Abstract: Multi-modal machine-learning model training techniques for search are described that overcome conventional challenges and inefficiencies to support real time output, which is not possible in conventional training techniques. In one example, a search system is configured to support multi-modal machine-learning model training. This includes use of a preview mode and an expanded mode. In the preview mode, a preview segment is generated as part of real time training of a machine learning model. In the expanded mode, the preview segment is persisted as an expanded segment that is used to train and utilize an expanded machine-learning model as part of search.

Abstract: Machine-learning model retargeting techniques are described. In one example, training data is generated by extrapolating feedback data collected from entities. These techniques supports an ability to identify a wider range of thresholds and corresponding entities than those available in the feedback data. This also provides an opportunity to explore additional thresholds than those used in the past through extrapolating operations outside of a range used to define a segment, for which, the feedback data is captured. These techniques also support retargeting of a machine-learning model for a secondary label that is different than a primary label used to initially train the machine-learning model.

Abstract: Multi-modal machine-learning model training techniques for search are described that overcome conventional challenges and inefficiencies to support real time output, which is not possible in conventional training techniques. In one example, a search system is configured to support multi-modal machine-learning model training. This includes use of a preview mode and an expanded mode. In the preview mode, a preview segment is generated as part of real time training of a machine learning model. In the expanded mode, the preview segment is persisted as an expanded segment that is used to train and utilize an expanded machine-learning model as part of search.

Abstract: This disclosure relates to enforcing restrictions on data collected from a first set of systems and disseminated to a second set of systems. For example, enforcing a set of restrictions includes receiving a first trait and a second trait that include data describing a user that has interacted with an online service. The first trait is labelled with a first usage restriction and the second trait is labelled with a second usage restriction different from the first usage restriction. The first trait and the second trait are combined into a segment. The segment preserves labelling of the first trait with the first usage restriction and the second trait with the second usage restriction. Use of the segment is controlled based on the first usage restriction and the second usage restriction.

Abstract: This disclosure relates to enforcing restrictions on data collected from a first set of systems and disseminated to a second set of systems. For example, enforcing a set of restrictions includes receiving a first trait and a second trait that include data describing a user that has interacted with an online service. The first trait is labelled with a first usage restriction and the second trait is labelled with a second usage restriction different from the first usage restriction. The first trait and the second trait are combined into a segment. The segment preserves labelling of the first trait with the first usage restriction and the second trait with the second usage restriction. Use of the segment is controlled based on the first usage restriction and the second usage restriction.

Abstract: This disclosure relates to enforcing restrictions on data collected from a first set of systems and disseminated to a second set of systems. For example, a method for enforcing a set of restrictions includes receiving a first trait and a second trait that include data describing a user that has interacted with an online service. The first trait is labelled with a first usage restriction and the second trait is labelled with a second usage restriction different from the first usage restriction. The method further includes combining the first trait and the second trait into a segment. The segment preserves labelling of the first trait with the first usage restriction and the second trait with the second usage restriction. The method further includes controlling use of the segment based on the first usage restriction and the second usage restriction.

Abstract: This disclosure relates to enforcing restrictions on data collected from a first set of systems and disseminated to a second set of systems. For example, a method for enforcing a set of restrictions includes receiving a first trait and a second trait that include data describing a user that has interacted with an online service. The first trait is labelled with a first usage restriction and the second trait is labelled with a second usage restriction different from the first usage restriction. The method further includes combining the first trait and the second trait into a segment. The segment preserves labelling of the first trait with the first usage restriction and the second trait with the second usage restriction. The method further includes controlling use of the segment based on the first usage restriction and the second usage restriction.