Fusing Diversity in Recommendations in Heterogeneous Information Networks.

In the past, hybrid recommender systems have shown the power of exploiting relationships amongst objects which directly or indirectly effect the recommendation task. However, the effect of all relations is not equal, and choosing their right balance for a recommendation problem at hand is non-trivial. We model these interactions using a Heterogeneous Information Network, and propose a systematic framework for learning their influence weights for a given recommendation task. Further, we address the issue of redundant results, which is very much prevalent in recommender systems. To alleviate redundancy in recommendations we use Vertex Reinforced Random Walk (a non-Markovian random walk) over a heterogeneous graph. It works by boosting the transitions to the influential nodes, while simultaneously shrinking the weights of others. This helps in discouraging recommendation of multiple influential nodes which lie in close proximity of each other, thus ensuring diversity. Finally, we demonstrate the effectiveness of our approach by experimenting on real world datasets. We find that, with the weights of relations learned using the proposed non-Markovian random walk based framework, the results consistently improve over the baselines.