Human brains can turn a single messy experience into a lasting skill, while even the most advanced artificial intelligence still needs oceans of data and careful supervision to do something similar.
The remarkable success in graph neural networks (GNNs) promotes the eXplainable Graph Learning (XGL) methods. However, existing XGL approaches are susceptible to exploiting shortcuts (aka, spurious ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results