Two connectionist models for graph processing: An experimental comparison on relational data

In this paper, two recently developed connectionist models for learning from relational or graph-structured data, i.e. Relational Neural Networks (RelNNs) and Graph Neural Networks (GNNs), are compared. We first introduce a general paradigm for connectionist learning from graphs that covers both approaches, and situate the approaches in this general paradigm. This gives a first view on how they relate to each other. As RelNNs have been developed with learning aggregate functions in mind, we compare them to GNNs for this specific task. Next, we compare both with other relational learners on a number of benchmark problems (mutagenesis, biodegradability). The results are promising and suggest that RelNNs and GNNs can be a viable approach for learning on relational data. They also point out a number of differences in behavior between both approaches that deserve further study.

[1]  Ah Chung Tsoi,et al.  A self-organizing map for adaptive processing of structured data , 2003, IEEE Trans. Neural Networks.

[2]  Alessandro Sperduti,et al.  Supervised neural networks for the classification of structures , 1997, IEEE Trans. Neural Networks.

[3]  Luís B. Almeida,et al.  A learning rule for asynchronous perceptrons with feedback in a combinatorial environment , 1990 .

[4]  A. Debnath,et al.  Structure-activity relationship of mutagenic aromatic and heteroaromatic nitro compounds. Correlation with molecular orbital energies and hydrophobicity. , 1991, Journal of medicinal chemistry.

[5]  Luc De Raedt,et al.  Using Logical Decision Trees for Clustering , 1997, ILP.

[6]  Saso Dzeroski,et al.  Experiments in Predicting Biodegradability , 1999, ILP.

[7]  Hendrik Blockeel,et al.  Classifying Relational Data with Neural Networks , 2005, ILP.

[8]  Pineda,et al.  Generalization of back-propagation to recurrent neural networks. , 1987, Physical review letters.

[9]  Stephen Muggleton,et al.  Is Mutagenesis still challenging ? , 2005 .

[10]  F. Scarselli,et al.  A new model for learning in graph domains , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[11]  Alessandro Sperduti,et al.  A general framework for adaptive processing of data structures , 1998, IEEE Trans. Neural Networks.

[12]  Risi Kondor,et al.  Diffusion kernels on graphs and other discrete structures , 2002, ICML 2002.

[13]  Giovanni Soda,et al.  Logo Recognition by Recursive Neural Networks , 1997, GREC.

[14]  Maurice Bruynooghe,et al.  Aggregation versus selection bias, and relational neural networks , 2003 .

[15]  Franco Scarselli,et al.  Recursive neural networks for processing graphs with labelled edges: theory and applications , 2005, Neural Networks.

[16]  W. A. Kirk,et al.  An Introduction to Metric Spaces and Fixed Point Theory , 2001 .