Affiliation:
1. Tongji University, China
2. Pinterest, United States
3. Squirrel AI Learning, United States
4. Middlesex School, United States
5. JD.COM, China
Abstract
Social recommendation based on social network has achieved great success in improving the performance of the recommendation system. Since social network (user-user relations) and user-item interactions are both naturally represented as graph-structured data, Graph Neural Networks (GNNs) have thus been widely applied for social recommendation. Despite the superior performance of existing GNNs-based methods, there are still several severe limitations: (i) Few existing GNNs-based methods have considered a single heterogeneous global graph which takes into account user-user relations, user-item interactions, and item-item similarities simultaneously. That may lead to a lack of complex semantic information and rich topological information when encoding users and items based on GNN. (ii) Furthermore, previous methods tend to overlook the reliability of the original user-user relations which may be noisy and incomplete. (iii) More importantly, the item-item connections established by a few existing methods merely using initial rating attributes or extra attributes (such as category) of items, may be inaccurate or sub-optimal with respect to social recommendation. In order to address these issues, we propose an end-to-end heterogeneous global graph learning framework, namely
Graph Learning Augmented Heterogeneous Graph Neural Network
(GL-HGNN) for social recommendation. GL-HGNN aims to learn a heterogeneous global graph that makes full use of user-user relations, user-item interactions and item-item similarities in a unified perspective. To this end, we design a Graph Learner (GL) method to learn and optimize user-user and item-item connections separately. Moreover, we employ a Heterogeneous Graph Neural Network (HGNN) to capture the high-order complex semantic relations from our learned heterogeneous global graph. To scale up the computation of graph learning, we further present the Anchor-based Graph Learner (AGL) to reduce computational complexity. Extensive experiments on four real-world datasets demonstrate the effectiveness of our model.
Funder
National Nature Science Foundation of China
Natural Science Foundation of Shanghai
Shanghai Science and Technology Plan Project
Technology research plan project of Ministry of Public and Security
Publisher
Association for Computing Machinery (ACM)
Reference69 articles.
1. Mikhail Belkin and Partha Niyogi. 2001. Laplacian eigenmaps and spectral techniques for embedding and clustering. In Advances in Neural Information Processing Systems, Vol. 14. 585–591.
2. Rianne van den Berg, Thomas N. Kipf, and Max Welling. 2017. Graph convolutional matrix completion. In ICLR.
3. Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences
4. Social boosted recommendation with folded bipartite network embedding;Chen Hongxu;IEEE Transactions on Knowledge and Data Engineering,2020
5. Topological relational learning on graphs;Chen Yuzhou;Advances in Neural Information Processing Systems,2021