System and method for diachronic machine learning architecture

A method for expanding a multi-relational data structure tunable for generating a non-linear dataset from a time-dependent query comprising:

• receiving the time-dependent query of the multi-relational data structure, the multi-relational data structure representing at least one tuple including entity nodes, a relation among the entity nodes, and time data associated with at least one entity node, wherein the time-dependent query includes at least one entity node at a queried time relative to the time data;
• obtaining, based on the time-dependent query, a temporal representation vector based on a diachronic embedding of the multi-relational data structure, wherein the diachronic embedding is based on a learnable parameter controlling proportions of at least one temporal feature to at least one persistent feature;
• determining, from the temporal representation vector, at least one time-varied score corresponding to the queried time;
• and
• generating a response dataset based on the at least one time-varied score determined from the temporal representation vector, the response dataset representing at least one added tuple previously unrepresented in the multi-relational data structure.

A non-transitory computer-readable medium or media having stored thereon machine interpretable instructions which, when executed by a processor, cause the processor to perform a computer-implemented method for expanding a multi-relational data structure tunable for generating a non-linear dataset from a time-dependent query, the method comprising:

• receiving a time-dependent query of the multi-relational data structure, the multi-relational data structure representing at least one tuple including entity nodes, a relation among the entity nodes, and time data associated with at least one entity node, wherein the time-dependent query includes at least one entity node at a queried time relative to the time data;
• obtaining, based on the time-dependent query, a temporal representation vector based on a diachronic embedding of the multi-relational data structure, wherein the diachronic embedding is based on a learnable parameter controlling proportions of at least one temporal feature to at least one persistent feature;
• determining, from the temporal representation vector, at least one time-varied score corresponding to the queried time;
• and
• generating a response dataset based on the at least one time-varied score determined from the temporal representation vector, the response dataset representing at least one added tuple previously unrepresented in the multi-relational data structure.