Developing scalable solutions for training Graph Neural Networks (GNNs) for link prediction tasks is challenging due to the high data dependencies which entail high computational cost and huge memory footprint.
Furthermore, the expressivity of the learned representation depends on the quality of negative samples used during training.
Knowledge graph embedding methods learn embeddings of entities and relations in a low dimensional space which can be used for various downstream machine learning tasks such as link prediction and entity matching.
Network representation learning (NRL) is crucial in the area of graph learning.
Sparse and irregularly sampled multivariate time series are common in clinical, climate, financial and many other domains.
A person ontology comprising concepts, attributes and relationships of people has a number of applications in data protection, didentification, population of knowledge graphs for business intelligence and fraud prevention.
Entity Type Classification can be defined as the task of assigning category labels to entity mentions in documents.
Enterprises operate large data lakes using Hadoop and Spark frameworks that (1) run a plethora of tools to automate powerful data preparation/transformation pipelines, (2) run on shared, large clusters to (3) perform many different analytics tasks ranging from model preparation, building, evaluation, and tuning for both machine learning and deep learning.
Specification alternatives range from ML algorithms expressed in domain-specific languages (DSLs) with optimization for performance, to ML task (learning problem) specifications with optimization for performance and accuracy.