Robust Graph Representation Learning for Local Corruption Recovery
This work addresses graph representation learning robustness for applications sensitive to data quality, but it appears incremental as it builds on existing graph autoencoder methods.
The paper tackles the problem of local corruption in graph data by proposing a scheme that automatically detects and recovers robust embeddings, achieving excellent performance in experiments with black-box poisoning.
The performance of graph representation learning is affected by the quality of graph input. While existing research usually pursues a globally smoothed graph embedding, we believe the rarely observed anomalies are as well harmful to an accurate prediction. This work establishes a graph learning scheme that automatically detects (locally) corrupted feature attributes and recovers robust embedding for prediction tasks. The detection operation leverages a graph autoencoder, which does not make any assumptions about the distribution of the local corruptions. It pinpoints the positions of the anomalous node attributes in an unbiased mask matrix, where robust estimations are recovered with sparsity promoting regularizer. The optimizer approaches a new embedding that is sparse in the framelet domain and conditionally close to input observations. Extensive experiments are provided to validate our proposed model can recover a robust graph representation from black-box poisoning and achieve excellent performance.