Structure Learning in Deep Multi-Task Models

Multi-Task Learning (MTL) aims at improving the learning process by solving different tasks simultaneously. Two general approaches for neural MTL are hard and soft information sharing during training. Here we propose two new approaches to neural MTL. The first one uses a common model to enforce a soft sharing learning of the tasks considered. The second one adds a graph Laplacian term to a hard sharing neural model with the goal of detecting existing but a priori unknown task relations. We will test both tasks on real and synthetic datasets and show that either one can improve on other MTL neural models.