Publikation
Where is the Truth? The Risk of Getting Confounded in a Continual World
Florian Peter Busch; Roshni Kamath; Rupert Mitchell; Wolfgang Stammer; Kristian Kersting; Martin Mundt
In: Computing Research Repository eprint Journal (CoRR), Vol. abs/2402.06434, Pages 1-31, arXiv, 2024.
Zusammenfassung
A dataset is confounded if it is most easily solved
via a spurious correlation which fails to general-
ize to new data. In this work, we show that, in
a continual learning setting where confounders
may vary in time across tasks, the challenge of
mitigating the effect of confounders far exceeds
the standard forgetting problem normally consid-
ered. In particular, we provide a formal descrip-
tion of such continual confounders and identify
that, in general, spurious correlations are easily
ignored when training for all tasks jointly, but
it is harder to avoid confounding when they are
considered sequentially. These descriptions serve
as a basis for constructing a novel CLEVR-based
continually confounded dataset, which we term
the ConCon dataset. Our evaluations demonstrate
that standard continual learning methods fail to ig-
nore the dataset’s confounders. Overall, our work
highlights the challenges of confounding factors,
particularly in continual learning settings, and
demonstrates the need for developing continual
learning methods to robustly tackle these.