SYSTEMS AND METHODS FOR LEARNING HUMAN-UNDERSTANDABLE LOGICAL RULES FROM DATA

Systems and methods for learning and applying a rule set from relational data include receiving a graph representing relational data, wherein nodes represent elements of the graph, and edges represent relationships between nodes, generating an intermediate representation of the graph by mapping features of the nodes and edges of the graph to an intermediate vector representation, wherein the intermediate vector representation contains binary values and/or probabilistic values, learning logical rules that define the nodes and edges of the graph based on the intermediate vector representation r by: defining a maximum satisfiability (MAX-SAT) problem for the graph; and estimating a gradient around a solution of the MAX-SAT problem for the graph to produce the logical rules; and applying the logical rules to a new graph.