Outlier ranking aims at the distinction between exceptional outliers and regular objects by measuring deviation of individual objects. In graphs with multiple numeric attributes, not all the attributes are relevant or show dependencies with the graph structure. Considering both graph structure and all given attributes, one cannot measure a clear deviation of objects. This is because the existence of irrelevant attributes clearly hinders the detection of outliers. Thus, one has to select local outlier contexts including only those attributes showing a high contrast between regular and deviating objects. It is an open challenge to detect meaningful local contexts for each node in attributed graphs.
In this work, we propose a novel local outlier ranking model for graphs with multiple numeric node attributes. For each object, our technique determines its subgraph and its statistically relevant subset of attributes locally. This context selection enables a high contrast between an outlier and the regular objects. Out of this context, we compute the outlierness score by incorporating both the attribute value deviation and the graph structure. In our evaluation on real and synthetic data, we show that our approach is able to detect contextual outliers that are missed by other outlier models.