The large amount of Semantic Web data and its fast growth pose a significant computational challenge in performing efficient and scalable reasoning. On a large scale, the resources of single machines are no longer sufficient and we are required to distribute the process to improve performance. The article that we attach to our submission  tackles this problem proposing a methodology to perform inference materializing every possible consequence using the MapReduce programming model. We introduce a number of optimizations to address the issues that a naive implementation would raise and to improve the overall performance. We have implemented the presented techniques in a prototype called WebPIE and the evaluation shows that our approach is able to perform complex inference based on the OWL language over a very large input of about 100 billion triples. To the best of our knowledge, it is the only approach that demonstrates complex inference over an input of a hundred billion of triples.
|Journal||Belgian/Netherlands Artificial Intelligence Conference|
|Publication status||Published - 2012|