Re: Link Prediction with Giraph
You could also approach the problem from a statistical point of view and sample from an inferred distribution of the links (which vertices they link). The prior distribution probably won't be as interesting as the conditional distributions you are most likely interested in...that is, start with some constraint (i.e. list of vertices you want to predict on), and then condition on the constraint. -David On Thu, Oct 31, 2013 at 7:26 AM, Pascal Jäger pas...@pascaljaeger.dewrote: Hi, Does anyone happen to know a paper about link prediction using a pregel like framework like Giraph? Or has someone an idea about how link prediction could be accomplished with Giraph? Any input is highly appreciated :) Thanks Pascal
Re: Link Prediction with Giraph
I would assume that it depends on your data. A graph is a very general structure, and it is difficult to attack this problem in general. The most obvious one is transitive closure (if A is connected to B and B to C then A could be conntected to C). The triangle counting example in our codebase (although the name is misleading) is based on these kinds of assumptions. On Thu, Oct 31, 2013 at 1:26 PM, Pascal Jäger pas...@pascaljaeger.dewrote: Hi, Does anyone happen to know a paper about link prediction using a pregel like framework like Giraph? Or has someone an idea about how link prediction could be accomplished with Giraph? Any input is highly appreciated :) Thanks Pascal -- Claudio Martella claudio.marte...@gmail.com
Re: Link Prediction with Giraph
Hi, You can look at the Facebook Link Prediction Challenge on Kaggle where you have to suggest links in a social Network. The link for the forum for the contest is: http://www.kaggle.com/c/FacebookRecruiting/forums It has a lot of interesting approaches. One of them can be found at the link below: http://blog.echen.me/2012/07/31/edge-prediction-in-a-social-graph-my-solution-to-facebooks-user-recommendation-contest-on-kaggle/ I am currently looking at a paper : Supervised Random Walks for Predicting Links in social networks. http://cs.stanford.edu/people/jure/pubs/linkpred-wsdm11.pdf I don't know If I can implement it in giraph. I will read the paper completely and try to. Will keep you posted. Thanks, Ameya On Thu, Oct 31, 2013 at 5:55 AM, Claudio Martella claudio.marte...@gmail.com wrote: I would assume that it depends on your data. A graph is a very general structure, and it is difficult to attack this problem in general. The most obvious one is transitive closure (if A is connected to B and B to C then A could be conntected to C). The triangle counting example in our codebase (although the name is misleading) is based on these kinds of assumptions. On Thu, Oct 31, 2013 at 1:26 PM, Pascal Jäger pas...@pascaljaeger.dewrote: Hi, Does anyone happen to know a paper about link prediction using a pregel like framework like Giraph? Or has someone an idea about how link prediction could be accomplished with Giraph? Any input is highly appreciated :) Thanks Pascal -- Claudio Martella claudio.marte...@gmail.com
