Machine learning for optimized learning of human-understandable logical rules from medical or other data

A computing device configured for learning and applying a rule set from relational data, the device comprising:

• one or more processors;
• and
• a memory storing instructions, wherein the instructions when executed by the one or more processors cause the network device to implement a machine learning method of learning and applying a rule set from relational data, the method comprising:
• receiving a graph representing relational data, wherein nodes represent elements of the graph, and edges represent relationships between nodes;
• learning optimized logical rules that define the nodes and edges of the graph 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 generate an intermediate representation of the graph by mapping features of the nodes and edges of the graph to an intermediate vector representation, and to produce the optimized logical rules;
• and
• applying the optimized logical rules to a new graph.

A machine learning method, the method comprising:

• extracting information from a graph that has learned logical rules applied thereto for a machine learning task, the learned logical rules having been determined by a machine learning process implemented on an initial graph representing relational data by:
• defining a maximum satisfiability (MAX-SAT) problem for the initial graph, wherein nodes represent elements of the initial graph, and edges represent relationships between nodes;
• and
• estimating a gradient around a solution of the MAX-SAT problem for the initial graph to generate an intermediate representation of the initial graph by mapping features of the nodes and edges of the initial graph to an intermediate vector representation, and to produce the learned logical rules.