We combine concept-based neural networks with generative, flow-based classifiers into a novel, intrinsically explainable, exactly invertible approach to supervised learning. Prototypical neural networks, a type of concept-based neural network, represent an exciting way forward in realizing human-comprehensible machine learning without concept annotations, but a human-machine semantic gap continues to haunt current approaches. We find that reliance on indirect interpretation functions for prototypical explanations imposes a severe limit on prototypes' informative power. From this, we posit that invertibly learning prototypes as distributions over the latent space provides more robust, expressive, and interpretable modeling. We propose one such model, called ProtoFlow, by composing a normalizing flow with Gaussian mixture models. ProtoFlow (1) sets a new state-of-the-art in joint generative and predictive modeling and (2) achieves predictive performance comparable to existing prototypical neural networks while enabling richer interpretation.

We develop an algorithm for adapting a semantic segmentation model that is trained using a labeled source domain to generalize well in an unlabeled target domain. A similar problem has been studied extensively in the unsupervised domain adaptation (UDA) literature, but existing UDA algorithms require access to both the source domain labeled data and the target domain unlabeled data for training a domain agnostic semantic segmentation model. Relaxing this constraint enables a user to adapt pretrained models to generalize in a target domain, without requiring access to source data. To this end, we learn a prototypical distribution for the source domain in an intermediate embedding space. This distribution encodes the abstract knowledge that is learned from the source domain. We then use this distribution for aligning the target domain distribution with the source domain distribution in the embedding space. We provide theoretical analysis and explain conditions under which our algorithm is effective. Experiments on benchmark adaptation task demonstrate our method achieves competitive performance even compared with joint UDA approaches.

We develop an algorithm for adaptation of a classifier from a labeled source domain to an unlabeled target domain in a sequential learning setting. This problem has been studied extensively in unsupervised domain adaptation (UDA) literature but the existing UDA methods consider a joint learning setting where the model is trained on the source domain and the target domain data simultaneously. We consider a more practical setting, where the model has been trained on the labeled source domain data and then needs to be adapted to the unlabeled target domain, without having access to the source domain training data. We tackle this problem by aligning the distributions of the source and the target domain in a discriminative embedding space. To overcome the challenges of learning in a sequential setting, we learn an intermediate prototypical distribution from the source labeled data and then use this distribution for knowledge transfer to the target domain. We provide theoretical justification for the proposed algorithm by showing that it optimizes an upper-bound for the expected risk in the target domain. We also conduct extensive experiments on several standard benchmarks and demonstrate the competitiveness of the proposed model adaptation method.