Collaborative Filtering With Network Representation Learning for Citation Recommendation

Citation recommendation plays an important role in the context of scholarly big data, where finding relevant papers has become more difficult because information overload. Applying traditional collaborative filtering (CF) to citation is challenging due cold start problem and lack paper ratings. To address these challenges, this article, we propose a with network representation learning framework for recommendation, namely CNCRec, which hybrid user-based CF considering both content topology. It aims at recommending citations heterogeneous academic networks. CNCRec creates rating matrix based on attributed learning, attributes are topics extracted from text information. Meanwhile, learned representations collaboration utilized improve selection nearest neighbors. By harnessing power able make full use whole topology compared previous context-aware network-based models. Extensive experiments DBLP APS datasets show that proposed method outperforms state-of-the-art methods terms precision, recall, MRR (Mean Reciprocal Rank). Moreover, can better solve data sparsity other CF-based baselines.