A gentle introduction to deep learning for graphs

被引：160
作者：
Bacciu, Davide [1 ]
Errica, Federico [1 ]
Micheli, Alessio [1 ]
Podda, Marco [1 ]
机构：
[1] Univ Pisa, Dept Comp Sci, Pisa, Italy
来源：
NEURAL NETWORKS | 2020年 / 129卷
关键词：
Deep learning for graphs; Graph neural networks; Learning for structured data; CASCADE CORRELATION; GENERAL FRAMEWORK; NEURAL-NETWORKS; CLASSIFICATION;
D O I：
10.1016/j.neunet.2020.06.006
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
The adaptive processing of graph data is a long-standing research topic that has been lately consolidated as a theme of major interest in the deep learning community. The snap increase in the amount and breadth of related research has come at the price of little systematization of knowledge and attention to earlier literature. This work is a tutorial introduction to the field of deep learning for graphs. It favors a consistent and progressive presentation of the main concepts and architectural aspects over an exposition of the most recent literature, for which the reader is referred to available surveys. The paper takes a top-down view of the problem, introducing a generalized formulation of graph representation learning based on a local and iterative approach to structured information processing. Moreover, it introduces the basic building blocks that can be combined to design novel and effective neural models for graphs. We complement the methodological exposition with a discussion of interesting research challenges and applications in the field. (C) 2020 Elsevier Ltd. All rights reserved.
引用
收藏
页码：203 / 221
页数：19
相关论文
共 146 条
  • [51] A self-organizing map for adaptive processing of structured data
    Hagenbuchner, M
    Sperduti, A
    Tsoi, AC
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 2003, 14 (03): : 491 - 505
  • [52] Graph self-organizing maps for cyclic and unbounded graphs
    Hagenbuchner, M.
    Sperduti, A.
    Tsoi, A. C.
    [J]. NEUROCOMPUTING, 2009, 72 (7-9) : 1419 - 1430
  • [53] What is a good medical decision? A research agenda guided by perspectives from multiple stakeholders
    Hamilton, Jada G.
    Lillie, Sarah E.
    Alden, Dana L.
    Scherer, Laura
    Oser, Megan
    Rini, Christine
    Tanaka, Miho
    Baleix, John
    Brewster, Mikki
    Lee, Simon Craddock
    Goldstein, Mary K.
    Jacobson, Robert M.
    Myers, Ronald E.
    Zikmund-Fisher, Brian J.
    Waters, Erika A.
    [J]. JOURNAL OF BEHAVIORAL MEDICINE, 2017, 40 (01) : 52 - 68
  • [54] Hamilton W. L., 2017, ADV NEURAL INFORM PR, P1025, DOI DOI 10.48550/ARXIV.1706.02216
  • [55] Universal approximation capability of cascade correlation for structures
    Hammer, B
    Micheli, A
    Sperduti, A
    [J]. NEURAL COMPUTATION, 2005, 17 (05) : 1109 - 1159
  • [56] Recursive self-organizing network models
    Hammer, B
    Micheli, A
    Sperduti, A
    Strickert, M
    [J]. NEURAL NETWORKS, 2004, 17 (8-9) : 1061 - 1085
  • [57] A general framework for unsupervised processing of structured data
    Hammer, B
    Micheli, A
    Sperduti, A
    Strickert, M
    [J]. NEUROCOMPUTING, 2004, 57 : 3 - 35
  • [58] Wavelets on graphs via spectral graph theory
    Hammond, David K.
    Vandergheynst, Pierre
    Gribonval, Remi
    [J]. APPLIED AND COMPUTATIONAL HARMONIC ANALYSIS, 2011, 30 (02) : 129 - 150
  • [59] The Predictive Toxicology Challenge 2000-2001
    Helma, C
    King, RD
    Kramer, S
    Srinivasan, A
    [J]. BIOINFORMATICS, 2001, 17 (01) : 107 - 108
  • [60] Hochreiter S, 1997, NEURAL COMPUT, V9, P1735, DOI [10.1162/neco.1997.9.8.1735, 10.1162/neco.1997.9.1.1, 10.1007/978-3-642-24797-2]
12345678910