Contrastive Meta-Learning for Partially Observable Few-Shot Learning
This addresses the challenge of few-shot learning with incomplete data for AI systems, though it appears incremental as it builds on existing contrastive and meta-learning frameworks.
The paper tackles the problem of learning unified representations from partial observations where features may only appear in some views, and introduces Partial Observation Experts Modelling (POEM) to meta-learn consistent representations, showing benefits over other meta-learning methods on an adapted Meta-Dataset benchmark.
Many contrastive and meta-learning approaches learn representations by identifying common features in multiple views. However, the formalism for these approaches generally assumes features to be shared across views to be captured coherently. We consider the problem of learning a unified representation from partial observations, where useful features may be present in only some of the views. We approach this through a probabilistic formalism enabling views to map to representations with different levels of uncertainty in different components; these views can then be integrated with one another through marginalisation over that uncertainty. Our approach, Partial Observation Experts Modelling (POEM), then enables us to meta-learn consistent representations from partial observations. We evaluate our approach on an adaptation of a comprehensive few-shot learning benchmark, Meta-Dataset, and demonstrate the benefits of POEM over other meta-learning methods at representation learning from partial observations. We further demonstrate the utility of POEM by meta-learning to represent an environment from partial views observed by an agent exploring the environment.