Learning with Missing or Incomplete Data

The problem of learning with missing or incomplete data has received a lot of attention in the literature; [6,10,13,21,23]. The reasons for missing data can be multi-fold ranging from sensor failures in engineering applications to deliberate withholding of some information in medical questioners in the case of missing input feature values or lack of solved (labelled) cases required in supervised learning algorithms in the case of missing labels. And though such problems are very interesting from the practical and theoretical point of view, there ate very few pattern recognition techniques which can deal with missing values in a. straightforward and efficient manner. 11; is in a sharp contrast to the very efficient way in which humans deal with unknown data and are able to perforin various pattern recognition tasks given only a subset; of input features or few labelled reference cases.