3. 2
present a consistently well-performing and parameter efficient encode-process-decode
architecture
Previous work on tasks taken from classical graph theory focuses on evaluating the
performance of GNN models on a single task such as shortest path
contributions
4. 3
believe this multi-task approach ensures that the GNNs are able to understand multiple
properties simultaneously, which is fundamental for solving complex graph problems.
efficiently sharing parameters between the tasks suggests a deeper understanding of the
structural features of the graphs.
Explore the generalization ability of the networks by testing on graphs of larger sizes than
those present in the training set
Hypothesis