ABSTRACT
Recently, graph neural network (GNN) approaches have received huge interests in recommendation tasks due to their ability of learning more effective user and item representations. However, existing GNN-based recommendation models cannot support real-time recommendation where the model keeps its freshness by continuously training the streaming data that users produced, leading to negative impact on recommendation performance. To fully support graph-enhanced large-scale recommendation in real-time scenarios, a deep graph learning system is required to dynamically store the streaming data as a graph structure and enable the development of any GNN model incorporated with the capabilities of real-time training and online inference. However, such requirements rule out existing deep graph learning solutions. In this paper, we propose a new deep graph learning system called PlatoGL, where (1) an effective block-based graph storage is designed with non-trivial insertion/deletion mechanism for updating the graph topology in-milliseconds, (2) a non-trivial multi-blocks neighbour sampling method is proposed for efficient graph query, and (3) a cache technique is exploited to improve the storage stability. We have deployed PlatoGL in Wechat, and leveraged its capability in various content recommendation scenarios including live-streaming, article and micro-video. Comprehensive experiments on both deployment performance and benchmark performance~(w.r.t. its key features) demonstrate its effectiveness and scalability. One real-time GNN-based model, developed with PlatoGL, now serves the major online traffic in WeChat live-streaming recommendation scenario.
Supplemental Material
- K. Bhatia, K. Dahiya, H. Jain, P. Kar, A. Mittal, Y. Prabhu, and M. Varma. 2016. The extreme classification repository: Multi-label datasets and code. http://manikvarma.org/downloads/XC/XMLRepository.htmlGoogle Scholar
- H. Cai, V. W Zheng, and K. C.-C. Chang. 2018. A comprehensive survey of graph embedding: Problems, techniques, and applications. TKDE 30, 9 (2018), 1616--1637.Google ScholarDigital Library
- B. Chandramouli, J. J. Levandoski, A. Eldawy, and M. F. Mokbel. 2011. Streamrec: a real-time recommender system. In SIGMOD. 1243--1246.Google Scholar
- M. Chen, A. Beutel, P. Covington, S. Jain, F. Belletti, and E. H Chi. 2019. Top-k off-policy correction for a REINFORCE recommender system. In WSDM. 456--464.Google Scholar
- P. Covington, J. Adams, and E. Sargin. 2016. Deep neural networks for youtube recommendations. In Recsys. 191--198.Google Scholar
- Y. Dong, N. V Chawla, and A. Swami. 2017. metapath2vec: Scalable representation learning for heterogeneous networks. In SIGKDD. 135--144.Google Scholar
- S. Fan, J. Zhu, X. Han, C. Shi, L. Hu, B. Ma, and Y. Li. 2019. Metapath-guided heterogeneous graph neural network for intent recommendation. In KDD. 2478--2486.Google Scholar
- I. Gama, J.and Žliobaite, A. Bifet, M. Pechenizkiy, and A. Bouchachia. 2014. A survey on concept drift adaptation. ACM computing surveys (CSUR) 46, 4 (2014), 1--37.Google Scholar
- C. Gao, Y. Zheng, N. Li, Y. Li, Y. Qin, J. Piao, Y. Quan, J. Chang, D. Jin, X. He, et al. 2021. Graph neural networks for recommender systems: Challenges, methods, and directions. arXiv preprint (2021).Google Scholar
- J. Gilmer, S. S. Schoenholz, P. F. Riley, O. Vinyals, and G. E. Dahl. 2017. Neural message passing for Quantum chemistry. In ICML. 1263--1272.Google Scholar
