This shows you the differences between two versions of the page.

Link to this comparison view

Next revision
Previous revision
user_centric_recommendations [2017/09/25 12:45] external edit
user_centric_recommendations [2018/09/07 13:15] (current)
Line 139: Line 139:
 https://​github.com/​Leavingseason/​OpenLearning4DeepRecsys https://​github.com/​Leavingseason/​OpenLearning4DeepRecsys
 +https://​arxiv.org/​abs/​1706.02263 Graph Convolutional Matrix Completion
 +We consider matrix completion for recommender systems from the point of view of link prediction on graphs. Interaction data such as movie ratings can be represented by a bipartite user-item graph with labeled edges denoting observed ratings. Building on recent progress in deep learning on graph-structured data, we propose a graph auto-encoder framework based on differentiable message passing on the bipartite interaction graph. Our model shows competitive performance on standard collaborative filtering benchmarks. In settings where complimentary feature information or structured data such as a social network is available, our framework outperforms recent state-of-the-art methods.
 +https://​engineering.pinterest.com/​sites/​engineering/​files/​article/​fields/​field_image/​human-curation-convnets%20%281%29.pdf Human Curation and Convnets: Powering
 +Item-to-Item Recommendations on Pinterest
 +https://​medium.com/​@Pinterest_Engineering/​pinsage-a-new-graph-convolutional-neural-network-for-web-scale-recommender-systems-88795a107f48 PinSage: A New Graph Convolutional Neural Network for Web-Scale Recommender Systems
 +Unlike Euclidean spaces, Hyperbolic spaces are intrinsically equipped to handle hierarchical structure, encouraged by its property of exponentially increasing distances away from origin. We propose HyperBPR (Hyperbolic Bayesian Personalized Ranking), a conceptually simple but highly effective model for the task at hand. Our proposed HyperBPR not only outperforms their Euclidean counterparts,​ but also achieves state-of-the-art performance on multiple benchmark datasets, demonstrating the effectiveness of personalized recommendation in Hyperbolic space.