当前位置:
X-MOL 学术
›
arXiv.cs.IR
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
DADNN: Multi-Scene CTR Prediction via Domain-Aware Deep Neural Network
arXiv - CS - Information Retrieval Pub Date : 2020-11-24 , DOI: arxiv-2011.11938 Junyou He, Guibao Mei, Feng Xing, Xiaorui Yang, Yongjun Bao, Weipeng Yan
arXiv - CS - Information Retrieval Pub Date : 2020-11-24 , DOI: arxiv-2011.11938 Junyou He, Guibao Mei, Feng Xing, Xiaorui Yang, Yongjun Bao, Weipeng Yan
Click through rate(CTR) prediction is a core task in advertising systems. The
booming e-commerce business in our company, results in a growing number of
scenes. Most of them are so-called long-tail scenes, which means that the
traffic of a single scene is limited, but the overall traffic is considerable.
Typical studies mainly focus on serving a single scene with a well designed
model. However, this method brings excessive resource consumption both on
offline training and online serving. Besides, simply training a single model
with data from multiple scenes ignores the characteristics of their own. To
address these challenges, we propose a novel but practical model named
Domain-Aware Deep Neural Network(DADNN) by serving multiple scenes with only
one model. Specifically, shared bottom block among all scenes is applied to
learn a common representation, while domain-specific heads maintain the
characteristics of every scene. Besides, knowledge transfer is introduced to
enhance the opportunity of knowledge sharing among different scenes. In this
paper, we study two instances of DADNN where its shared bottom block is
multilayer perceptron(MLP) and Multi-gate Mixture-of-Experts(MMoE)
respectively, for which we denote as DADNN-MLP and DADNN-MMoE.Comprehensive
offline experiments on a real production dataset from our company show that
DADNN outperforms several state-of-the-art methods for multi-scene CTR
prediction. Extensive online A/B tests reveal that DADNN-MLP contributes up to
6.7% CTR and 3.0% CPM(Cost Per Mille) promotion compared with a well-engineered
DCN model. Furthermore, DADNN-MMoE outperforms DADNN-MLP with a relative
improvement of 2.2% and 2.7% on CTR and CPM respectively. More importantly,
DADNN utilizes a single model for multiple scenes which saves a lot of offline
training and online serving resources.
中文翻译:
DADNN:通过领域感知的深度神经网络进行多场景点击率预测
点击率(CTR)预测是广告系统中的一项核心任务。我们公司蓬勃发展的电子商务业务导致了越来越多的场景。它们中的大多数是所谓的长尾场景,这意味着单个场景的流量有限,但总体流量却很大。典型的研究主要集中在为模型设计良好的单一场景服务。但是,这种方法在离线培训和在线服务上都会带来过多的资源消耗。此外,仅使用来自多个场景的数据训练单个模型就忽略了它们自身的特征。为了解决这些挑战,我们提出了一种新颖但实用的模型,即仅通过一个模型为多个场景提供服务的领域感知深度神经网络(DADNN)。特别,所有场景之间共享的底部块用于学习通用表示,而特定领域的负责人保持每个场景的特征。此外,引入了知识转移以增加不同场景之间知识共享的机会。在本文中,我们研究了DADNN的两个实例,它们共享的底部模块分别是多层感知器(MLP)和多门专家混合物(MMoE),我们分别将其表示为DADNN-MLP和DADNN-MMoE。在我们公司的实际生产数据集上进行的实验表明,DADNN优于几种用于多场景CTR预测的最新方法。广泛的在线A / B测试显示,与精心设计的DCN模型相比,DADNN-MLP最多可提高6.7%的点击率和3.0%的CPM(每千次展示费用)。此外,DADNN-MMoE优于DADNN-MLP,其CTR和CPM分别相对提高了2.2%和2.7%。更重要的是,DADNN将单个模型用于多个场景,从而节省了大量离线培训和在线服务资源。
更新日期:2020-11-25
中文翻译:
DADNN:通过领域感知的深度神经网络进行多场景点击率预测
点击率(CTR)预测是广告系统中的一项核心任务。我们公司蓬勃发展的电子商务业务导致了越来越多的场景。它们中的大多数是所谓的长尾场景,这意味着单个场景的流量有限,但总体流量却很大。典型的研究主要集中在为模型设计良好的单一场景服务。但是,这种方法在离线培训和在线服务上都会带来过多的资源消耗。此外,仅使用来自多个场景的数据训练单个模型就忽略了它们自身的特征。为了解决这些挑战,我们提出了一种新颖但实用的模型,即仅通过一个模型为多个场景提供服务的领域感知深度神经网络(DADNN)。特别,所有场景之间共享的底部块用于学习通用表示,而特定领域的负责人保持每个场景的特征。此外,引入了知识转移以增加不同场景之间知识共享的机会。在本文中,我们研究了DADNN的两个实例,它们共享的底部模块分别是多层感知器(MLP)和多门专家混合物(MMoE),我们分别将其表示为DADNN-MLP和DADNN-MMoE。在我们公司的实际生产数据集上进行的实验表明,DADNN优于几种用于多场景CTR预测的最新方法。广泛的在线A / B测试显示,与精心设计的DCN模型相比,DADNN-MLP最多可提高6.7%的点击率和3.0%的CPM(每千次展示费用)。此外,DADNN-MMoE优于DADNN-MLP,其CTR和CPM分别相对提高了2.2%和2.7%。更重要的是,DADNN将单个模型用于多个场景,从而节省了大量离线培训和在线服务资源。