Introduces replay-based continual learning with sequential invariance alignment to learn domain-invariant representations, outperforming baselines on generalization to unseen domains across six datasets in vision, medicine, manufacturing, and ecology.
arXiv preprint arXiv:2403.10834 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
S²PLR identifies a safe subspace for reliable pseudo-labels in source-free graph domain adaptation using semantic committee signals and structural contrastive verification, then applies noise-tolerant regularization to uncertain samples.
citing papers explorer
-
Continual Learning of Domain-Invariant Representations
Introduces replay-based continual learning with sequential invariance alignment to learn domain-invariant representations, outperforming baselines on generalization to unseen domains across six datasets in vision, medicine, manufacturing, and ecology.
-
Safe-Subspace Pseudo-Label Refinement for Source-Free Graph Domain Adaptation
S²PLR identifies a safe subspace for reliable pseudo-labels in source-free graph domain adaptation using semantic committee signals and structural contrastive verification, then applies noise-tolerant regularization to uncertain samples.