The classifier judged this item not relevant to AI security, so it is left out of lists, feeds, the API and dataset releases. If that is wrong, report a correction on this page.
Mitigating Negative Transfer via Reducing Environmental Disagreement
- Published
- Record updated
Summary
This study revisits negative transfer in Unsupervised Domain Adaptation (UDA) through causally disentangled learning. The authors argue that overreliance on non-causal environmental features causes cross-domain discriminative disagreement, which they call environmental disagreement. They propose Reducing Environmental Disagreement (RED), which adversarially trains domain-specific environmental feature extractors to separate domain-invariant causal features from domain-specific non-causal ones, then estimates and reduces the disagreement. Experiments reportedly show RED mitigates negative transfer and achieves state-of-the-art performance.
Mitigation
RED: disentangle each sample into domain-invariant causal features and domain-specific non-causal environmental features by adversarially training domain-specific environmental feature extractors in the opposite domains, then estimate and reduce environmental disagreement based on the domain-specific non-causal environmental features.