- P. Goyal and E. Ferrara. 2018. Graph embedding techniques, applications, and performance: A survey. Knowledge-Based Systems 151 (2018), 78--94.Google ScholarCross Ref
- W. L. Hamilton, R. Ying, and J. Leskovec. 2017. Inductive representation learning on large graphs. In NIPS. 1025--1035.Google Scholar
- W. L Hamilton, R. Ying, and J. Leskovec. 2017. Representation learning on graphs: Methods and applications. arXiv. (2017).Google Scholar
- X. He, K. Deng, X. Wang, Y. Li, Y. Zhang, and M. Wang. 2020. Lightgcn: Simplifying and powering graph convolution network for recommendation. In SIGIR. 639--648.Google ScholarDigital Library
- Y. Huang, B. Cui, W. Zhang, J. Jiang, and Y. Xu. 2015. Tencentrec: Real-time stream recommendation in practice. In SIGMOD. 227--238.Google ScholarDigital Library
- Z. Huang, M. Tao, and B. Zhang. 2021. Deep Inclusion Relation-aware Network for User Response Prediction at Fliggy. In KDD. 3059--3067.Google Scholar
- Alibaba Inc. 2020. Euler Framework for Deep Graph Learning. https://github.com/alibaba/euler.Google Scholar
- Tencent Inc. 2019. PlatoGraph Framework for Graph Algorithms. https://github.com/Tencent/plato.Google Scholar
- G. Karypis and V. Kumar. 1995. METIS--unstructured graph partitioning and sparse matrix ordering system, version 2.0. (1995).Google Scholar
- T. N Kipf and M. Welling. 2017. Semi-supervised classification with graph convolutional networks. ICLR (2017).Google Scholar
- C. Lei, Y. Liu, L. Zhang, G. Wang, H. Tang, H. Li, and C. Miao. 2021. SEMI: A Sequential Multi-Modal Information Transfer Network for E-Commerce Micro- Video Recommendations. In KDD. 3161--3171.Google Scholar
- A. Lerer, L. Wu, J. Shen, T. Lacroix, L. Wehrstedt, A. Bose, and A. Peysakhovich. 2019. Pytorch-biggraph: A large scale graph embedding system. Proceedings of Machine Learning and Systems 1 (2019), 120--131.Google Scholar
- W. Lin. 2019. Distributed algorithms for fully personalized pagerank on large graphs. In WWW. 1084--1094.Google Scholar
- D. Liu, J. Lian, Z. Liu, X. Wang, G. Sun, and X. Xie. 2021. Reinforced Anchor Knowledge Graph Generation for News Recommendation Reasoning. In KDD. 1055--1065.Google Scholar
- J. Rappaz, J. McAuley, and K. Aberer. 2021. Recommendation on Live-Streaming Platforms: Dynamic Availability and Repeat Consumption. In Recsys. 390--399.Google Scholar
- C. Shi, B. Hu, W. X. Zhao, and S Y. Philip. 2018. Heterogeneous information network embedding for recommendation. TKDE 31, 2 (2018), 357--370.Google ScholarDigital Library
- C. Sima, Y. Fu, M.-K. Sit, L. Guo, X. Gong, F. Lin, J. Wu, Y. Li, H. Rong, P.-L. Aublin, et al. 2022. Ekko: A {Large-Scale} Deep Learning Recommender System with Low-Latency Model Update. In OSDI. 821--839.Google Scholar
- P. Velickovic, G. Cucurull, A. Casanova, A. Romero, P. Liò, and Y. Bengio. 2018. Graph Attention Networks. In ICLR.Google Scholar
- M. Wang, Y. Lin, G. Lin, K. Yang, and X. Wu. 2020. M2GRL: A multi-task multi-view graph representation learning framework for web-scale recommender systems. In KDD. 2349--2358.Google Scholar
- X. Wang, X. He, M. Wang, F. Feng, and T.-S. Chua. 2019. Neural graph collaborative filtering. In SIGIR. 165--174.Google Scholar
- S. Wu, F. Sun, W. Zhang, and B. Cui. 2020. Graph neural networks in recommender systems: a survey. arXiv preprint (2020).Google Scholar
- Z. Wu, S. Pan, F. Chen, G. Long, C. Zhang, and S. Y. Philip. 2020. A comprehensive survey on graph neural networks. TNNLS 32, 1 (2020), 4--24.Google ScholarCross Ref
- M. Xie, K. Ren, Y. Lu, G. Yang, Q. Xu, B. Wu, J. Lin, H. Ao, W. Xu, and J. Shu. 2020. Kraken: memory-efficient continual learning for large-scale real-time recommendations. In SC. 1--17.Google Scholar
