Multi-label Chaining with Imprecise Probabilities
This work addresses uncertainty handling in multi-label classification for domains requiring reliable predictions, though it is incremental as it builds on existing chaining and credal classifier methods.
The paper tackles the problem of multi-label classification under uncertainty by extending chaining methods to use imprecise probabilities, resulting in computationally efficient adaptations that produce cautious predictions on hard-to-predict instances where precise models fail.
We present two different strategies to extend the classical multi-label chaining approach to handle imprecise probability estimates. These estimates use convex sets of distributions (or credal sets) in order to describe our uncertainty rather than a precise one. The main reasons one could have for using such estimations are (1) to make cautious predictions (or no decision at all) when a high uncertainty is detected in the chaining and (2) to make better precise predictions by avoiding biases caused in early decisions in the chaining. We adapt both strategies to the case of the naive credal classifier, showing that this adaptations are computationally efficient. Our experimental results on missing labels, which investigate how reliable these predictions are in both approaches, indicate that our approaches produce relevant cautiousness on those hard-to-predict instances where the precise models fail.