Reliable Graph Neural Networks for Drug Discovery Under Distributional Shift
This addresses reliability issues in critical drug discovery tasks, but it is incremental as it builds on existing methods for a specific domain.
The paper tackles the problem of overconfident mis-predictions in Graph Neural Networks for drug discovery under distributional shift by introducing a new benchmark, CardioTox, and developing GNN-SNGP, which increases distance-awareness and reduces overconfident mis-predictions without sacrificing accuracy.
The concern of overconfident mis-predictions under distributional shift demands extensive reliability research on Graph Neural Networks used in critical tasks in drug discovery. Here we first introduce CardioTox, a real-world benchmark on drug cardio-toxicity to facilitate such efforts. Our exploratory study shows overconfident mis-predictions are often distant from training data. That leads us to develop distance-aware GNNs: GNN-SNGP. Through evaluation on CardioTox and three established benchmarks, we demonstrate GNN-SNGP's effectiveness in increasing distance-awareness, reducing overconfident mis-predictions and making better calibrated predictions without sacrificing accuracy performance. Our ablation study further reveals the representation learned by GNN-SNGP improves distance-preservation over its base architecture and is one major factor for improvements.