Differentiable Graph Module (DGM) for Graph Convolutional Networks

Abstract

Graph deep learning has recently emerged as a powerful ML concept allowing to generalize successful deep neural architectures to non-Euclidean structured data. Such methods have shown promising results on a broad spectrum of applications ranging from social science, biomedicine, and particle physics to computer vision, graphics, and chemistry. One of the limitations of the majority of current graph neural network architectures is that they are often restricted to the transductive setting and rely on the assumption that the underlying graph is {\em known} and {\em fixed}. Often, this assumption is not true since the graph may be noisy, or partially and even completely unknown. In such cases, it would be helpful to infer the graph directly from the data, especially in inductive settings where some nodes were not present in the graph at training time. Furthermore, learning a graph may become an end in itself, as the inferred structure may provide complementary insights next to the downstream task. In this paper, we introduce Differentiable Graph Module (DGM), a learnable function that predicts edge probabilities in the graph which are optimal for the downstream task. DGM can be combined with convolutional graph neural network layers and trained in an end-to-end fashion. We provide an extensive evaluation of applications from the domains of healthcare (disease prediction), brain imaging (age prediction), computer graphics (3D point cloud segmentation), and computer vision (zero-shot learning). We show that our model provides a significant improvement over baselines both in transductive and inductive settings and achieves state-of-the-art results.

References in corpus (6)

• Semi-Supervised Classification with Graph Convolutional Networks
• Hyperbolic Geometry of Complex Networks
• Hyperbolic Graph Convolutional Neural Networks
• Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings
• Kernel Operations on the GPU, with Autodiff, without Memory Overflows
• Latent-Graph Learning for Disease Prediction

Cited by in corpus (21)

• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
• Mining Latent Structures for Multimedia Recommendation
• A Tale of Two Graphs: Freezing and Denoising Graph Structures for Multimodal Recommendation
• Rethinking Graph Transformers with Spectral Attention
• Latent-Graph Learning for Disease Prediction
• Learning physical properties of anomalous random walks using graph neural networks
• Brain Networks and Intelligence: A Graph Neural Network Based Approach to Resting State fMRI Data
• Understanding over-squashing and bottlenecks on graphs via curvature
• Graph Deep Learning for Time Series Forecasting
• SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks
• Pointer Graph Networks
• Beltrami Flow and Neural Diffusion on Graphs
• GNN-LoFI: a Novel Graph Neural Network through Localized Feature-based Histogram Intersection
• Beyond Euclid: An Illustrated Guide to Modern Machine Learning with Geometric, Topological, and Algebraic Structures
• Balanced Graph Structure Information for Brain Disease Detection
• GraphFM: Graph Factorization Machines for Feature Interaction Modeling
• Utilising Graph Machine Learning within Drug Discovery and Development
• My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control
• Deep Dynamic Effective Connectivity Estimation from Multivariate Time Series
• Refined Causal Graph Structure Learning via Curvature for Brain Disease Classification
• Exploring Graph Classification Techniques Under Low Data Constraints: A Comprehensive Study