DeepFM: A Factorization-Machine based Neural Network for CTR Prediction

Guo, Huifeng; Tang, Ruiming; Ye, Yunming; Li, Zhenguo; He, Xiuqiang

doi:10.48550/arxiv.1703.04247

Cited by 344 publications

(445 citation statements)

References 14 publications

Supporting

Mentioning

445

Contrasting

Order By: Relevance

“…For offline evaluation, we compare our method with four categories of models: Feature Interaction (FI) models,User Interests Modeling (UIM) models, Graph Neural Networks (GNN) models and Transformer-based models.FI models include DeepFM [8], xDeepFM [17], UIM models include DIN [36], DIEN [35] and DMR [19]. GNN models include GCN [16], GAT [26], Graph-SAGE [9] and HGNN models includes RGCN [23], HAN [29], HGT [12],NIRec [14].…”

Section: Competitors and Metricsmentioning

confidence: 99%

“…To discover the potential click-through relation between user and item, the most popular learning paradigm is to firstly use an embedding layer to transfer the sparse user/item features to a low-dimensional dense embedding, and then to construct the feature fusion & learning models to encode the user preferences, item characteristic or their interactions. Typical models include Wide&Deep [2], DeepFM [8], xDeepFM [17], AFM [31], DeepMCP [20] and so on. However, this learning paradigm treats the sparse categorical feature equally and ignores the intrinsic structures among them, e.g., the sequential order of historical behaviors.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Neighbour Interaction based Click-Through Rate Prediction via Graph-masked Transformer

Min¹,

Yu²,

Xu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Click-Through Rate (CTR) prediction, is an essential component of online advertising. The mainstream techniques mostly focus on feature interaction or user interest modeling, which rely on users' directly interacted items. The performance of these methods is usually impeded by inactive behaviours and system's exposure, incurring that the features extracted do not contain enough information to represent all potential interests. For this sake, we propose Neighbor-Interaction based CTR prediction, which put this task into a Heterogeneous Information Network (HIN) setting, then involves local neighborhood of the target user-item pair in the HIN to predict their linkage. In order to enhance the representation of the local neighbourhood, we consider four types of topological interaction among the nodes, and propose a novel Graph-masked Transformer architecture to effectively incorporates both feature and topological information. We conduct comprehensive experiments on two real world datasets and the experimental results show that our proposed method outperforms state-of-the-art CTR models significantly. CCS CONCEPTS• Information systems → Computational advertising.

show abstract

Section: Competitors and Metricsmentioning

confidence: 99%

mentioning

confidence: 99%

Neighbour Interaction based Click-Through Rate Prediction via Graph-masked Transformer

Min¹,

Yu²,

Xu³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The second group serves as baselines without cold-start alleviating component as well as backbones to test the generalization and adaptability of our proposed VELF. (1) DeepFM [7] is a deep recommendation method that learns both low-and high-level interactions between fields. (2) Wide&Deep [3] develop wide linear models and deep neural networks together to enhance their respective abilities.…”

Section: Baselinesmentioning

confidence: 99%

“…We compare our VELF with the SOTA methods to alleviate cold-start problem from the perspective of embedding learning, i.e., Dropout-Net [28] and MWUF [34]. Comparisons with state-of-the-arts are conducted on DeepFM [7] which is one of the most popular model structures used in industry. For more detailed and directed analysis, we also report the results of the second group baseline models mentioned before.…”

Section: Comparison With State-of-the-arts (Rq1)mentioning

confidence: 99%

Alleviating Cold-start Problem in CTR Prediction with A Variational Embedding Learning Framework

Xu¹,

Chen²,

Qian³

et al. 2022

Preprint

View full text Add to dashboard Cite

We propose a general Variational Embedding Learning Framework (VELF) for alleviating the severe cold-start problem in CTR prediction. VELF addresses the cold start problem via alleviating over-fits caused by data-sparsity in two ways: learning probabilistic embedding, and incorporating trainable and regularized priors which utilize the rich side information of cold start users and advertisements (Ads). The two techniques are naturally integrated into a variational inference framework, forming an end-to-end training process. Abundant empirical tests on benchmark datasets well demonstrate the advantages of our proposed VELF. Besides, extended experiments confirmed that our parameterized and regularized priors provide more generalization capability than traditional fixed priors.

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

DeepFM: A Factorization-Machine based Neural Network for CTR Prediction

Cited by 344 publications

References 14 publications

Neighbour Interaction based Click-Through Rate Prediction via Graph-masked Transformer

Neighbour Interaction based Click-Through Rate Prediction via Graph-masked Transformer

Alleviating Cold-start Problem in CTR Prediction with A Variational Embedding Learning Framework

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

Contact Info

Product

Resources

About