However, the cross-client edges naturally exist among clients.

GNNs to mitigate the bias as well as boost their utility in an end-to-end manner.

This prevailing paradigm heavily relies on the out-of-distribution (OOD) effect to influence the model's prediction.

Molecular representation learning lays the foundation for drug discovery. However, existing methods suffer from poor out-of-distribution (OOD) generalization, particularly when data for training and testing originate from different environments.

However, local attention limits the receptive field to one-hop neighbors.

However, such an approach is highly empirical and provides an indirect evaluation affected by external factors.