Probabilistic task modelling for meta-learning
This work addresses the challenge of task representation in meta-learning, which is incremental as it builds on existing probabilistic methods.
The authors tackled the problem of representing tasks in meta-learning by proposing a probabilistic task model that combines variational auto-encoding and latent Dirichlet allocation, resulting in improved task selection and relatedness inference for meta-learning algorithms.
We propose probabilistic task modelling -- a generative probabilistic model for collections of tasks used in meta-learning. The proposed model combines variational auto-encoding and latent Dirichlet allocation to model each task as a mixture of Gaussian distribution in an embedding space. Such modelling provides an explicit representation of a task through its task-theme mixture. We present an efficient approximation inference technique based on variational inference method for empirical Bayes parameter estimation. We perform empirical evaluations to validate the task uncertainty and task distance produced by the proposed method through correlation diagrams of the prediction accuracy on testing tasks. We also carry out experiments of task selection in meta-learning to demonstrate how the task relatedness inferred from the proposed model help to facilitate meta-learning algorithms.