievement Award. He has published more than 90 top-ranked conference and journal papers, and is a co-inventor of more than 40 filed US patents. Because of the high commercial value of his patents, he has received eight invention achievement awards and has been appointed as IBM Master Inventors, class of 2020. He was the recipients of theBest Paper Award and Best Student Paper Award of several conferences such as IEEE ICC19, AAAI workshop on DLGMA20 and KDD workshop on DLG19. His research has been featured in numerous media outlets, including NatureNews, YahooNews, Venturebeat, TechTalks, SyncedReview, Leiphone, QbitAI, MIT News, IBM Research News, and SIAM News. He has co-organized 10+ conferences (KDD, AAAI, IEEE BigData) and is the founding co-chair for Workshops of Deep Learning on Graphs (with AAAI21, AAAI20, KDD21, KDD20, KDD19, and IEEE BigData19). He has currently served as Associate Editor for IEEE Transactions on Neural Networks and Learning Systems, ACM Transactions on Knowledge Discovery from Data and International Journal of Intelligent Systems, and regularly served as a SPC/PC member of the following major AI/ML/NLP conferences including KDD, IJCAI, AAAI, NIPS, ICML, ICLR, and ACL.

Dr. Peng Cui is an Associate Professor with tenure at Department of Computer Science in Tsinghua University. He obtained his PhD degree from Tsinghua University in 2010. His research interests include data mining, machine learning and multimedia analysis, with expertise on network representation learning, causal inference and stable learning, social dynamics modeling, and user behavior modeling, etc. He is keen to promote the convergence and integration of causal inference and machine learning, addressing the fundamental issues of todays AI technology, including explainability, stability and  fairness issues. He is recognized as a Distinguished Scientist of ACM, Distinguished Member of CCF and Senior Member of IEEE. He has published more than 100 papers in prestigious conferences and journals in machine learning and data mining. He is one of the most cited authors in network embedding. A number of his pro- posed algorithms on network embedding generate substantial impact in academia and industry. His recent research won the IEEE Multimedia Best Department Paper Award, IEEE ICDM2015 Best Student Paper Award, IEEE ICME 2014 Best Paper Award, ACM MM12 Grand Challenge Multimodal Award, MMM13 Best Paper Award, and were selected into the Best of KDD special issues in 2014 and 2016, respectively. He was PC co-chair of CIKM2019 and MMM2020, SPC or area chair of ICML, KDD, WWW, IJCAI, AAAI, etc., and Associate Editors of IEEE TKDE (2017-), IEEE TBD (2019-), ACM TIST(2018-), and ACM TOMM (2016-) etc. He received ACM China Rising Star Award in 2015, and CCF-IEEE CS Young Scientist Award in 2018.

Dr. Jian Pei is a Professor in the School of Computing Science at Simon Fraser University. He is a well-known leading researcher in the general areas of data science, big data, data mining, and database systems. His expertise is on developing effective and efficient data analysis techniques for novel data intensive applications, and transferring his research results to products and business practice. He is recognized as a Fellow of the Royal Society of Canada (Canadas national academy), the Canadian Academy of Engineering, the Association of Computing Machinery (ACM) and the Institute of Electrical and Electronics Engineers (IEEE). He is one of the most cited authors in data mining, database systems, and information retrieval. Since 2000, he has published one textbook, two monographs and over 300 research papers in refereed journals and conferences, which have been cited extensively by others. His research has generated remarkable impact substantially beyond academia. For example, his algorithms have been adopted by industry in production and popular open-source software suites. Jian Pei also demonstrated outstanding professional leadership in many academic organizations and activities. He was the editor-in-chief of the IEEE Transactions of Knowledge and Data Engineering (TKDE) in 2013-16, the chair of the Special Interest Group on Knowledge Discovery in Data (SIGKDD) of the As- sociation for Computing Machinery (ACM) in 2017-2021, and a general co-chair or program committee co-chair of many premier conferences. He maintains a wide spectrum of industry relations with both global and local industry partners. He is an active consultant and coach for industry on enterprise data strategies, healthcare informatics, network security intelligence, computational finance, and smart retail. He received many prestigious awards, including the 2017 ACM SIGKDD Innovation Award, the 2015 ACM SIGKDD Service Award, the 2014 IEEE ICDM Re- search Contributions Award, the British Columbia Innovation Council 2005 Young Innovator Award, an NSERC 2008 Discovery Accelerator Supplements Award (100 awards cross the whole country), an IBM Faculty Award (2006), a KDD Best Ap- plication Paper Award (2008), an ICDE Influential Paper Award (2018), a PAKDD Best Paper Award (2014), a PAKDD Most Influential Paper Award (2009), and an IEEE Outstanding Paper Award (2007).

Dr. Liang Zhao is an assistant professor at the Department of Compute Science at Emory University. Before that, he was an assistant professor in the Department of Information Science and Technology and the Department of Computer Science at George Mason University. He obtained his PhD degree in 2016 from Computer Science Department at Virginia Tech in the United States. His research interests include data mining, artificial intelligence, and machine learning, with special interests in spatiotemporal and network data mining, deep learning on graphs, nonconvex optimization, model parallelism, event prediction, and interpretable machine learning. He received AWS Ma- chine Learning Research Award in 2020 from Amazon Company for his research on distributed graph neural networks. He won NSF Career Award in 2020 awarded by National Science Foundation for his research on deep learning for spatial networks, and Jeffress Trust Award in 2019 for his research on deep generative models for bio- molecules, awarded by Jeffress Memorial Trust Foundation and Bank of America. He won the Best Paper Award in the 19th IEEE International Conference on Data Mining (ICDM 2019) for the paper of his lab on deep graph transformation. He has also won Best Paper Award Shortlist in the 27th Web Conference (WWW 2021) for deep generative models. He was selected as Top 20 Rising Star in Data Mining by Microsoft Search in 2016 for his research on spatiotemporal data mining. He has also won Outstanding Doctoral Student in the Department of Computer Science at Virginia Tech in 2017. He is awarded as CI-Fellow Mentor 2021 by the Computing Community Consortium for his research on deep learning for spatial data. He has published numerous research papers in top-tier conferences and journals such as KDD, TKDE, ICDM, ICLR, Proceedings of the IEEE, ACM Computing Surveys, TKDD, IJCAI, AAAI, and WWW. He has been serving as organizers such as publication chair, poster chair, and session chair for many top-tier conferences such as SIGSPATIAL, KDD, ICDM, and CIKM.





 
Lisainfo e-raamatute kohta Lisainfo e-raamatute kohta
Püsilink: https://www.kriso.ee/db/97898116605422e.html
Märksõnad: