RecSys for his presentation on SocialMF, a model-based recommender designed to improve ratings-based recommendations for users who have made few ratings but who have friends, or friends of friends, who have provided plenty. Mohsen's previous solution to the same problem was TrustWalker. TrustWalker predicts ratings from a set of item-item similarities and a social graph, where nodes are users and edges represent trust or friendship relationships. The rating for item i for user u is predicted by taking a short random walk on the graph, stopping at some friend-of-a-friend v and returning v's rating for item j, where j is the most similar item to i which v has rated. Closed form expressions for these predictions don't scale at all well, so to make a prediction TrustWalker actually executes the random walk a few times and returns the average rating. On a test set of ratings by 50k users for 100k product reviews from the Epinions website, TrustWalker does indeed show a significant benefit in both coverage and prediction accuracy for cold start users over baseline methods that don't leverage the social graph.
SocialMF is a Bayesian model-based solution to the same problem: latent factors for all users and items are learned jointly from ratings and the social graph. Ratings for cold start users can then be predicted from their learned factors. When tested on the epinions dataset, and a new one of ratings by 1M users for 50k movies crawled from Flixster, SocialMF again does indeed improve the accuracy of predicted ratings for cold start users over latent factor models that don't take the social graph into account.
The model-based approach is elegant and perhaps even scalable: learning time is linear in the number of users, and the paper reports a runtime of 5.5 hours for 1M users. But it lacks the powerful explanations of the simpler system: "recommended for you because your friend xyz likes it".