Neural network for graphs: A contextual constructive approach

IEEE Transactions on Neural Networks

Volumn 20, Issue 3, 2009, Pages 498-511

  Micheli, Alessio ^a  

^a UNIVERSITY OF PISA   (Italy)

Author keywords

Cascade correlation; Contextual transductions; Graph patterns; Learning in structured domains (SDs); Neural networks for structured data; Recursive neural networks

Indexed keywords

BACTERIOPHAGES; DIFFUSERS (OPTICAL); EDUCATION; NEURONS; RECURSIVE FUNCTIONS; STATE FEEDBACK;

CASCADE CORRELATION; CONTEXTUAL TRANSDUCTIONS; GRAPH PATTERNS; LEARNING IN STRUCTURED DOMAINS (SDS); RECURSIVE NEURAL NETWORKS;

FEEDFORWARD NEURAL NETWORKS;

EID: 63049119992     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/TNN.2008.2010350     Document Type: Article

References (47)

1. L. Getoor and B. Taskar, Introduction to Statistical Relational Learning (Adaptive Computation and Machine Learning). Cambridge, MA: MIT Press, 2007.
2. L. D. Raedt, "Statistical relational learning: An inductive logic programming perspective," in Lecture Notes in Computer Science. Berlin, Germany: Springer-Verlag, 2005, vol. 3721, pp. 3-5.
3. S. Džeroski and N. Lavrač, Relational Data Mining. Berlin, Germany: Springer-Verlag, Sep. 2001.
4. T. Gärtner, "A survey of kernels for structured data," SIGKDD Explor. Newslett., vol. 5, no. 1, pp. 49-58, 2003.
5. J. Shawe-Taylor and N. Cristianini, Kernel Methods for Pattern Analysis. Cambridge, U.K.: Cambridge Univ. Press, Jun. 2004.
6. B. Hammer and B. J. Jain, "Neural methods for non-standard data," in Proc. Eur. Symp. Artif. Neural Netw., 2004, pp. 281-292.
7. B. Schölkopf, K. Tsuda, and J. Vert, Kernel Methods in Computational Biology. Cambridge, MA: MIT Press, 2004.
8. A. Micheli, A. Sperduti, and A. Starita, "An introduction to recursive neural networks and kernel methods for cheminformatics," Curr. Pharm. Des., vol. 13, Special Issue on "Ground-Breaking Mathematical Models for Basic and Applied Research", no. 14, pp. 1469-1495, 2007.
9. J. Ramon and T. Gartner, "Expressivity versus efficiency of graph kernels," in Proc. 1st Int. Workshop Mining Graphs Trees Sequences 2003 [Online]. Available: http://www.ar.sanken.osaka-u.ac.jp/~washio/list/7.pdf
10. T. Gartner, P. Flach, and S. Wrobel, "On graph kernels: Hardness results and efficient alternatives," in Proc. 16th Annu. Conf. Comput. Learn. Theory/7th Kernel Workshop, Aug. 2003, pp. 129-143.
11. P. Frasconi, M. Gori, and A. Sperduti, "A general framework for adaptive processing of data structures," IEEE Trans. Neural Netw. vol. 9, no. 5, pp. 768-786, Sep. 1998.
12. A. Sperduti and A. Starita, "Supervised neural networks for the classification of structures," IEEE Trans. Neural Netw., vol. 8, no. 3, pp. 714-735, May 1997.
13. P. Frasconi, M. Gori, A. Küchler, and A. Sperduti, "From sequences to data structures: Theory and applications," in A Field Guide to Dynamical Recurrent Networks, K. J. F. and K. S. C., Eds. Piscataway, NJ: IEEE Press, 2001, ch. 19.
14. S. Fahlman and C. Lebiere, "The recurrent cascade-correlation learning architecture," Carnegie Mellon Univ., Pittsburgh, PA, Tech. Rep. CMU-CS-91-100, May 1991.
15. A. Bianucci, A. Micheli, A. Sperduti, and A. Starita, "Application of cascade correlation networks for structures to chemistry," Appl. Intell., vol. 12, pp. 117-146, 2000.
16. A. Micheli, "Recursive processing of structured domains in machine learning," Ph.D. dissertation, Dept. Comput. Sci., Univ. Pisa, Pisa, Italy, 2003, TD-13/03.
17. A. Micheli, D. Sona, and A. Sperduti, "Contextual processing of structured data by recursive cascade correlation," IEEE Trans. Neural Netw., vol. 15, no. 6, pp. 1396-1410, Nov. 2004.
18. M. Bianchini, M. Gori, and F. Scarselli, "Processing directed acyclic graphs with recursive neural networks," IEEE Trans. Neural Netw., vol. 12, no. 6, pp. 1464-1470, Nov. 2001.
19. B. Hammer, A. Micheli, and A. Sperduti, "Universal approximation capability of cascade correlation for structures," Neural Comput. vol. 17, no. 5, pp. 1109-1159, 2005.
20. M. Bianchini, M. Gori, L. Sarti, and F. Scarselli, "Recursive processing of cyclic graphs," IEEE Trans. Neural Netw., vol. 17, no. 1, pp. 10-18, Jan. 2006.
21. F. Scarselli, A. Tsoi, M. Gori, and M. Hagenbuchner, "A new neural network model for graph processing," Univ. Siena, Siena, Italy, Tech. Rep. DII 01/05, Jul. 2005.
22. V. Di Massa, G. Monfardini, L. Sarti, F. Scarselli, M. Maggini, and M. Gori, "A comparison between recursive neural networks and graph neural networks," in Proc. World Congr. Comput. Intell./Int. Joint Conf. Neural Netw., 2006, pp. 778-785.
23. B. Hammer and J. J. Steil, "Tutorial: Perspectives on learning with RNNs," in Proc. Eur. Symp. Artif. Neural Netw., 2002, pp. 357-368.
