基于全局属性注意力神经过程模型的数据补全研究

Study on Data Filling Based on Global-attributes Attention Neural Process Model

注意力神经过程(Attentive Neural Process, ANP)模型采用生成模型的方法,以样本的任意局部上下文点为输入,输出整个样本的分布函数,从而模仿高斯过程回归完成数据补全任务。样本的属性信息可以为样本的生成提供重要信息,然而ANP模型忽略了对属性信息的使用。受条件变分自动编码机(CVAE)模型以标签为条件控制样本生成的启发,文中提出了全局属性注意力神经过程(Global-attribute Attentive Neural Process, GANP),将样本属性嵌入到编码器网络,从而使浅层变量隐含样本属性信息。同时,在解码器网络中加入样本属性作为特征,使模型的生成样本更为准确,特别是当输入上下文点数量稀少时,属性信息能够帮助模型生成更清晰、准确的样本。最后,从定性和定量两个方面证明了GANP性能的优越性,可以看出该模型扩展了NP家族模型的应用范围,从而更灵活、快速、准确地解决只有部分上下文信息时整个样本的数据补全问题。

The attention neural process(ANP) model which adopts the method of generative model, takes any number context points of the sample as input, and outputs the distribution function of the entire sample, so as to approximate the function of Gaussian process regression(GPR) to realize the data fullfilling task.In reality, many scenes or datasets containe the attributes or labels data which are critical for generating the missing data.However, the ANP ignores full use of them.Inspired by CVAE model which control sample generation with lable as condition, this paper proposes global attribute attentional neural process(GANP),which embeds sample attributes or labels into ANP network to make the model generate samples more accurately, especially when the number of input context points are scarce.In detail, the sample attributes are embedded into the encoder network, so that the latent variables contain the sample attribute information.At the same time, the sample attributes are added as features in the decoder network to help generate more accurate samples.Finally, experimental results prove the superiority of GANP in both qualitative and quantitative, and it also reveals that GANP expands the application of NP families which can solve the Gaus-sian process regression problem more flexibly, quickly and accurately.