Learning to Drop: Robust Graph Neural Network via Topological Denoising
arXiv:2011.07057
Abstract
Graph Neural Networks (GNNs) have shown to be powerful tools for graph analytics. The key idea is to recursively propagate and aggregate information along edges of the given graph. Despite their success, however, the existing GNNs are usually sensitive to the quality of the input graph. Real-world graphs are often noisy and contain task-irrelevant edges, which may lead to suboptimal generalization performance in the learned GNN models. In this paper, we propose PTDNet, a parameterized topological denoising network, to improve the robustness and generalization performance of GNNs by learning to drop task-irrelevant edges. PTDNet prunes task-irrelevant edges by penalizing the number of edges in the sparsified graph with parameterized networks. To take into consideration of the topology of the entire graph, the nuclear norm regularization is applied to impose the low-rank constraint on the resulting sparsified graph for better generalization. PTDNet can be used as a key component in GNN models to improve their performances on various tasks, such as node classification and link prediction. Experimental studies on both synthetic and benchmark datasets show that PTDNet can improve the performance of GNNs significantly and the performance gain becomes larger for more noisy datasets.
arXiv commentWSDM 2021
References in corpus (21)
- Community detection in graphs
- Semi-Supervised Classification with Graph Convolutional Networks
- Inductive Representation Learning on Large Graphs
- Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
- Categorical Reparameterization with Gumbel-Softmax
- Spectral Networks and Locally Connected Networks on Graphs
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- Graph Neural Networks: A Review of Methods and Applications
- Variational Graph Auto-Encoders
- DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
- FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
- Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
- How Powerful are Graph Neural Networks?
- Revisiting Semi-Supervised Learning with Graph Embeddings
- PairNorm: Tackling Oversmoothing in GNNs
- Adaptive Sampling Towards Fast Graph Representation Learning
- Deep Learning on Graphs: A Survey
- Learning Sparse Neural Networks through Regularization
- Adaptive Graph Convolutional Neural Networks
- A Unifying Framework for Spectrum-Preserving Graph Sparsification and Coarsening
- Uncovering Hierarchical Structure in Social Networks using Isospectral Reductions