Concepterror gap

Error Gap

The difference in prediction error between two models, used to quantify the contribution of a given mechanism, such as parameter sharing or graph structure, to model performance.

Timeline (last 90 days)

Oct 27

On the feeder data, parameter sharing recovers about two-thirds of the error gap between node-specific models and the GNN (relative to the regularized baseline).

Unverified50%

All Facts (1)

Unverified

On the feeder data, parameter sharing recovers about two-thirds of the error gap between node-specific models and the GNN (relative to the regularized baseline).

50%

Source Articles

GNN Power Load Forecasting: A Diagnostic Protocol to Disentangle Parameter Sharing from Neighbor AccessOct 27