When such components are expected to be embedded in safety-critical systems (e.g.,

Neural Information Processing Systems http://nips.cc/

While one side of the coin is a boost of interest and investment on deep learning research, theother isanemergent need foritsrobustness, sample efficiency,security,and interpretability.

Neural Information Processing Systems http://nips.cc/

InfoGAN [10] in particular, learns an unsupervised disentangled representation by maximizing the mutual information between the discrete or continuous latent variables and the corresponding generated samples.

However,GNNs have notconsidered different types ofuncertainties associated with class probabilities to minimize risk of increasing misclassification under uncertainty in real life. In this work, we propose a multi-source uncertainty framework using a GNN that reflects various types of predictive uncertainties in both deep learning and belief/evidence theory domains fornodeclassification predictions.