Where is the Truth? The Risk of Getting Confounded in a Continual World
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915340054691840 |
|---|---|
| author | Busch, Florian Peter Kamath, Roshni Mitchell, Rupert Stammer, Wolfgang Kersting, Kristian Mundt, Martin |
| author_facet | Busch, Florian Peter Kamath, Roshni Mitchell, Rupert Stammer, Wolfgang Kersting, Kristian Mundt, Martin |
| contents | A dataset is confounded if it is most easily solved via a spurious correlation, which fails to generalize 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 considered. In particular, we provide a formal description 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 ignore 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_06434 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Where is the Truth? The Risk of Getting Confounded in a Continual World Busch, Florian Peter Kamath, Roshni Mitchell, Rupert Stammer, Wolfgang Kersting, Kristian Mundt, Martin Machine Learning A dataset is confounded if it is most easily solved via a spurious correlation, which fails to generalize 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 considered. In particular, we provide a formal description 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 ignore 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. |
| title | Where is the Truth? The Risk of Getting Confounded in a Continual World |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2402.06434 |