Collaborative multitask and transfer learning for predicting properties with scarce data

A method of forming a model for predicting a property of an item, the method comprising:

• determining a plurality of datasets of properties, wherein the item is a material, and wherein the properties are material properties;
• training decoders and a common encoder utilizing the plurality of datasets of properties to generate models, wherein each decoder of the decoders is distinct from each other and is configured to model different properties, wherein the decoders include a first decoder and a second decoder, wherein each of the decoders is used to generate a respective model of the models, wherein the first decoder is configured to generate a first model and the second decoder is configured to generate a second model, wherein the common encoder is a compositionally restricted attention-based network, and, wherein the second decoder is trained using a loss function that considers the accuracy of the second model;
• generating a predicted property using a model of the models;
• and
• making the item using the predicted property,
• wherein limited data is available for the second decoder compared to the first decoder, and wherein the first decoder is trained using a first loss function which considers the accuracy of both the first model and second model.

An item produced by a process comprising:

• determining a plurality of datasets of properties, wherein the item is a material, and wherein the properties are material properties;
• training a common encoder and one or more individual decoders utilizing the plurality of datasets of properties, wherein each individual decoder of the one or more individual decoders is distinct from each other and is configured to model different properties, wherein the common encoder is a compositionally restricted attention-based network, wherein the one or more individual decoders includes a first decoder, wherein the first decoder is configured to generate a first model to predict a first predicted property;
• determining a transfer learning dataset for one or more properties;
• training a new decoder using the transfer learning dataset and the common encoder, wherein the new decoder is configured to generate a second model to predict a second predicted property, wherein more input data is available for the first decoder than the new decoder, wherein the new decoder is trained after the common encoder and the first decoder, and wherein the new decoder is trained using a loss function that considers the accuracy of the second model;
• generating a predicted property of the item using the common encoder and the new decoder;
• and
• making the item using the predicted property.