VICE: Variational Interpretable Concept Embeddings
This work addresses the need for interpretable and reliable models of human concept representations in cognitive science, offering an incremental improvement over existing methods.
The paper tackled the problem of developing numerical models for mental representations of object concepts by introducing VICE, a variational Bayesian method that embeds concepts in a vector space using human data from a triplet odd-one-out task, resulting in representations that rival or outperform its predecessor SPoSE in predicting human behavior and are more reproducible.
A central goal in the cognitive sciences is the development of numerical models for mental representations of object concepts. This paper introduces Variational Interpretable Concept Embeddings (VICE), an approximate Bayesian method for embedding object concepts in a vector space using data collected from humans in a triplet odd-one-out task. VICE uses variational inference to obtain sparse, non-negative representations of object concepts with uncertainty estimates for the embedding values. These estimates are used to automatically select the dimensions that best explain the data. We derive a PAC learning bound for VICE that can be used to estimate generalization performance or determine a sufficient sample size for experimental design. VICE rivals or outperforms its predecessor, SPoSE, at predicting human behavior in the triplet odd-one-out task. Furthermore, VICE's object representations are more reproducible and consistent across random initializations, highlighting the unique advantage of using VICE for deriving interpretable embeddings from human behavior.