Reliable Graph Neural Networks via Robust Aggregation

Understand

Perturbations targeting the graph structure have proven to be extremely effective in reducing the performance of Graph Neural Networks (GNNs), and traditional defenses such as adversarial training do not seem to be able to improve robustness.

• This work is motivated by the observation that adversarially injected edges effectively can be viewed as additional samples to a node's neighborhood aggregation function, which results in distorted aggregations accumulating over the layers.
• Conventional GNN aggregation functions, such as a sum or mean, can be distorted arbitrarily by a single outlier.
• We propose a robust aggregation function motivated by the field of robust statistics.