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

@inproceedings{Uwents2006TwoCM,
  title={Two connectionist models for graph processing: An experimental comparison on relational data},
  author={Werner Uwents and Gabriele Monfardini and Hendrik Blockeel and Franco Scarselli and Marco Gori},
  year={2006}
}
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… CONTINUE READING

Similar Papers

Loading similar papers…