Skip to yearly menu bar Skip to main content


Processing of missing data by neural networks

Marek Śmieja · Łukasz Struski · Jacek Tabor · Bartosz Zieliński · Przemysław Spurek

Room 517 AB #131

Keywords: [ Deep Learning ] [ Missing Data ]


We propose a general, theoretically justified mechanism for processing missing data by neural networks. Our idea is to replace typical neuron's response in the first hidden layer by its expected value. This approach can be applied for various types of networks at minimal cost in their modification. Moreover, in contrast to recent approaches, it does not require complete data for training. Experimental results performed on different types of architectures show that our method gives better results than typical imputation strategies and other methods dedicated for incomplete data.

Live content is unavailable. Log in and register to view live content