Is ```observe_class_IL_batch``` function considering inter-edge connections in ```pipeline_class_IL_no_inter_edge_minibatch```?

[arnabkmondal]

In the observe_class_IL_batch function of ergnn_model.py while sampling the subgraph corresponding to task id t > 0 the code seems to sample the subgraph from the entire dataset. However,

1. The entire graph should not be available for any task ID during training.
2. It may include inter-task edges between different task IDs already existing in the dataset.

Therefore, this code seems to take an extra advantage in the class incremental setting without inter-edge connections in pipeline_class_IL_no_inter_edge_minibatch.

Can you please clarify our concern?

[QueuQ]

Thanks for the question,

CGLB/NCGL/Backbones/utils.py

Lines 136 to 137 in f514016

	if remove_edges:
	# to facilitate the methods like ER-GNN to only retrieve nodes

In the line above, the remove_edge is used to remove the edges from the retrived subgraphs, therefore the inter-task edges will not participate in methods like ergnn.

Besides, it is true that the entire graph should not be available during training. The code you quoted only retrived the stored node ids, which means only these buffered node ids are available for memory replay. Therefore, although the model retrives the nodes from the datasets everytime for memory replay, since it only gets the previously stored ids, it is same as storing the nodes and does not access the entire datasets anymore.