Algorithm 1 Error detection on medical knowledge graphs via intrinsic label information

Input: Knowledge graph $\mathcal{G}$ with noise Output: KG embeddings and confidence score   1:Initialize network parameters,   2:Construct a triplet-level and a hyper-view KG as per Definitions 2 and 3, respectively.   3:while not converged do   4:   for each $(h,r,t)$∈ S do   5:   Modeling the local structural information of triplets as defined in Equation (1),   6:   Extract the intrinsic label information in hyper-view and then compute the importance score of triplets as defined in Equation (6),   7:   Acquire the representation in hyper-view GAT in Equation (9),   8:   Compute the KG embedding distance in Equation (10) and global triplet embedding distance in Equation (11). Combined with a trade-off parameter $\lambda$ and obtain the joint loss in Equation (13).   9:end while 10:Compute the confidence score as defined in Equation (14).