Conformal Credal Self-Supervised Learning

J. Lienen, C. Demir, E. Hüllermeier, ArXiv:2205.15239 (2022).

Preprint | English
In semi-supervised learning, the paradigm of self-training refers to the idea of learning from pseudo-labels suggested by the learner itself. Across various domains, corresponding methods have proven effective and achieve state-of-the-art performance. However, pseudo-labels typically stem from ad-hoc heuristics, relying on the quality of the predictions though without guaranteeing their validity. One such method, so-called credal self-supervised learning, maintains pseudo-supervision in the form of sets of (instead of single) probability distributions over labels, thereby allowing for a flexible yet uncertainty-aware labeling. Again, however, there is no justification beyond empirical effectiveness. To address this deficiency, we make use of conformal prediction, an approach that comes with guarantees on the validity of set-valued predictions. As a result, the construction of credal sets of labels is supported by a rigorous theoretical foundation, leading to better calibrated and less error-prone supervision for unlabeled data. Along with this, we present effective algorithms for learning from credal self-supervision. An empirical study demonstrates excellent calibration properties of the pseudo-supervision, as well as the competitiveness of our method on several benchmark datasets.
Publishing Year
Journal Title

Cite this

Lienen J, Demir C, Hüllermeier E. Conformal Credal Self-Supervised Learning. arXiv:220515239. Published online 2022.
Lienen, J., Demir, C., & Hüllermeier, E. (2022). Conformal Credal Self-Supervised Learning. In arXiv:2205.15239.
@article{Lienen_Demir_Hüllermeier_2022, title={Conformal Credal Self-Supervised Learning}, journal={arXiv:2205.15239}, author={Lienen, Julian and Demir, Caglar and Hüllermeier, Eyke}, year={2022} }
Lienen, Julian, Caglar Demir, and Eyke Hüllermeier. “Conformal Credal Self-Supervised Learning.” ArXiv:2205.15239, 2022.
J. Lienen, C. Demir, and E. Hüllermeier, “Conformal Credal Self-Supervised Learning,” arXiv:2205.15239. 2022.
Lienen, Julian, et al. “Conformal Credal Self-Supervised Learning.” ArXiv:2205.15239, 2022.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]

Link(s) to Main File(s)
Access Level
Restricted Closed Access


Marked Publications

Open Data LibreCat

Search this title in

Google Scholar