Learning to Drop: Robust Graph Neural Network via Topological Denoising

By Dongsheng Luo, Wei Cheng, Wenchao Yu, Bo Zong, Jingchao Ni, Haifeng Chen, Xiang Zhang. Web Search and Data Mining, 2020

323 citations recorded by the source corpus.

Graph Neural Networks (GNNs) have shown to be powerful tools for graph analytics. The key idea is to recursively propagate and aggregate information along the 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 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.

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics, Urban Studies

View Paper: https://www.semanticscholar.org/paper/7eaa067078c96b383f2f2e6f1543cd063c5d6d45

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xin Zhou
2. Liang Wang
3. Zhiqi Shen
4. Yanqiao Zhu
5. Qiang Liu
6. Shuhui Wang
7. Shu Wu
8. Jun Liu

In Statistical and Nonlinear Physics

1. Liang Wang
2. Yanqiao Zhu
3. Qiang Liu
4. Shu Wu
5. Michalis K. Titsias

Citations in the corpus

• A Tale of Two Graphs: Freezing and Denoising Graph Structures for Multimodal Recommendation (2022, background): “The former work [15, 22, 23, 27] leverages attention mechanisms or pre-defined functions to calculate a node’s attention or affinity scores with its neighbors.”
• Mining Latent Structures for Multimedia Recommendation (2021, methodology): “There are three categories of GSL methods: metric learning [5, 21, 36], probabilistic modeling [7, 24, 43], and direct optimization approaches [8, 16, 41].”