Systems and methods for predicting differentiating features

A method comprising:

• generating a first set of graph embeddings based on a first data entry of a plurality of first data entries representative of source data used for training a first machine learning model;
• generating a second set of graph embeddings based on a second data entry of a plurality of second data entries representative of predictive data generated using the first machine learning model;
• and
• processing, using a second machine learning model, the first set of graph embeddings and the second set of graph embeddings to identify at least one feature with a probability satisfying a threshold indicating a difference between the source training data and the predictive data.

One or more non-transitory, computer-readable media comprising instructions that, when executed by one or more processors, cause operations comprising:

• generating a first set of graph embeddings based on a first data entry of a plurality of first data entries representative of source data used for training a first machine learning model;
• generating a second set of graph embeddings based on a second data entry of a plurality of second data entries representative of predictive data generated using the first machine learning model;
• and
• processing, using a second machine learning model, the first set of graph embeddings and the second set of graph embeddings to identify at least one feature associated with a difference between the source training data and the predictive data.