Uncertainty-Aware Robust Learning on Noisy Graphs
This addresses the problem of robust graph learning for practitioners dealing with noisy data, but it is incremental as it builds on existing GNN and robust optimization methods.
The paper tackled the problem of graph neural networks (GNNs) being hampered by noisy measurements in real-world graphs, and the result was a novel uncertainty-aware framework that demonstrated superior predictive performance over baselines across noisy scenarios.
Graph neural networks (GNNs) have excelled in various graph learning tasks, particularly node classification. However, their performance is often hampered by noisy measurements in real-world graphs, which can corrupt critical patterns in the data. To address this, we propose a novel uncertainty-aware graph learning framework inspired by distributionally robust optimization. Specifically, we use a graph neural network-based encoder to embed the node features and find the optimal node embeddings by minimizing the worst-case risk through a minimax formulation. Such an uncertainty-aware learning process leads to improved node representations and a more robust graph predictive model that effectively mitigates the impact of uncertainty arising from data noise. Our experimental results demonstrate superior predictive performance over baselines across noisy scenarios.