Yingyi Zhang
ABSTRACT
Large-scale e-commercial platforms usually contain multiple business fields, which require industrial algorithms to characterize user intents across multiple domains. Numerous efforts have been made in user multi-domain intent modeling to achieve state-of-the-art performance. However, existing methods mainly focus on the domains having rich user information, which makes implementation to domains with sparse or rare user behavior meet with mixed success. Hence, in this paper, we propose a novel method named Meta-generator enhanced multi-Domain model (MetaDomain) to address the above issue. MetaDomain mainly includes two steps, 1) users’ multi-domain intent representation and 2) users’ multi-domain intent fusion. Specifically, in users’ multi-domain intent representation, we use the gradient information from a domain intent extractor to train the domain intent meta-generator, where the domain intent extractor has the input of users’ sequence feature and domain meta-generator has the input of users’ basic feature, hence the capability of generating users’ intent with sparse behavior. Afterward, in users’ multi-domain intent fusion, a domain graph is used to represent the high-order multi-domain connectivity. Extensive experiments have been carried out under a real-world industrial platform named Meituan. Both offline and rigorous online A/B tests under the billion-level data scale demonstrate the superiority of the proposed MetaDomain method over the state-of-the-art baselines. Furthermore comparing with the method using multi-domain sequence features, MetaDomain can reduce the serving latency by 20%. Currently, MetaDomain has been deployed in Meituan one of the largest worldwide Online-to-Offline(O2O) platforms.
Supplemental Material
- Djork-Arné Clevert, Thomas Unterthiner, and Sepp Hochreiter. 2016. Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs). In 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http://arxiv.org/abs/1511.07289Google Scholar
- John Duchi, Elad Hazan, and Yoram Singer. 2011. Adaptive subgradient methods for online learning and stochastic optimization.Journal of machine learning research 12, 7 (2011).Google Scholar
- Xiaobo Hao, Yudan Liu, Ruobing Xie, Kaikai Ge, Linyao Tang, Xu Zhang, and Leyu Lin. 2021. Adversarial Feature Translation for Multi-domain Recommendation. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 2964–2973.Google ScholarDigital Library
- Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016).Google Scholar
- Jiaqi Ma, Zhe Zhao, Xinyang Yi, Jilin Chen, Lichan Hong, and Ed H Chi. 2018. Modeling task relationships in multi-task learning with multi-gate mixture-of-experts. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 1930–1939.Google ScholarDigital Library
- Weizhi Ma, Min Zhang, Chenyang Wang, Cheng Luo, Yiqun Liu, and Shaoping Ma. 2018. Your Tweets Reveal What You Like: Introducing Cross-media Content Information into Multi-domain Recommendation. In IJCAI. 3484–3490.Google Scholar
- Xiao Ma, Liqin Zhao, Guan Huang, Zhi Wang, Zelin Hu, Xiaoqiang Zhu, and Kun Gai. 2018. Entire space multi-task model: An effective approach for estimating post-click conversion rate. In The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval. 1137–1140.Google ScholarDigital Library
- Xiang-Rong Sheng, Liqin Zhao, Guorui Zhou, Xinyao Ding, Binding Dai, Qiang Luo, Siran Yang, Jingshan Lv, Chi Zhang, Hongbo Deng, 2021. One Model to Serve All: Star Topology Adaptive Recommender for Multi-Domain CTR Prediction. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management. 4104–4113.Google ScholarDigital Library
- Hongyan Tang, Junning Liu, Ming Zhao, and Xudong Gong. 2020. Progressive layered extraction (ple): A novel multi-task learning (mtl) model for personalized recommendations. In Fourteenth ACM Conference on Recommender Systems. 269–278.Google ScholarDigital Library
- Ruobing Xie, Zhijie Qiu, Jun Rao, Yi Liu, Bo Zhang, and Leyu Lin. 2020. Internal and Contextual Attention Network for Cold-start Multi-channel Matching in Recommendation. In IJCAI. 2732–2738.Google Scholar
- Yu Zhang, Bin Cao, and Dit-Yan Yeung. 2012. Multi-domain collaborative filtering. arXiv preprint arXiv:1203.3535 (2012).Google Scholar
- Guorui Zhou, Xiaoqiang Zhu, Chenru Song, Ying Fan, Han Zhu, Xiao Ma, Yanghui Yan, Junqi Jin, Han Li, and Kun Gai. 2018. Deep interest network for click-through rate prediction. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining. 1059–1068.Google ScholarDigital Library
Index Terms
- Meta-Generator Enhanced Multi-Domain Recommendation
Recommendations
Adaptive Domain Interest Network for Multi-domain Recommendation
CIKM '22: Proceedings of the 31st ACM International Conference on Information & Knowledge ManagementIndustrial recommender systems usually hold data from multiple business scenarios and are expected to provide recommendation services for these scenarios simultaneously. In the retrieval step, the topK high-quality items selected from a large number of ...
Active learning in multi-domain collaborative filtering recommender systems
SAC '18: Proceedings of the 33rd Annual ACM Symposium on Applied ComputingThe lack of information is an acute challenge in most recommender systems, especially for the collaborative filtering algorithms which utilize user-item rating matrix as the only source of information. Active learning can be used to remedy this problem ...
Cross-domain Recommendation with Probabilistic Knowledge Transfer
Neural Information ProcessingAbstractRecommender systems have drawn great attention from both academic and practical area. One challenging and common problem in many recommendation methods is data sparsity, due to the limited number of observed user interaction with the products/...
Comments