Jiarui Qin
Abstract
Click-through rate (CTR) estimation plays a crucial role in modern online personalization services. It is essential to capture users’ drifting interests by modeling sequential user behaviors to build an accurate CTR estimation model. However, as the users accumulate a large amount of behavioral data on the online platforms, the current CTR models have to truncate user behavior sequences and utilize the most recent behaviors, which leads to a problem that sequential patterns such as periodicity or long-term dependency are not contained in the recent behaviors but in far back history. However, it is non-trivial to model the entire user sequence by directly using it for two reasons. Firstly, the very long input sequences will make online inference time and system load infeasible. Secondly, the very long sequences contain much noise, thus making it difficult for CTR models to capture useful patterns effectively. To tackle this issue, we consider it from the input data perspective instead of designing more sophisticated yet complex models. As the entire user behavior sequence contains much noise, it is unnecessary to input the entire sequence. Instead, we could just retrieve only a small part of it as the input to the CTR model. In this article, we propose the User Behavior Retrieval (UBR) framework which aims at learning to retrieve the most informative user behaviors according to each CTR estimation request. Retrieving only a small set of behaviors could alleviate the two problems of utilizing very long sequences (i.e., inference efficiency and noisy input). The distinguishing property of UBR is that it supports arbitrary and learnable retrieval functions instead of utilizing a fixed pre-defined function, which is different from the current retrieval-based methods. Offline evaluations on three large-scale real-world datasets demonstrate the superiority and efficacy of the UBR framework. We further deploy UBR at the Huawei App Store, where it achieves 6.6% of eCPM gain in the online A/B test and now serves the main traffic in the Huawei App Store advertising scenario.
- [1] . 2018. Latent cross: Making use of context in recurrent recommender systems. In Proceedings of the WSDM.Google Scholar
Digital Library
- [2] . 2002. Similarity estimation techniques from rounding algorithms. In Proceedings of the 34th Annual ACM Symposium on Theory of Computing. 380–388.Google ScholarDigital Library
- [3] . 2021. End-to-end user behavior retrieval in click-through RatePrediction model. CoRR abs/2108.04468 (2021).Google Scholar
- [4] . 2019. Behavior sequence transformer for e-commerce recommendation in alibaba. In Proceedings of the 1st DLP-KDD Workshop. 1–4.Google ScholarDigital Library
- [5] . 2020. Sequence-aware factorization machines for temporal predictive analytics. In Proceedings of the 2020 IEEE 36th International Conference on Data Engineering. IEEE, 1405–1416.Google ScholarCross Ref
- [6] . 2018. Sequential recommendation with user memory networks. In Proceedings of the WSDM.Google ScholarDigital Library
- [7] . 2016. Wide and deep learning for recommender systems. In Proceedings of the DLRS@RecSys, ACM, 7–10.Google ScholarDigital Library
- [8] . 2020. Rethinking attention with performers. In Proceeding of the ICLR.Google Scholar
- [9] . 2018. Collaborative memory network for recommendation systems. In Proceedings of the SIGIR.Google ScholarDigital Library
- [10] . 2019. Deep session interest network for click-through rate prediction. In Proceedings of the IJCAI.Google ScholarCross Ref
- [11] . 2014. Neural turing machines. CoRR abs/1410.5401 (2014).Google Scholar
- [12] . 2017. DeepFM: A factorization-machine based neural network for CTR prediction. In Proceeding of the IJCAI. 1725–1731Google Scholar
- [13] . 2016. Vista: A visually, socially, and temporally-aware model for artistic recommendation. In Proceedings of the RecSys.Google ScholarDigital Library
- [14] . 2016. Fusing similarity models with markov chains for sparse sequential recommendation. In Proceedings of the ICDM.Google ScholarCross Ref
- [15] . 2018. Recurrent neural networks with top-k gains for session-based recommendations. In Proceedings of the CIKM.Google Scholar
- [16] . 2016. Session-based recommendations with recurrent neural networks. ICLR.Google Scholar
- [17] . 2019. FiBiNET: Combining feature importance and bilinear feature interaction for click-through rate prediction. In Proceedings of the 13th ACM Conference on Recommender Systems. 169–177.Google ScholarDigital Library
