Towards a Unifying Framework for Formal Theories of Novelty
DOI:
https://doi.org/10.1609/aaai.v35i17.17766Keywords:
Novelty, Out-of-distribution Detection, Open-set, Open-worldAbstract
Managing inputs that are novel, unknown, or out-of-distribution is critical as an agent moves from the lab to the open world. Novelty-related problems include being tolerant to novel perturbations of the normal input, detecting when the input includes novel items, and adapting to novel inputs. While significant research has been undertaken in these areas, a noticeable gap exists in the lack of a formalized definition of novelty that transcends problem domains. As a team of researchers spanning multiple research groups and different domains, we have seen, first hand, the difficulties that arise from ill-specified novelty problems, as well as inconsistent definitions and terminology. Therefore, we present the first unified framework for formal theories of novelty and use the framework to formally define a family of novelty types. Our framework can be applied across a wide range of domains, from symbolic AI to reinforcement learning, and beyond to open world image recognition. Thus, it can be used to help kick-start new research efforts and accelerate ongoing work on these important novelty-related problems.Downloads
Published
2021-05-18
How to Cite
Boult, T., Grabowicz, P., Prijatelj, D., Stern, R., Holder, L., Alspector, J., M. Jafarzadeh, M., Ahmad, T., Dhamija, A., Li, C., Cruz, S., Shrivastava, A., Vondrick, C., & Walter, S. (2021). Towards a Unifying Framework for Formal Theories of Novelty. Proceedings of the AAAI Conference on Artificial Intelligence, 35(17), 15047-15052. https://doi.org/10.1609/aaai.v35i17.17766
Issue
Section
Senior Member Presentation: Blue Sky Papers