With the rapid development of online advertising and recommendation systems, click-through rate prediction is expected to play an increasingly important role.Recently many DNN-based models which follow a similar Embedding&MLP paradigm have been proposed, and have achieved good result in image/voice and nlp fields.In these methods the Wide&Deep model announced by Google plays a key role.Most models first map large scale sparse input features into low-dimensional vectors which are transformed to fixed-length vectors, then concatenated together before being fed into a multilayer perceptron (MLP) to learn non-linear relations among input features. The number of trainable variables normally grow dramatically the number of feature fields and the embedding dimension grow. It is a big challenge to get state-of-the-art result through training deep neural network and embedding together, which falls into local optimal or overfitting easily.In this paper, we propose an Structured Semantic Model (SSM) to tackles this challenge by designing a orthogonal base convolution and pooling model which adaptively learn the multi-scale base semantic representation between features supervised by the click label.The output of SSM are then used in the Wide&Deep for CTR prediction.Experiments on two public datasets as well as real Weibo production dataset with over 1 billion samples have demonstrated the effectiveness of our proposed approach with superior performance comparing to state-of-the-art methods.
翻译:随着在线广告和推荐系统的快速发展,预计点击率预测将发挥越来越重要的作用。 最近提出了许多基于DNN的基于DNN的模型,这些模型遵循类似的嵌入和MLP范式,在图像/声音和 nlp 字段中取得了良好效果。 在这些方法中,谷歌宣布的宽度和深度模型起着关键作用。 多数模型首先将大规模稀释的输入特性映射到低维矢量中,这些矢量转换成固定矢量,然后在输入多层的感应器(MLP)之前将之连接起来,以学习输入特性之间的非线性关系。 可训练变量的数量通常会大幅增加功能字段的数量和嵌入维度的增长。要通过培训深层神经网络和嵌入一起取得最新结果,这是一大挑战。 在本文中,我们提出了一个结构化的语义模型,通过设计一个或多层次的基质对比和集合模型,以适应性地学习多层次的高级基础比值,然后通过SMLS-semantisal 数据标签,将S-real developmental laveal dal laction laction laction laction lappal labal lady dal lady dal labal laction lady dal laction laction laction labal labal labal labal labal labal labal ladal laction lautdal laction laction lavedal ladal laction laction laction lactional lactional labal laction labal lactionsal ladal ladal ladal labal labal lactionsal labal labal labal lactionsal lactionsal laction lactional labal ladal laction labal ladal ladal ladal ladal ladal ladal ladal ladal labaldal ladal ladal ladal lactional la