TABLE IV. Ablation Studies on Model Hyperparameters.

Various Hyperparameters Were Varied to Evaluate Their Effect on the Overall Model Performance. All the Models Were Trained and Evaluated Using a Portion of Data From the Cptac Cohort, and Model Accuracy was Reported on the Left-Out Cptac Cases (Last Column). the MLP Dimension of the Model was 128. We Used Wsis with 20× Magnification for all Cases. We Used Non Overlapping Patches for All Cases Except for *. the Batch Size Used was 8 Except for †. for all These Studies, the Cptac Data was Randoly Divided in 7:3 Ratio, Where 70% Data was Used for Training and the Rest for Testing

Model configuration				Graph configuration		Accuracy
Hidden dimension	GCN layer	Transformer block	min-cut node	patch size	node connectivity
128	3	3	120	512	8	0.925
128	3	3	100	512	8	0.915
128	3	3	80	512	8	0.903
128	1	3	100	512	8	0.908
128	3	6	100	512	8	0.894
128	1	6	100	512	8	0.919
128	1	6	80	512	8	0.906
128	1	6	120	512	8	0.898
128	1	3	120	512	8	0.911
64	3	3	120	512	8	0.908
64	1	3	100	512	8	0.903
64	1	6	100	512	8	0.913
64	3	3	100	512	8	0.901
64	3	6	100	512	8	0.901
128	3	3	120	512	4	0.896
128	3	3	120	512*	8	0.881
128	3	3	120	1024	8	0.864
128	3	3	120	360	8	0.898†

^*patches have overlap (10%).

^†Batch size is 2 due to memory limitation.