Timezone: »

 
Oral
Domain Generalization using Causal Matching
Divyat Mahajan · Shruti Tople · Amit Sharma

Thu Jul 22 07:00 AM -- 07:20 AM (PDT) @
in Domain Generalization and Multi-task Learning »

In the domain generalization literature, a common objective is to learn representations independent of the domain after conditioning on the class label. We show that this objective is not sufficient: there exist counter-examples where a model fails to generalize to unseen domains even after satisfying class-conditional domain invariance. We formalize this observation through a structural causal model and show the importance of modeling within-class variations for generalization. Specifically, classes contain objects that characterize specific causal features, and domains can be interpreted as interventions on these objects that change non-causal features. We highlight an alternative condition: inputs across domains should have the same representation if they are derived from the same object. Based on this objective, we propose matching-based algorithms when base objects are observed (e.g., through data augmentation) and approximate the objective when objects are not observed (MatchDG). Our simple matching-based algorithms are competitive to prior work on out-of-domain accuracy for rotated MNIST, Fashion-MNIST, PACS, and Chest-Xray datasets. Our method MatchDG also recovers ground-truth object matches: on MNIST and Fashion-MNIST, top-10 matches from MatchDG have over 50% overlap with ground-truth matches.

Keywords: Algorithms · Multitask, Transfer, and Meta Learning

Author Information

Divyat Mahajan (Microsoft Research India)
Shruti Tople (Microsoft Research)
Amit Sharma (Microsoft Research)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors