Distributionally-robust heterogeneous graph neural networks via relation-aware grouping
Out-of-distribution (OOD) generalization remains a key challenge for heterogeneous graph neural networks (HGNNs), which often exhibit substantial performance degradation under real-world distribution shifts. While Group Distributionally Robust Optimization (GroupDRO) has proven effective in promoting OOD generalization...
Yunfei Wang, Yanghui Fu, Shixuan Liu et al.
· Information Processing & Man... · 0 citations