- [18] . 2022. Learn over past, evolve for future: Search-based time-aware recommendation with sequential behavior data. In Proceeding of the WWW, ACM, 2451–2461.Google Scholar
- [19] . 2017. Neural survival recommender. In Proceedings of the WSDM.Google ScholarDigital Library
- [20] . 2016. Field-aware factorization machines for CTR prediction. In Proceedings of the 10th ACM Conference on Recommender Systems. 43–50.Google ScholarDigital Library
- [21] . 2018. Self-attentive sequential recommendation. In Proceedings of the ICDM.Google Scholar
- [22] . 2020. Transformers are rnns: Fast autoregressive transformers with linear attention. In Proceedings of the International Conference on Machine Learning. PMLR, 5156–5165.Google Scholar
- [23] . 2020. Reformer: The Efficient Transformer. In Proceeding of the ICLR.Google Scholar
- [24] . 2009. Collaborative filtering with temporal dynamics. In Proceedings of the KDD.Google ScholarDigital Library
- [25] . 2020. Time interval aware self-attention for sequential recommendation. In Proceedings of the WSDM.Google ScholarDigital Library
- [26] . 2019. Fi-gnn: Modeling feature interactions via graph neural networks for ctr prediction. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management. 539–548.Google ScholarDigital Library
- [27] . 2018. xdeepfm: Combining explicit and implicit feature interactions for recommender systems. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 1754–1763.Google ScholarDigital Library
- [28] . 2019. Feature generation by convolutional neural network for click-through rate prediction. In Proceedings of the World Wide Web Conference. 1119–1129.Google ScholarDigital Library
- [29] . 2016. Context-aware sequential recommendation. In Proceedings of the ICDM.Google ScholarCross Ref
- [30] . 2018. Translation-based factorization machines for sequential recommendation. In Proceedings of the 12th ACM Conference on Recommender Systems. 63–71.Google ScholarDigital Library
- [31] . 2019. Practice on long sequential user behavior modeling for click-through rate prediction. In Proceedings of the SIGKDD.Google ScholarDigital Library
- [32] . 2020. Search-based user interest modeling with lifelong sequential behavior data for click-through rate prediction. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.Google Scholar
- [33] . 2020. Sequential recommendation with dual side neighbor-based collaborative relation modeling. In Proceedings of the 13th ACM International Conference on Web Search and Data Mining. ACM.Google ScholarDigital Library
- [34] . 2021. Retrieval and interaction machine for tabular data prediction. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 1379–1389.Google ScholarDigital Library
- [35] . 2020. User behavior retrieval for click-through rate prediction. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval.Google ScholarDigital Library
- [36] . 2016. Product-based neural networks for user response prediction. In Proceedings of the ICDM.Google ScholarCross Ref
- [37] . 2018. Product-based neural networks for user response prediction over multi-field categorical data. ACM Transactions on Information Systems 37, 1 (2018), 1–35.Google ScholarDigital Library
- [38] . 2019. Lifelong sequential modeling with personalized memorization for user response prediction. In Proceeding of the SIGIR, ACM, 565–574.Google Scholar
- [39] . 2019. RepeatNet: A repeat aware neural recommendation machine for session-based recommendation. In Proceeding of the AAAI. AAAI Press, 4806–4813.Google Scholar
- [40] . 2010. Factorization machines. In Proceedings of the ICDM.Google ScholarDigital Library
- [41] . 2009. BPR: Bayesian Personalized Ranking from Implicit Feedback. In UAI. AUAI Press, 452–461.Google Scholar
- [42] . 2010. Factorizing personalized markov chains for next-basket recommendation. In Proceedings of the WWW.Google ScholarDigital Library
- [43] Stephen E. Robertson, Steve Walker, Susan Jones, Micheline M. Hancock-Beaulieu, and Mike Gatford. 1995. Okapi at TREC-3. Nist Special Publication Sp 109, 109 (1995).Google Scholar
- [44] . 2019. BERT4Rec: Sequential recommendation with bidirectional encoder representations from transformer. In Proceedings of the CIKM. 1441–1450.Google ScholarDigital Library
- [45] . 2015. Factorization machines with follow-the-regularized-leader for CTR prediction in display advertising. In Proceedings of the 2015 IEEE International Conference on Big Data. IEEE.Google ScholarDigital Library
