Constructing compact and effective graphs for recommender systems via node and edge aggregations

作者：

Highlights：

• We present an aggregation technique for building compact graphs for recommendation.

• We present an algorithm for ranking nodes for recommendation.

• Node and edge aggregation can significantly reduce the graph size.

• Using a compact graph for recommendation does not sacrifice much accuracy.

摘要

•We present an aggregation technique for building compact graphs for recommendation.•We present an algorithm for ranking nodes for recommendation.•Node and edge aggregation can significantly reduce the graph size.•Using a compact graph for recommendation does not sacrifice much accuracy.

论文关键词：Graph,Heterogeneity,Recommendation,Aggregation,Random-walk,Ranking

论文评审过程：Available online 10 December 2014.

论文官网地址：https://doi.org/10.1016/j.eswa.2014.11.062