Dingxian Wang

TL;DR: Wang et al. as mentioned in this paper propose a knowledge-aware path recurrent network (KPRN) to generate path representations by composing the semantics of both entities and relations, which allows effective reasoning on paths to infer the underlying rationale of a user-item interaction.

TL;DR: A new model named Knowledge-aware Path Recurrent Network (KPRN) is contributed to exploit knowledge graph for recommendation to allow effective reasoning on paths to infer the underlying rationale of a user-item interaction.

TL;DR: Wang et al. as mentioned in this paper explored intents behind a user-item interaction by using auxiliary item knowledge, and proposed a new model, Knowledge Graph-based Intent Network (KGIN), which model each intent as an attentive combination of KG relations, encouraging the independence of different intents for better model capability and interpretability.

TL;DR: Huang et al. as discussed by the authors proposed a knowledge graph-based intent network (KGIN) to model each intent as an attentive combination of KG relations, encouraging the independence of different intents.

TL;DR: BiRank as mentioned in this paper is a ranking algorithm for bipartite graphs, which iteratively assigns scores to vertices and finally converges to a unique stationary ranking, which smooths the graph under the guidance of the query vector.