REVIEW 4 cited by
Simple GNN Regularisation for 3D Molecular Property Prediction & Beyond
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
In this paper we show that simple noise regularisation can be an effective way to address GNN oversmoothing. First we argue that regularisers addressing oversmoothing should both penalise node latent similarity and encourage meaningful node representations. From this observation we derive "Noisy Nodes", a simple technique in which we corrupt the input graph with noise, and add a noise correcting node-level loss. The diverse node level loss encourages latent node diversity, and the denoising objective encourages graph manifold learning. Our regulariser applies well-studied methods in simple, straightforward ways which allow even generic architectures to overcome oversmoothing and achieve state of the art results on quantum chemistry tasks, and improve results significantly on Open Graph Benchmark (OGB) datasets. Our results suggest Noisy Nodes can serve as a complementary building block in the GNN toolkit.
Forward citations
Cited by 4 Pith papers
-
M4GN: Mesh-based Multi-segment Hierarchical Graph Network for Dynamic Simulations
A hierarchical mesh-graph network with modal-decomposition-guided segmentation reports up to 56% lower rollout error than baselines and introduces a long-range beam-deformation benchmark.
-
ToxBench: A Binding Affinity Prediction Benchmark with AB-FEP-Calculated Labels for Human Estrogen Receptor Alpha
ToxBench provides 8,770 AB-FEP-computed binding affinities for ERα-ligand complexes, and the proposed DualBind model learns to predict them orders of magnitude faster.
-
MEGA-CL: A Molecular Foundation Model for Generalizable ADMET Prediction through Graph External Attention and Contrastive Learning
A contrastive GNN with external attention, pre-trained on ~100M molecules, improves multi-task ADMET prediction and shows prospective wet-lab agreement on three compounds.
-
WATS: Calibrating Graph Neural Networks with Wavelet-Aware Temperature Scaling
WATS uses heat-kernel graph wavelet features to predict node-specific temperatures for GNN calibration, reporting the lowest ECE on benchmark datasets, though hyperparameter selection uses test-set information.
Discussion (0). Sign in to comment.