Simple GNN Regularisation for 3D Molecular Property Prediction & Beyond
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.
Code (1)
Tasks
DenoisingDiversityGraph Property PredictionInitial Structure to Relaxed Energy (IS2RE)Molecular Property PredictionPredictionProperty PredictionStructured PredictionSimilar Papers 제목 키워드 기반
Simple GNN Regularisation for 3D Molecular Property Prediction and Beyond
Graph Neural Networks (GNNs) have been proven effective across a wide range of molecular property prediction and structured learning problems. However, their efficiency is known to be hindered by practical challenges suc…
Initial Structure to Relaxed Energy (IS2RE), DirectMolecular Property PredictionProperty PredictionGated Graph Recursive Neural Networks for Molecular Property Prediction
Molecule property prediction is a fundamental problem for computer-aided drug discovery and materials science. Quantum-chemical simulations such as density functional theory (DFT) have been widely used for calculating th…
Drug DiscoveryMolecular Property PredictionPredictionProperty PredictionOn Sparsity in Overparametrised Shallow ReLU Networks
The analysis of neural network training beyond their linearization regime remains an outstanding open question, even in the simplest setup of a single hidden-layer. The limit of infinitely wide networks provides an appea…
Open-Ended Question AnsweringKnown Unknowns: Out-of-Distribution Property Prediction in Materials and Molecules
Discovery of high-performance materials and molecules requires identifying extremes with property values that fall outside the known distribution. Therefore, the ability to extrapolate to out-of-distribution (OOD) proper…
Known UnknownsProperty PredictionImproving VAE based molecular representations for compound property prediction
Collecting labeled data for many important tasks in chemoinformatics is time consuming and requires expensive experiments. In recent years, machine learning has been used to learn rich representations of molecules using …
BIG-bench Machine LearningPredictionProperty Prediction