Causal Concept Identification in Open World Environments

Moritz Willig, Matej Zečević, Jonas Seng, Florian Peter Busch
Proceedings of The First AAAI Bridge Program on Continual Causality, PMLR 208:52-58, 2023.

Abstract

The ability to continually discover novel concepts is a core task in open world learning. For classical learning tasks new samples might be identified via manual labeling. Since this is a labor intensive task, this paper proposes to utilize causal information for doing so. Image data provides us with the ability to directly observe the physical, real-world appearance of concepts. However, the information presented in images is usually of noisy and unstructured nature. In this position paper we propose to leverage causal information to both structure and causally connect visual representations. Specifically, we discuss the possibilities of using causal models as a knowledge source for identifying novel concepts in the visual domain.

Cite this Paper

BibTeX
@InProceedings{pmlr-v208-willig23a, title = {Causal Concept Identification in Open World Environments}, author = {Willig, Moritz and Ze\v{c}evi\'c, Matej and Seng, Jonas and Busch, Florian Peter}, booktitle = {Proceedings of The First AAAI Bridge Program on Continual Causality}, pages = {52--58}, year = {2023}, editor = {Mundt, Martin and Cooper, Keiland W. and Dhami, Devendra Singh and Ribeiro, Adéle and Smith, James Seale and Bellot, Alexis and Hayes, Tyler}, volume = {208}, series = {Proceedings of Machine Learning Research}, month = {07--08 Feb}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v208/willig23a/willig23a.pdf}, url = {https://proceedings.mlr.press/v208/willig23a.html}, abstract = {The ability to continually discover novel concepts is a core task in open world learning. For classical learning tasks new samples might be identified via manual labeling. Since this is a labor intensive task, this paper proposes to utilize causal information for doing so. Image data provides us with the ability to directly observe the physical, real-world appearance of concepts. However, the information presented in images is usually of noisy and unstructured nature. In this position paper we propose to leverage causal information to both structure and causally connect visual representations. Specifically, we discuss the possibilities of using causal models as a knowledge source for identifying novel concepts in the visual domain.} }
Endnote
%0 Conference Paper %T Causal Concept Identification in Open World Environments %A Moritz Willig %A Matej Zečević %A Jonas Seng %A Florian Peter Busch %B Proceedings of The First AAAI Bridge Program on Continual Causality %C Proceedings of Machine Learning Research %D 2023 %E Martin Mundt %E Keiland W. Cooper %E Devendra Singh Dhami %E Adéle Ribeiro %E James Seale Smith %E Alexis Bellot %E Tyler Hayes %F pmlr-v208-willig23a %I PMLR %P 52--58 %U https://proceedings.mlr.press/v208/willig23a.html %V 208 %X The ability to continually discover novel concepts is a core task in open world learning. For classical learning tasks new samples might be identified via manual labeling. Since this is a labor intensive task, this paper proposes to utilize causal information for doing so. Image data provides us with the ability to directly observe the physical, real-world appearance of concepts. However, the information presented in images is usually of noisy and unstructured nature. In this position paper we propose to leverage causal information to both structure and causally connect visual representations. Specifically, we discuss the possibilities of using causal models as a knowledge source for identifying novel concepts in the visual domain.
APA
Willig, M., Zečević, M., Seng, J. & Busch, F.P.. (2023). Causal Concept Identification in Open World Environments. Proceedings of The First AAAI Bridge Program on Continual Causality, in Proceedings of Machine Learning Research 208:52-58 Available from https://proceedings.mlr.press/v208/willig23a.html.

Related Material