- [46] . 2018. Personalized top-n sequential recommendation via convolutional sequence embedding. In Proceedings of the WSDM.Google ScholarDigital Library
- [47] . 2022. Efficient transformers: A survey. ACM Computing Surveys 55, 6 (2022), 1–28.Google Scholar
- [48] . 2017. Attention is all you need. In Proceedings of the Advances in Neural Information Processing Systems.Google Scholar
- [49] . 2018. Recurrent neural networks for long and short-term sequential recommendation. CoRR abs/1807.09142 (2018).Google Scholar
- [50] . 2018. Neural memory streaming recommender networks with adversarial training. In Proceedings of the KDD.Google ScholarDigital Library
- [51] . 2017. Deep and cross network for ad click predictions. In Proceedings of the ADKDD’17. 1–7.Google ScholarDigital Library
- [52] . 2018. The lambdaloss framework for ranking metric optimization. In Proceedings of the CIKM.Google ScholarDigital Library
- [53] . 1996. Learning in the presence of concept drift and hidden contexts. Machine Learning 23, 1 (1996), 69–101.Google ScholarCross Ref
- [54] . 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning 8, 3 (1992), 229–256.Google ScholarDigital Library
- [55] . 2017. Recurrent recommender networks. In Proceedings of the WSDM.Google ScholarDigital Library
- [56] . 2019. Dual sequential prediction models linking sequential recommendation and information dissemination. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 447–457.Google ScholarDigital Library
- [57] . 2019. Session-based recommendation with graph neural networks. In Proceedings of the AAAI.Google ScholarDigital Library
- [58] . 2021. Linear-time self attention with codeword histogram for efficient recommendation. In Proceedings of the Web Conference 2021. 1262–1273.Google ScholarDigital Library
- [59] . 2020. Neural hierarchical factorization machines for user’s event sequence analysis. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 1893–1896.Google ScholarDigital Library
- [60] . 2017. Attentional factorization machines: Learning the weight of feature interactions via attention networks. In Proceeding of the IJCAI. ijcai.org, 3119–3125.Google Scholar
- [61] . 2019. Graph contextualized self-attention network for session-based recommendation. In Proceedings of the IJCAI.Google ScholarCross Ref
- [62] . 2018. Attention with sparsity regularization for neural machine translation and summarization. IEEE/ACM Transactions on Audio, Speech, and Language Processing 27, 3 (2018), 507–518.Google ScholarDigital Library
- [63] . 2016. Deep learning over multi-field categorical data: A case study on user response prediction. In Proceedings of the ECIR.Google Scholar
- [64] . 2021. Deep learning for click-through rate estimation. In Proceedings of the IJCAI.Google ScholarCross Ref
- [65] . 2019. Deep interest evolution network for click-through rate prediction. In Proceedings of the AAAI.Google ScholarDigital Library
- [66] . 2018. Deep interest network for click-through rate prediction. In Proceedings of the KDD.Google ScholarDigital Library
- [67] . 2018. Learning tree-based deep model for recommender systems. In Proceedings of the KDD.Google ScholarDigital Library
Index Terms
- Learning to Retrieve User Behaviors for Click-through Rate Estimation
Recommendations
User Behavior Retrieval for Click-Through Rate Prediction
SIGIR '20: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information RetrievalClick-through rate (CTR) prediction plays a key role in modern online personalization services. In practice, it is necessary to capture user's drifting interests by modeling sequential user behaviors to build an accurate CTR prediction model. However, ...
User Response Learning for Directly Optimizing Campaign Performance in Display Advertising
CIKM '16: Proceedings of the 25th ACM International on Conference on Information and Knowledge ManagementLearning and predicting user responses, such as clicks and conversions, are crucial for many Internet-based businesses including web search, e-commerce, and online advertising. Typically, a user response model is established by optimizing the prediction ...
A methodology based on Deep Learning for advert value calculation in CPM, CPC and CPA networks
In this research, we propose a methodology for advert value calculation in CPM, CPC and CPA networks. Accurately estimating this value increases the three previous networks' incomes by selecting the most profitable advert. By increasing income, ...
Comments