Multitask feature learning approach for knowledge graph enhanced recommendations with RippleNet

Abstract

Introducing a knowledge graph into a recommender system as auxiliary information can effectively solve the sparse and cold start problems existing in traditional recommender systems. In recent years, many researchers have performed related work. A recommender system with knowledge graph embedding learning characteristics can be combined with a recommender system of the following three forms: one-by-one learning, joint learning, and alternating learning. For current knowledge graph embedding, a deep learning framework only has one embedding mode, which fails to excavate the potential information from the knowledge graph thoroughly. To solve this problem, this paper proposes the Ripp-MKR model, a multitask feature learning approach for knowledge graph enhanced recommendations with RippleNet, which combines joint learning and alternating learning of knowledge graphs and recommender systems. Ripp-MKR is a deep end-to-end framework that utilizes a knowledge graph embedding task to assist recommendation tasks. Similar to the MKR model, in the Ripp-MKR model, two tasks are associated with cross and compress units, which automatically share latent features and learn the high-order interactions among items in recommender systems and entities in the knowledge graph. Additionally, the model borrows ideas from RippleNet and combines the knowledge graph with the historical interaction record of a user’s historically clicked items to represent the user’s characteristics. Through extensive experiments on real-world datasets, we demonstrate that Ripp-MKR achieves substantial gains over state-of-the-art baselines in movie, book, and music recommendations.

MHNF: Multi-hop Heterogeneous Neighborhood information Fusion graph representation learning

“…This lowdimensional vector representation can well maintain the node features, structural characteristics, and semantic information of the original graph, so it can be used for downstream semantic computing tasks, such as node classification, node clustering, and link prediction [1]. Then, it can be applied to knowledge question answering systems [2], recommendation systems [3], social influence analyses [4], and other fields. In the early days, the traditional graph representation learning methods (e.g., DeepWalk [5] and Node2Vec [6]) use different optimization strategies to optimize the hidden matrix of the neural networks and use this matrix as the low-dimensional vector representation of the network nodes.…”

A Survey on Knowledge Graph-Based Recommender Systems

“…serve as edges. After obtaining the embeddings of entities in the graph, the user's preference can be calculated with Equation 1, or by further KDD 2016 entity2rec [66] RecSys 2017 ECFKG [67] Algorithms 2018 SHINE [68] WSDM 2018 DKN [48] WWW 2018 KSR [44] SIGIR 2018 CFKG [13] SIGIR 2018 KTGAN [69] ICDM 2018 KTUP [70] WWW 2019 MKR [45] WWW 2019 DKFM [71] WWW 2019 SED [72] WWW 2019 RCF [73] SIGIR 2019 BEM [74] CIKM 2019 Hete-MF [75] IJCAI 2013 HeteRec [76] RecSys 2013 HeteRec p [77] WSDM 2014 Hete-CF [78] ICDM 2014 SemRec [79] CIKM 2015 ProPPR [80] RecSys 2016 FMG [3] KDD 2017 MCRec [1] KDD 2018 RKGE [81] RecSys 2018 HERec [82] TKDE 2019 KPRN [83] AAAI 2019 RuleRec [84] WWW 2019 PGPR [85] SIGIR 2019 EIUM [86] MM 2019 Ekar [87] arXiv 2019 RippleNet [14] CIKM 2018 RippleNet-agg [88] TOIS 2019 KGCN [89] WWW 2019 KGAT [90] KDD 2019 KGCN-LS [91] KDD 2019 AKUPM [92] KDD 2019 KNI [93] KDD 2019 IntentGC [94] KDD 2019 RCoLM [95] IEEE Access 2019 AKGE [96] arXiv 2019 considering the relation embedding in the graph via…”

“…Hence, embeddings of items and preferences can be enriched by transferring knowledge of entities, relations and preference in each module under the framework of KTUP. Meanwhile, Wang et al [45] proposed MKR, which consists of a recommendation module and a KGE module. The former learns latent representation for users and items, while the latter learns representation for item associated entities with the semantic matching KGE model.…”

“…Recommender systems have been applied in many domains, including movies [2], [44], music [1], [45], POIs [46], [47], news [14], [48], education [49], [50], etc. The recommendation task is to recommend one or a series of unobserved items to a given user, and it can be formulated into the following steps.…”

Untitled

“…Thus the refinement of user and item embedding are pulled together. Besides, Wang et al proposed Ripp-MKR [37], a deep framework that combined the main idea of Ripplenet and MKR. The framework enriches the recommendation system with users' historical clicked-items, and combined with knowledge graph information.…”