Graph-Driven Generative Models for Heterogeneous Multi-Task Learning
This work addresses the challenge of multi-task learning in healthcare, where tasks like clinical topic modeling and procedure recommendation benefit from shared graph data, though it is incremental as it builds on existing GCN and VAE techniques.
The paper tackles the problem of unifying heterogeneous learning tasks with shared graph structures by proposing a graph-driven generative model that combines graph convolutional networks with multiple variational autoencoders, demonstrating performance boosts in healthcare applications such as clinical topic modeling, procedure recommendation, and admission-type prediction, outperforming state-of-the-art methods.
We propose a novel graph-driven generative model, that unifies multiple heterogeneous learning tasks into the same framework. The proposed model is based on the fact that heterogeneous learning tasks, which correspond to different generative processes, often rely on data with a shared graph structure. Accordingly, our model combines a graph convolutional network (GCN) with multiple variational autoencoders, thus embedding the nodes of the graph i.e., samples for the tasks) in a uniform manner while specializing their organization and usage to different tasks. With a focus on healthcare applications (tasks), including clinical topic modeling, procedure recommendation and admission-type prediction, we demonstrate that our method successfully leverages information across different tasks, boosting performance in all tasks and outperforming existing state-of-the-art approaches.