Timezone: »

A Closer Look at Distribution Shifts and Out-of-Distribution Generalization on Graphs
Mucong Ding · Kezhi Kong · Jiuhai Chen · John Kirchenbauer · Micah Goldblum · David P Wipf · Furong Huang · Tom Goldstein

Mon Dec 13 12:30 PM -- 12:40 PM (PST) @ None
Event URL: https://openreview.net/forum?id=XvgPGWazqRH »

Distribution shifts, in which the training distribution differs from the testing distribution, can significantly degrade the performance of Graph Neural Networks (GNNs). We curate GDS, a benchmark of eight datasets reflecting a diverse range of distribution shifts across graphs. We observe that: (1) most domain generalization algorithms fail to work when applied to domain shifts on graphs; and (2) combinations of powerful GNN models and augmentation techniques usually achieve the best out-of-distribution performance. These emphasize the need for domain generalization algorithms tailored for graphs and further graph augmentation techniques that enhance the robustness of predictors.

Author Information

Mucong Ding (Department of Computer Science, University of Maryland, College Park)
Kezhi Kong (University of Maryland, College Park)
Jiuhai Chen (University of Maryland, College Park)
John Kirchenbauer (University of Maryland, College Park)
Micah Goldblum (University of Maryland)
David P Wipf (AWS)
Furong Huang (University of Maryland)

Furong Huang is an assistant professor of computer science. Huang’s research focuses on machine learning, high-dimensional statistics and distributed algorithms—both the theoretical analysis and practical implementation of parallel spectral methods for latent variable graphical models. Some applications of her research include developing fast detection algorithms to discover hidden and overlapping user communities in social networks, learning convolutional sparse coding models for understanding semantic meanings of sentences and object recognition in images, healthcare analytics by learning a hierarchy on human diseases for guiding doctors to identify potential diseases afflicting patients, and more. Huang recently completed a postdoctoral position at Microsoft Research in New York.

Tom Goldstein (Rice University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors