[GraphX] how to compute only a subset of vertices in the whole graph?
Hi, I just implemented our algorithm(like personalised pagerank) using Pregel api, and it seems works well. But I am thinking of if I can compute only some selected vertexes(hubs), not to do update on every vertex… is it possible to do this using Pregel API? or, more realistically, only hubs can receive messages and compute results in the LAST iteration? since we don't need the final result of non-hub vertices. Best, Yifan LI - To unsubscribe, e-mail: user-unsubscr...@spark.apache.org For additional commands, e-mail: user-h...@spark.apache.org
Re: [GraphX] how to compute only a subset of vertices in the whole graph?
At 2014-08-02 19:04:22 +0200, Yifan LI iamyifa...@gmail.com wrote: But I am thinking of if I can compute only some selected vertexes(hubs), not to do update on every vertex… is it possible to do this using Pregel API? The Pregel API already only runs vprog on vertices that received messages in the previous iteration. Is there some other selection criteria that you'd like to express? Depending on the criteria, the easiest thing might be to move off the Pregel API and write against the lower-level GraphX API. I did this for PageRank recently [1]. or, more realistically, only hubs can receive messages and compute results in the LAST iteration? since we don't need the final result of non-hub vertices. For this it might be easiest to duplicate the Pregel API implementation and special-case the last iteration. Ankur [1] https://github.com/ankurdave/spark/blob/3231a8efadbb45227dea63011c1a8dd856595475/graphx/src/main/scala/org/apache/spark/graphx/impl/GraphImpl.scala#L274 - To unsubscribe, e-mail: user-unsubscr...@spark.apache.org For additional commands, e-mail: user-h...@spark.apache.org
