Knowledge Graph Convolutional Networks for Recommender Systems

Abstract

To alleviate sparsity and cold start problem of collaborative filtering based recommender systems, researchers and engineers usually collect attributes of users and items, and design delicate algorithms to exploit these additional information. In general, the attributes are not isolated but connected with each other, which forms a knowledge graph (KG). In this paper, we propose Knowledge Graph Convolutional Networks (KGCN), an end-to-end framework that captures inter-item relatedness effectively by mining their associated attributes on the KG. To automatically discover both high-order structure information and semantic information of the KG, we sample from the neighbors for each entity in the KG as their receptive field, then combine neighborhood information with bias when calculating the representation of a given entity. The receptive field can be extended to multiple hops away to model high-order proximity information and capture users' potential long-distance interests. Moreover, we implement the proposed KGCN in a minibatch fashion, which enables our model to operate on large datasets and KGs. We apply the proposed model to three datasets about movie, book, and music recommendation, and experiment results demonstrate that our approach outperforms strong recommender baselines.

Knowledge-aware Graph Neural Networks with Label Smoothness Regularization for Recommender Systems

“…The results of R@10 in Last.FM dataset are plotted in Figure 5. It is clear that the performance of KGNN-LS with a non-zero λ is better than λ = 0 (the case of Wang et al [28]), which justifies our claim that LS regularization can assist learning the edge weights in a KG and achieve better generalization in recommender systems. But note that a too large λ is less favorable, since it overwhelms the overall loss and misleads the direction of gradients.…”

“…Path-based methods make use of KGs in a more intuitive way, but they rely heavily on manually designed metapaths/meta-graphs, which are hard to tune in practice. (3) Hybrid methods [18,24,28] combine the above two categories and learn user/item embeddings by exploiting the structure of KGs. Our proposed model can be seen as an instance of hybrid methods.…”

“…In this paper, we develop Knowledge-aware Graph Neural Networks with Label Smoothness regularization (KGNN-LS) that extends GNNs architecture to knowledge graphs to simultaneously capture semantic relationships between the items as well as personalized user preferences and interests. To account for the relational heterogeneity in KGs, similar to [28], we use a trainable and personalized relation scoring function that transforms the KG into a user-specific weighted graph, which characterizes both the semantic information of the KG as well as user's personalized interests. For example, in the movie recommendation setting the relation scoring function could learn that a given user really cares about "director" relation between movies and persons, while somebody else may care more about the "lead actor" relation.…”

Graph neural news recommendation with long-term and short-term interest modeling

“…With the constructed heterogeneous user-news-topic graph, we then apply GNN [31,32,33] to capture high-order relationships between users and news by propagating the embeddings through it.…”

Quaternion-Based Knowledge Graph Network for Recommendation

“…Obviously, incorporating KG provides more structural information for RS to better dig out the relational information between users and items, which helps to improve the accuracy of recommendation. In the past few years, many research efforts have been devoted to KG in RS [41,43,44], so as to learn effective user/item embeddings and user preference by using KG's structural information. To name a few, RippleNet [41] first proposes a preference propagation mechanism where users' interests are explicitly propagated along the paths in KG.…”