Geometric graphs from data to aid classification tasks with graph convolutional networks
arXiv:2005.04081 · doi:10.1016/j.patter.2021.100237
Abstract
Traditional classification tasks learn to assign samples to given classes based solely on sample features. This paradigm is evolving to include other sources of information, such as known relations between samples. Here we show that, even if additional relational information is not available in the data set, one can improve classification by constructing geometric graphs from the features themselves, and using them within a Graph Convolutional Network. The improvement in classification accuracy is maximized by graphs that capture sample similarity with relatively low edge density. We show that such feature-derived graphs increase the alignment of the data to the ground truth while improving class separation. We also demonstrate that the graphs can be made more efficient using spectral sparsification, which reduces the number of edges while still improving classification performance. We illustrate our findings using synthetic and real-world data sets from various scientific domains.
arXiv commentPublished in Patterns; Date of Publication: 09 April 2021
References in corpus (11)
- Geometric deep learning: going beyond Euclidean data
- Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting
- Graph Convolutional Neural Networks for Web-Scale Recommender Systems
- Adversarial Attacks on Neural Networks for Graph Data
- DeepInf: Social Influence Prediction with Deep Learning
- Random Walks, Markov Processes and the Multiscale Modular Organization of Complex Networks
- Laplacian Dynamics and Multiscale Modular Structure in Networks
- Entangled networks, synchronization, and optimal network topology
- Network structure from rich but noisy data
- Graph-based data clustering via multiscale community detection
- Finding role communities in directed networks using Role-Based Similarity, Markov Stability and the Relaxed Minimum Spanning Tree