Multitask Learning over Shared Subspaces

Abstract This paper uses constructs from machine learning to define pairs of learning tasks that either shared or did not share a common subspace. Human subjects then learnt these tasks using a feedback-based approach. We found, as hypothesised, that subject performance was significantly higher on the second task if it shared the same subspace as the first. Additionally, accuracy was positively correlated over subjects learning same-subspace tasks, and negatively correlated for those learning different-subspace tasks. These results were compared to the behaviour of a Neural Network model trained using sequential Bayesian learning. Human performance was found to be consistent with a minimal capacity variant of this model. Networks with an increased representational capacity, and networks without Bayesian learning, did not show these transfer effects. We propose that the concept of shared subspaces provides a useful framework for the experimental study of human multitask and transfer learning. Author summaryHow does knowledge gained from previous experience affect learning of new tasks ? This question of “Transfer Learning” has been addressed by teachers, psychologists, and more recently by researchers in the fields of neural networks and machine learning. Leveraging constructs from machine learning, we designed pairs of learning tasks that either shared or did not share a common subspace. We compared the dynamics of transfer learning in humans with those of a multitask neural network model, finding that human performance was consistent with a minimal capacity variant of the model. Learning was boosted in the second task if the same subspace was shared between tasks. Additionally, accuracy between tasks was positively correlated but only when they shared the same subspace. Our results highlight the roles of subspaces, showing how they could act as a learning boost if shared, and be detrimental if not.