Abstract: Embodiments regard a system for inference and corresponding action. A method includes receiving, from one or more sensors, measurements of evidence of existence of an event of interest, providing, to a model that operates using a type-2 probability and encodes probabilistic rules, the measurements of the evidence, providing, by the model and responsive to the measurements of the evidence, an output indicating a likelihood the event of interest exists, and altering, based on a communication from an operator, an object in a geographical region of the event of interest.

Abstract: Discussed herein are devices, systems, and methods for determining an approximation of a set of largest maximal cliques containing each node, entities represented by nodes and pairwise relation represented by edges. The method can include receiving dynamic graph data indicating the nodes and the edges of a dynamic graph, estimating, for one or more nodes of the nodes, cliques of size less than (or equal to) a user specified or default clique size parameter, storing the estimated cliques in a clique variable, identifying, for cliques of size greater than (or equal to) the clique size parameter, at most a single clique of a corresponding size, storing the identified single clique in the clique variable, and returning, for each node, the largest maximal cliques in the clique variable.

Abstract: Discussed herein are devices, systems, and methods for unsupervised pattern discovery using continuous-time dynamic graphs. A method can include receiving, from a graph neural network (GNN), source node embeddings and destination node embeddings, clustering the destination node embeddings generated by the GNN resulting in first groups of destination node embeddings, removing, from the destination node embeddings, embeddings from a noise group of the first groups resulting in signal destination node embeddings, clustering the signal destination node embeddings resulting in second groups of destination node embeddings, and identifying a pattern in the destination node embeddings and source node embeddings based on the second groups of destination node embeddings, the source node embeddings, and the destination node embeddings.

Abstract: Discussed herein are devices, systems, and methods for more flexible temporal graph network (TGN) graph interaction. A method includes executing first and second temporal graph networks (TGNs) to generate embeddings of respective first and second dynamic graphs, storing, as respective edge features of a first node of the first graph and a second node of the second graph, a memory state vector of the first node and a memory state vector of the second node, and determining, based on the embeddings and the edge features, a likelihood of an edge between nodes of the first graph.