We investigate the use of multiple intrinsic geometric at- tributes, including angles, geodesic distances, and curva- tures, for 3D face recognition, where each face is repre- sented by a triangle mesh, preprocessed to possess a uni- form connectivity. As invariance to facial expressions holds the key to improving recognition performance, we propose to train for the component-wise weights to be applied to each individual attribute, as well as the weights used to combine the attributes, in order to adapt to expression vari- ations. Using the eigenface approach based on the training results and a nearest neighbor classifier, we report recogni- tion results on the expression-rich GavabDB face database and the well-known Notre Dame FRGC 3D database. We also perform a cross validation between the two databases.