Fig. 6
From: Evolving knowledge graph similarity for supervised learning in complex biomedical domains
WAF Boxplot using yeast datasets to training and testing. The labels of the plots are in format ’D1+D2_D3+D4’, where D1, D2, D3, D4 are the original datasets, D1+D2 is the training set that contains data from D1 and D2, and D3+D4 is the test set that contains data from D3 and D4. In the labels, the names of the datasets STRING-SC, BIND-SC, and DIP/MIPS-SC are abbreviated to “S”, “B”, and “D”, respectively