Abstract: A method for determining negative samples for training a knowledge graph embedding of a knowledge graph enhanced by an ontology including at least one constraint for distinguishing a fact of the knowledge graph from a spurious fact. The method comprises determining embedding predicted triples; determining a set of triples that comprises a triple of the knowledge graph and at least one of the predicted triples that are inconsistent with respect to the ontology; determining from the set of triples a replacement entity for the object entity in the at least one triple of the predicted triples; and determining the negative sample to comprise the relation, the subject entity and the replacement entity, or determining from the subset a replacement entity for the subject entity in the at least one triple of the predicted triples and determining the negative sample to comprise the relation, the object entity, and the replacement entity.

Abstract: A device, computer implemented method, computer program and non-transitory computer-readable storage, for automatically generating negative samples for training a knowledge graph embedding model, The method includes providing at least one first triple, the first triple is a true triple of a knowledge graph, providing at least one second triple, training the knowledge graph embedding model to predict triples of the knowledge graph depending on a set of triples comprising the at least one first triple and the at least one second triple, determining vector representations of entities and relations with the knowledge graph embedding model, determining a plurality of triples with the vector representations of entities and relations, providing an ontology comprising constraints that characterize correct triples, determining with the ontology at least one triple that violates at least one constraint of the constraints or that violates a combination of at least some of the constraints.

Abstract: One embodiment provides a method, including: identifying an application executing across a plurality of processors, wherein the application generates communication messages between the plurality of processors; collecting, using a profiler, a plurality of samples of the messages, wherein the plurality of samples are collected at a predetermined sampling rate and wherein the collecting comprises interrupting the execution of the application to collect a sample; determining, using an adaptive sampling technique, if the sampling rate comprises a sampling rate that is sufficiently low while meeting a predetermined quality threshold; adjusting, based upon the sampling rate not comprising a sampling rate that is sufficiently low, the sampling rate, and then collecting samples until the sampling rate comprises the sampling rate that is sufficiently low while meeting a predetermined quality threshold; and building, using the collected samples, an output performance profile of the application.