Network embedding : theories, methods, and applications

Bibliographische Detailangaben

Titel
Network embedding theories, methods, and applications
verantwortlich
Yang, Cheng (VerfasserIn); Liu, Zhiyuan (VerfasserIn); Tu, Cunchao (VerfasserIn); Shi, Chuan (VerfasserIn); Sun, Maosong (VerfasserIn)
Schriftenreihe
Synthesis lectures on artificial intelligence and machine learning ; 48
veröffentlicht
[San Rafael, CA]: Morgan & Claypool Publishers, [2021]
Erscheinungsjahr
2021
Teil von
Synthesis lectures on artificial intelligence and machine learning ; 48
Medientyp
Buch
Datenquelle
K10plus Verbundkatalog
Tags
Tag hinzufügen

Zugang

Weitere Informationen sehen Sie, wenn Sie angemeldet sind. Noch keinen Account? Jetzt registrieren.

Zusammenfassung
Part I. Introduction to network embedding. 1. The basics of network embedding -- 1.1. Background -- 1.2. The rising of network embedding -- 1.3. The evaluation of network embedding
2. Network embedding for general graphs -- 2.1. Representative methods -- 2.2. Theory : a unified network embedding framework -- 2.3. Method : network embedding update (NEU) -- 2.4. Empirical analysis -- 2.5. Further reading
Part II. Network embedding with additional information. 3. Network embedding for graphs with node attributes -- 3.1. Overview -- 3.2. Method : text-associated DeepWalk -- 3.3. Empirical analysis -- 3.4. Further reading
4. Revisiting attributed network embedding : a GCN-based perspective -- 4.1. GCN-based network embedding -- 4.2. Method : adaptive graph encoder -- 4.3. Empirical analysis -- 4.4. Further reading
5. Network embedding for graphs with node contents -- 5.1. Overview -- 5.2. Method : context-aware network embedding -- 5.3. Empirical analysis -- 5.4. Further reading
6. Network embedding for graphs with node labels -- 6.1. Overview -- 6.2. Method : max-margin DeepWalk -- 6.3. Empirical analysis -- 6.4. Further reading
Part III. Network embedding with different characteristics. 7. Network embedding for community-structured graphs -- 7.1. Overview -- 7.2. Method : community-enhanced NRL -- 7.3. Empirical analysis -- 7.4. Further reading
8. Network embedding for large-scale graphs -- 8.1. Overview -- 8.2. Method : COmpresSIve network embedding (COSINE) -- 8.3. Empirical analysis -- 8.4. Further reading
9. Network embedding for heterogeneous graphs -- 9.1. Overview -- 9.2. Method : relation structure-aware HIN embedding -- 9.3. Empirical analysis -- 9.4. Further reading
Part IV. Network embedding applications. 10. Network embedding for social relation extraction -- 10.1. Overview -- 10.2. Method : TransNet -- 10.3. Empirical analysis -- 10.4. Further reading
11. Network embedding for recommendation systems on LBSNs -- 11.1. Overview -- 11.2. Method : joint network and trajectory model (JNTM) -- 11.3. Empirical analysis -- 11.4. Further reading
12. Network embedding for information diffusion prediction -- 12.1. Overview -- 12.2. Method : neural diffusion model (NDM) -- 12.3. Empirical analysis -- 12.4. Further reading
Part V. Outlook for network embedding. 13. Future directions of network embedding -- 13.1. Network embedding based on advanced techniques -- 13.2. Network embedding in more fine-grained scenarios -- 13.3. Network embedding with better interpretability -- 13.4. Network embedding for applications.
Many machine learning algorithms require real-valued feature vectors of data instances as inputs. By projecting data into vector spaces, representation learning techniques have achieved promising performance in many areas such as computer vision and natural language processing. There is also a need to learn representations for discrete relational data, namely networks or graphs. Network Embedding (NE) aims at learning vector representations for each node or vertex in a network to encode the topologic structure. Due to its convincing performance and efficiency, NE has been widely applied in many network applications such as node classification and link prediction. This book provides a comprehensive introduction to the basic concepts, models, and applications of network representation learning (NRL). The book starts with an introduction to the background and rising of network embeddings as a general overview for readers. Then it introduces the development of NE techniques by presenting several representative methods on general graphs, as well as a unified NE framework based on matrix factorization. Afterward, it presents the variants of NE with additional information: NE for graphs with node attributes/contents/labels; and the variants with different characteristics: NE for community-structured/large-scale/heterogeneous graphs. Further, the book introduces different applications of NE such as recommendation and information diffusion prediction. Finally, the book concludes the methods and applications and looks forward to the future directions
Umfang
xxi, 220 Seiten; Diagramme
Sprache
Englisch
Schlagworte
BK-Notation
54.72 Künstliche Intelligenz
DDC-Notation
006.3/1
ISBN
1636390463
9781636390468
9781636390444