Town Hall Events
On 10/20, we hosted our first town hall.
The PyG core team members Rex Ying and Jiaxuan You presented the latest research in AutoML. There are millions of potential GNN designs for solving any problem (i.e. architecture design, hyperparameters/hidden dimensions, learning configs, etc), so picking the best design for your specific problem can be challenging. GraphGym, a design space to manage GNN experiments, makes it easy to run a set of experiments, capture results, reproduce, and run different models / data sets simply by modifying a config file.
The presentation also covered AutoTransfer (leveraging existing knowledge from a task-model bank to decide the best architecture and transfer to new tasks), and training a meta-model to predict performance given an architecture and task (and to optimize the architecture with best predicted performance).
We also heard from the ArangoDB team present and do a live demo of the ArangoDB-PyG Adapter, which exports graphs from ArangoDB, a multi-modal graph DB, into PyG.