Abstract: Mechanisms are provided for fully homomorphic encryption enabled graph embedding. An encrypted graph data structure, having encrypted entities and predicates, is received and, for each encrypted entity, a corresponding set of entity ciphertexts is generated based on an initial embedding of entity features. For each encrypted predicate, a corresponding predicate ciphertext is generated based on an initial embedding of predicate features. A machine learning process is iteratively executed, on the sets of entity ciphertexts and the predicate ciphertexts, to update embeddings of the entity features of the encrypted entities and update embeddings of predicate features of the encrypted predicates, to generate a computer model for embedding entities and predicates. A final embedding is output based on the updated embeddings of the entity features and predicate features of the computer model.

Abstract: A computer-implemented method including: receiving a list of ciphertexts, wherein a majority of ciphertexts in the list homomorphically-encrypt zero values and a minority of ciphertexts in the list homomorphically-encrypt non-zero values; and compressing the list of ciphertexts to remove the ciphertexts which homomorphically-encrypt zero values, wherein: the compression is performed without knowledge on what each of the ciphertexts in the list encrypts, and the compression is based on homomorphic comparison of each of the ciphertexts in the list with a homomorphically-encrypted zero value, to determine which of the ciphertexts in the list to remove.