Unsupervised Hierarchical Concept Learning

Sumegh Roychowdhury, Sumedh Anand Sontakke, Mausoom Sarkar, Nikaash Puri, Milan Aggarwal, Pinkesh Badjatiya, Balaji Krishnamurthy, Laurent Itti

Keywords: hierarchical learning, unsupervised learning, unsupervised hierarchical learning, video representation learning, learning from demonstrations

Abstract: Discovering concepts (or temporal abstractions) in an unsupervised manner from demonstration data in the absence of an environment is an important problem. Organizing these discovered concepts hierarchically at different levels of abstraction is useful in discovering patterns, building ontologies, and generating tutorials from demonstration data. However, recent work to discover such concepts without access to any environment does not discover relationships (or a hierarchy) between these discovered concepts. In this paper, we present a Transformer-based concept abstraction architecture UNHCLE (pronounced uncle) that extracts a hierarchy of concepts in an unsupervised way from demonstration data. We empirically demonstrate how UNHCLE discovers meaningful hierarchies using datasets from Chess and Cooking domains. Finally, we show how UNHCLE learns meaningful language labels for concepts by using demonstration data augmented with natural language for cooking and chess. All of our code is available at https://github.com/UNHCLE/UNHCLE

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2010.02556/code)

Reviewed Version (pdf): https://openreview.net/references/pdf?id=UTBScyFLr5