- J. Yang, X. Yi, D. Cheng, L. Hong, Y. Li, S. Wang, T. Xu, and E. H Chi. 2020. Mixed negative sampling for learning two-tower neural networks in recommendations. In Companion Proceedings of the Web Conference 2020. 441--447.Google ScholarDigital Library
- K. Yang, M. Zhang, K. Chen, X. Ma, Y. Bai, and Y. Jiang. 2019. Knightking: a fast distributed graph random walk engine. In SOSP. 524--537.Google Scholar
- X. Yi, J. Yang, L. Hong, D. Z. Cheng, L. Heldt, A. Kumthekar, Z. Zhao, L. Wei, and E. H Chi. 2019. Sampling-bias-corrected neural modeling for large corpus item recommendations. In Recsys. 269--277.Google Scholar
- R. Ying, R. He, K. Chen, P. Eksombatchai, W. L Hamilton, and J. Leskovec. 2018. Graph convolutional neural networks for web-scale recommender systems. In KDD. 974--983.Google Scholar
- S. Yu, Z. Jiang, D. Chen, S. Feng, D. Li, Q. Liu, and J. Yi. 2021. Leveraging Tripartite Interaction Information from Live Stream E-Commerce for Improving Product Recommendation. In KDD. 3886--3894.Google Scholar
- Z. Zhao, L. Hong, L. Wei, J. Chen, A. Nath, S. Andrews, A. Kumthekar, M. Sathiamoorthy, Xinyang Yi, and E. H Chi. 2019. Recommending what video to watch next: a multitask ranking system. In Recsys. 43--51.Google Scholar
- D. Zheng, C. Ma, M. Wang, J. Zhou, Q. Su, X. Song, Q. Gan, Z. Zhang, and G. Karypis. 2020. Distdgl: distributed graph neural network training for billion-scale graphs. In IEEE IA3.Google Scholar
- G. Zheng, F. Zhang, Z. Zheng, Y. Xiang, N. J. Yuan, X. Xie, and Z. Li. 2018. DRN: A deep reinforcement learning framework for news recommendation. In WWW. 167--176.Google ScholarDigital Library
- J. Zheng, Q. Lin, J. Xu, C. Wei, C. Zeng, P. Yang, and Y. Zhang. 2017. PaxosStore: high-availability storage made practical in WeChat. VLDB Endowment (2017).Google Scholar
- J. Zheng, Q. Ma, H. Gu, and Z. Zheng. 2021. Multi-view Denoising Graph Auto-Encoders on Heterogeneous Information Networks for Cold-start Recommendation. In KDD. 2338--2348.Google Scholar
- R. Zhu, K. Zhao, H. Yang, W. Lin, C. Zhou, B. Ai, Y. Li, and J. Zhou. 2019. AliGraph: a comprehensive graph neural network platform. VLDB Endowment (2019).Google Scholar
Index Terms
- PlatoGL: Effective and Scalable Deep Graph Learning System for Graph-enhanced Real-Time Recommendation
Recommendations
Course Recommendation Based on Graph Convolutional Neural Network
Advances and Trends in Artificial Intelligence. Theory and ApplicationsAbstractSelecting the right learning content according to learners’ learning abilities and interests is the first and most important factor in achieving good learning performance. Based on the similarity between the course rating data in the Collaborative ...
Exploiting Group Information for Personalized Recommendation with Graph Neural Networks
Personalized recommendation has become more and more important for users to quickly find relevant items. The key issue of the recommender system is how to model user preferences. Previous work mostly employed user historical data to learn users’ ...
User-Oriented Interest Representation on Knowledge Graph for Long-Tail Recommendation
Advanced Data Mining and ApplicationsAbstractGraph neural networks have demonstrated impressive performance in the field of recommender systems. However, existing graph neural network recommendation approaches are proficient in capturing users’ mainstream interests and recommending popular ...
Comments