24. O. De Jesus and M. T. Hagan, "Backpropagation algorithms for a broad class of dynamic networks," IEEE Trans. Neural Netw., vol. 18, no. 1, pp. 14-27, Jan. 2007.
25. W. Yilei, S. Qing, and L. Sheng, "A normalized adaptive training of recurrent neural networks with augmented error gradient," IEEE Trans. Neural Netw., vol. 19, no. 2, pp. 351-356, Feb. 2008.
26. R. Ilin, R. Kozma, and P. J. Werbos, "Beyond feedforward models trained by backpropagation: A practical training tool for a more efficient universal approximator," IEEE Trans. Neural Netw., vol. 19, no. 6, pp. 351-356, Jun. 2008.
27. A. Micheli and A. Sestito, "A new neural network model for contextual processing of graphs," in Neural Nets: 16th Italian Workshop on Neural Nets, WIRN2005, June 8-11, 2005, ser. Lecture Notes in Computer Science, B. Apolloni, M. Marinaro, G. Nicosia, and R. Tagliaferri, Eds. Berlin, Germany: Springer-Verlag, 2006, vol. 3931, pp. 10-17.
28. A. Micheli and A. Sestito, "Dealing with graphs by neural networks," in Proc.Workshop Sub-Symbolic Paradigms for Learning in Structured Domains/16th Eur. Conf. Mach. Learn./9th Eur. Conf. Principles Practice Knowl. Disc. Databases, M. Gori and P. Avesani, Eds., Oct. 2005, pp. 66-75.
29. P. Baldi, S. Brunak, P. Frasconi, G. Pollastri, and G. Soda, "Exploiting the past and the future in protein secondary structure prediction," Bioinformatics, vol. 15, no. 11, pp. 937-946, 1999.
30. P. Baldi and G. Pollastri, "The principled design of large-scale recursive neural network architectures-DAG-RNNs and the protein structure prediction problem," J. Mach. Learn. Res., vol. 4, pp. 575-602, 2003.
31. A. Ceroni, P. Frasconi, and G. Pollastri, "Learning protein secondary structure from sequential and relational data," Neural Netw., vol. 18, no. 8, pp. 1029-1039, 2005.
32. S. Fahlman and C. Lebiere, "The cascade-correlation learning architecture," Carnegie Mellon Univ., Pittsburgh, PA, Tech. Rep. CMU-CS-90-100, Aug. 1990.
33. E. Littmann and H. Ritter, "Learning and generalization in cascade network architectures," Neural Comput., vol. 8, no. 7, pp. 1521-1539, 1996.
34. J. L. Elman, "Finding structure in time," Cogn. Sci., vol. 14, pp. 179-211, 1990.
35. W. Press, S. Teukolsky, W. Vetterling, and B. Flannery, Numerical Recipes in C: The Art of Scientific Computing, 2nd ed. Cambridge, U.K.: Cambridge Univ. Press, 1992.
36. S. Haykin, Neural Networks, A Comprehensive Foundation, 2nd ed. Englewood Cliffs, NJ: Prentice-Hall, 1999.
37. K. Doya, "Recurrent networks: Supervised learning," in The Handbook of Brain Theory and Neural Networks, M. Arbib, Ed. Cambridge, MA: MIT Press, 1995, pp. 796-800.
38. A. Cayley, "On the theory of analytic forms called trees," Philos. Mag., vol. 13, pp. 19-30, 1857.
39. O. Ivanciuc, T. Ivanciuc, and A. Balaban, "Quantitative structure-property relationships for the normal boiling temperatures of acyclic carbonyl compounds," Internet Electron. J. Molecular Design vol. 1, no. 5, pp. 252-268, May 2002.
40. A. Micheli, F. Portera, and A. Sperduti, "A preliminary empirical comparison of recursive neural networks and tree kernel methods on regression tasks for tree structured domains," Neurocomputing, vol. 64, pp. 73-92, Mar. 2005.
41. A. Bianucci, A. Micheli, A. Sperduti, and A. Starita, A Novel Approach to QSPR/QSAR Based on Neural Networks for Structures, H. Cartwright and L. M. Sztandera, Eds. New York: Springer-Verlag, Mar. 2003, pp. 265-296.
42. D. Cherqaoui and D. Villemin, "Use of neural network to determine the boiling point of alkanes," J. Chem. Soc. Faraday Trans., vol. 90, no. 1, pp. 97-102, 1994.
43. A. Passerini and P. Frasconi, "Kernels on prolog ground terms," in Proc. 19th Int. Joint Conf. Artif. Intell., Edinburgh, Scotland, U.K., 2005, pp. 1626-1627.
44. B. Hammer, "Learning with recurrent neural networks," in Lecture Notes in Control and Information Sciences. Berlin, Germany: Springer-Verlag, 2000, vol. 254.
45. S. Menchetti, F. Costa, P. Frasconi, and M. Pontil, "Comparing convolution kernels and recursive neural networks for learning preferences on structured data," in Proc. IAPR - TC3 Int. Workshop Artif. Neural Netw. Pattern Recognit., 2003 [Online]. Available: http://www.dsi.unifi.it/ANNPR/CR/27.pdf
46. S. Menchetti, F. Costa, P. Frasconi, and M. Pontil, "Wide coverage natural language processing using kernel methods and neural networks for structured data," Pattern Recognit. Lett., vol. 26, no. 12, pp. 1896-1906, 2005.
47. G. Adami, P. Avesani, and D. Sona, "Clustering documents into a web directory for bootstrapping a supervised classification," J. Data Knowl. Eng., vol. 54, pp. 301-325, 2005.