Identifying outlier nodes is an important task in complex network mining, which can be done taking into account several criteria. For example, if we consider only the connectivity of the nodes in a scale-free network, the most outlier nodes will be the hubs because its connectivity is much higher than the average connectivity of the network. Here, we consider the random walk distance measure. The method determines a “view” to the whole network for each node (the distance measure) and infers that outliers are those nodes whose view differs significantly from majority of the nodes. We apply the method to the yeast protein-protein interaction network and we show that the outlier proteins are those related to metabolism and cell cycle and DNA processing. There is a well defined relationship between the view of each protein (node) and their biological functions.