Self-supervised learning can be made more robust to distribution shift by sampling mini-batches so that spurious background variables are independent of the anchor label, using a VAE and balancing-score matching.
Reformulation of OOD Generalization as Generalization on Task Distributions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
On the Out-of-Distribution Generalization of Self-Supervised Learning
Self-supervised learning can be made more robust to distribution shift by sampling mini-batches so that spurious background variables are independent of the anchor label, using a VAE and balancing-score matching.