2000 character limit reached
Cross Domain LifeLong Sequential Modeling for Online Click-Through Rate Prediction
Published 11 Dec 2023 in cs.IR | (2312.06424v2)
Abstract: Deep neural networks (DNNs) that incorporated lifelong sequential modeling (LSM) have brought great success to recommendation systems in various social media platforms. While continuous improvements have been made in domain-specific LSM, limited work has been done in cross-domain LSM, which considers modeling of lifelong sequences of both target domain and source domain. In this paper, we propose Lifelong Cross Network (LCN) to incorporate cross-domain LSM to improve the click-through rate (CTR) prediction in the target domain. The proposed LCN contains a LifeLong Attention Pyramid (LAP) module that comprises of three levels of cascaded attentions to effectively extract interest representations with respect to the candidate item from lifelong sequences. We also propose Cross Representation Production (CRP) module to enforce additional supervision on the learning and alignment of cross-domain representations so that they can be better reused on learning of the CTR prediction in the target domain. We conducted extensive experiments on WeChat Channels industrial dataset as well as on benchmark dataset. Results have revealed that the proposed LCN outperforms existing work in terms of both prediction accuracy and online performance.
- Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467 (2016).
- Contrastive Cross-Domain Sequential Recommendation. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management. 138–147.
- Cross-Domain Recommendation to Cold-Start Users via Variational Information Bottleneck. arXiv:2203.16863 [cs.IR]
- Sampling Is All You Need on Modeling Long-Term User Behaviors for CTR Prediction. arXiv:2205.10249 [cs.IR]
- TWIN: TWo-stage Interest Network for Lifelong User Behavior Modeling in CTR Prediction at Kuaishou. arXiv:2302.02352 [cs.IR]
- Moses S Charikar. 2002. Similarity estimation techniques from rounding algorithms. In Proceedings of the thiry-fourth annual ACM symposium on Theory of computing. 380–388.
- DAGCN: Dual Attention Graph Convolutional Networks. arXiv:1904.02278 [cs.LG]
- End-to-End User Behavior Retrieval in Click-Through RatePrediction Model. arXiv:2108.04468 [cs.IR]
- A Simple Framework for Contrastive Learning of Visual Representations. arXiv:2002.05709 [cs.LG]
- Xinlei Chen and Kaiming He. 2020. Exploring Simple Siamese Representation Learning. arXiv:2011.10566 [cs.CV]
- Wide & Deep Learning for Recommender Systems. arXiv:1606.07792 [cs.LG]
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv:1810.04805 [cs.CL]
- Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 249–256.
- MISS: Multi-Interest Self-Supervised Learning Framework for Click-Through Rate Prediction. arXiv:2111.15068 [cs.IR]
- CoNet: Collaborative Cross Networks for Cross-Domain Recommendation. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management (CIKM ’18). ACM. https://doi.org/10.1145/3269206.3271684
- Diederik P. Kingma and Jimmy Ba. 2017. Adam: A Method for Stochastic Optimization. arXiv:1412.6980 [cs.LG]
- RecGURU: Adversarial Learning of Generalized User Representations for Cross-Domain Recommendation. In Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining (WSDM ’22). ACM. https://doi.org/10.1145/3488560.3498388
- Cross domain recommendation via bi-directional transfer graph collaborative filtering networks. In Proceedings of the 29th ACM international conference on information & knowledge management. 885–894.
- AT4CTR: Auxiliary Match Tasks for Enhancing Click-Through Rate Prediction. arXiv preprint arXiv:2312.06683 (2023).
- Exploiting Variational Domain-Invariant User Embedding for Partially Overlapped Cross Domain Recommendation. arXiv:2205.06440 [cs.IR]
- Disentangled self-supervision in sequential recommenders. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 483–491.
- π𝜋\piitalic_π-Net: A Parallel Information-Sharing Network for Shared-Account Cross-Domain Sequential Recommendations. In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval (Paris, France) (SIGIR’19). Association for Computing Machinery, New York, NY, USA, 685–694. https://doi.org/10.1145/3331184.3331200
- Minet: Mixed interest network for cross-domain click-through rate prediction. In CIKM. 2669–2676.
- Click-through Rate Prediction with Auto-Quantized Contrastive Learning. arXiv:2109.13921 [cs.IR]
- Context Encoders: Feature Learning by Inpainting. arXiv:1604.07379 [cs.CV]
- Practice on Long Sequential User Behavior Modeling for Click-Through Rate Prediction. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD ’19). ACM. https://doi.org/10.1145/3292500.3330666
- Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction. arXiv:2006.05639 [cs.IR]
- User Behavior Retrieval for Click-Through Rate Prediction. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR ’20). ACM. https://doi.org/10.1145/3397271.3401440
- Towards Source-Aligned Variational Models for Cross-Domain Recommendation. In Proceedings of the 15th ACM Conference on Recommender Systems (Amsterdam, Netherlands) (RecSys ’21). Association for Computing Machinery, New York, NY, USA, 176–186. https://doi.org/10.1145/3460231.3474265
- BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer. arXiv:1904.06690 [cs.IR]
- Parallel Split-Join Networks for Shared-account Cross-domain Sequential Recommendations. arXiv:1910.02448 [cs.IR]
- Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research 9, 11 (2008).
- Attention Is All You Need. arXiv:1706.03762 [cs.CL]
- CL4CTR: A Contrastive Learning Framework for CTR Prediction. In Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining. 805–813.
- DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems. In Proceedings of the Web Conference 2021 (WWW ’21). ACM. https://doi.org/10.1145/3442381.3450078
- Self-Supervised Reinforcement Learning for Recommender Systems. arXiv:2006.05779 [cs.LG]
- Self-supervised Learning for Large-scale Item Recommendations. arXiv:2007.12865 [cs.LG]
- Field-aware Neural Factorization Machine for Click-Through Rate Prediction. arXiv:1902.09096 [cs.LG]
- Contrastive Learning for Debiased Candidate Generation in Large-Scale Recommender Systems. arXiv:2005.12964 [cs.IR]
- Deep Interest Evolution Network for Click-Through Rate Prediction. arXiv:1809.03672 [stat.ML]
- Deep Interest Network for Click-Through Rate Prediction. arXiv:1706.06978 [stat.ML]
- Transfer-Meta Framework for Cross-domain Recommendation to Cold-Start Users. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR ’21). ACM. https://doi.org/10.1145/3404835.3463010
- Personalized Transfer of User Preferences for Cross-domain Recommendation. arXiv:2110.11154 [cs.IR]
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.