Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction

Pi, Qi; Zhou, Guorui; Zhang, Yujing; Wang, Zhe; Ren, Lejian; Fan, Ying; Zhu, Xiaoqiang; Gai, Kun

doi:10.1145/3340531.3412744

Cited by 150 publications

(139 citation statements)

References 18 publications

Supporting

Mentioning

138

Contrasting

Order By: Relevance

“…Thus, it makes the retrieval process learnable, and it is optimized using REINFORCE algorithm. Search-based Interest Model (SIM) [Qi et al, 2020] is another retrieval based model which proposes hard search and soft search approaches. For the hard search, it uses predefined IDs such as user ID and category ID to build the index.…”

Section: Retrieval Based Modelsmentioning

confidence: 99%

“…The upper layers update less frequently than the lower layers, thus HPMN could capture long-term yet multi-scale temporal patterns. With similar motivations,Pi et al [2019] designed a User Interest Center (UIC) module which decouples the time-consuming user behavior modeling procedure with the real-time prediction process. At the inference time, the user behavioral representation is directly obtained from UIC, which is calculated offline.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning for Click-Through Rate Estimation

Zhang

Qin

Guo

et al. 2021

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

Click-through rate (CTR) estimation plays as a core function module in various personalized online services, including online advertising, recommender systems, and web search etc. From 2015, the success of deep learning started to benefit CTR estimation performance and now deep CTR models have been widely applied in many industrial platforms. In this survey, we provide a comprehensive review of deep learning models for CTR estimation tasks. First, we take a review of the transfer from shallow to deep CTR models and explain why going deep is a necessary trend of development. Second, we concentrate on explicit feature interaction learning modules of deep CTR models. Then, as an important perspective on large platforms with abundant user histories, deep behavior models are discussed. Moreover, the recently emerged automated methods for deep CTR architecture design are presented. Finally, we summarize the survey and discuss the future prospects of this field.

show abstract

Section: Retrieval Based Modelsmentioning

confidence: 99%

mentioning

confidence: 99%

Deep Learning for Click-Through Rate Estimation

Zhang

Qin

Guo

et al. 2021

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…MIMN [9] embeds user long-term interest into fixed-sized memory network to decrease the burden of the latency and storage of online serving. SIM [10] leverages a general search unit to get a sub user behavior sequence that is relevant to the candidate item and proposes an exact search unit to model the precise relationship between the candidate item and the sub sequence.…”

Section: Related Workmentioning

confidence: 99%

Multiple Interest and Fine Granularity Network for User Modeling

Xie¹,

Wei²,

Hua³

et al. 2021

Preprint

View full text Add to dashboard Cite

User modeling plays a fundamental role in industrial recommender systems, either in the matching stage and the ranking stage, in terms of both the customer experience and business revenue. How to extract users' multiple interests effectively from their historical behavior sequences to improve the relevance and personalization of the recommend results remains an open problem for user modeling. Most existing deep-learning based approaches exploit item-ids and category-ids but neglect fine-grained features like color and material, which hinders modeling the fine granularity of users' interests.In the paper, we present Multiple interest and Fine granularity Network (MFN), which tackle users' multiple and fine-grained interests and construct the model from both the similarity relationship and the combination relationship among the users' multiple interests. Specifically, for modeling the similarity relationship, we leverage two sets of embeddings, where one is the fixed embedding from pretrained models (e.g. Glove) to give the attention weights and the other is trainable embedding to be trained with MFN together. For modeling the combination relationship, self-attentive layers are exploited to build the higher order combinations of different interest representations. In the construction of network, we design an interest-extract module using attention mechanism to capture multiple interest representations from user historical behavior sequences and leverage an auxiliary loss to boost the distinction of the interest representations. Then a hierarchical network is applied to model the attention relation between the multiple interest vectors of different granularities and the target item. We evaluate MFN on both public and industrial datasets. The experimental results demonstrate that the proposed MFN achieves superior performance than other existed representing methods.

show abstract

“…Although advertisers play an important role in this ecosystem, much less attention has been paid to understanding advertisers either from academic or industrial communities. Existing studies mainly focus on the user side [2,7,17,27,28,40,41], while some [8] [37] noticed the necessity of advertiser understanding for platforms' long-term development, but they focused on predicting one single task like churn rate. As different advertisers at different business cycles have various demands as well as advertising performance, for example, impressions or clicks of advertised products, ROI (i.e return on investment), expenditure constraints, active or churn rate, etc, it is insufficient to measure overall conditions of advertisers based on one single task.…”

Section: Introductionmentioning

confidence: 99%

Leaving No One Behind: A Multi-Scenario Multi-Task Meta Learning Approach for Advertiser Modeling

Zhang

Liao

Liu

et al. 2022

Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

Advertisers play an essential role in many e-commerce platforms like Taobao and Amazon. Fulfilling their marketing needs and supporting their business growth is critical to the long-term prosperity of platform economies. However, compared with extensive studies on user modeling such as click-through rate predictions, much less attention has been drawn to advertisers, especially in terms of understanding their diverse demands and performance. Different from user modeling, advertiser modeling generally involves many kinds of tasks (e.g. predictions of advertisers' expenditure, active-rate, or total impressions of promoted products). In addition, major e-commerce platforms often provide multiple marketing scenarios (e.g. Sponsored Search, Display Ads, Live Streaming Ads) while advertisers' behavior tend to be dispersed among many of them. This raises the necessity of multi-task and multi-scenario consideration in comprehensive advertiser modeling, which faces the following challenges: First, one model per scenario or per task simply doesn't scale; Second, it is particularly hard to model new or minor scenarios with limited data samples; Third, inter-scenario correlations are complicated, and may vary given different tasks.To tackle these challenges, we propose a multi-scenario multitask meta learning approach (M2M) which simultaneously predicts multiple tasks in multiple advertising scenarios. Specifically, we introduce a novel meta unit that incorporates rich scenario knowledge to learn explicit inter-scenario correlations and can easily scale to new scenarios. Furthermore, we present a meta attention module to capture diverse inter-scenario correlations given different tasks, and a meta tower module to enhance the capability of capturing the representation of scenario-specific features. Compelling results from both offline evaluation and online A/B tests demonstrate the superiority of M2M over state-of-the-art methods.

show abstract

Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction

Cited by 150 publications

References 18 publications

Deep Learning for Click-Through Rate Estimation

Deep Learning for Click-Through Rate Estimation

Multiple Interest and Fine Granularity Network for User Modeling

Leaving No One Behind: A Multi-Scenario Multi-Task Meta Learning Approach for Advertiser Modeling

Contact Info

Product

Resources

About