Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.24044 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909873617240064 |
|---|---|
| author | Sun, Hui Xie, Zheng He, Hao-Yuan Li, Ming |
| author_facet | Sun, Hui Xie, Zheng He, Hao-Yuan Li, Ming |
| contents | Unsupervised Domain Adaptation~(UDA) focuses on transferring knowledge from a labeled source domain to an unlabeled target domain, addressing the challenge of \emph{domain shift}. Significant domain shifts hinder effective knowledge transfer, leading to \emph{negative transfer} and deteriorating model performance. Therefore, mitigating negative transfer is essential. This study revisits negative transfer through the lens of causally disentangled learning, emphasizing cross-domain discriminative disagreement on non-causal environmental features as a critical factor. Our theoretical analysis reveals that overreliance on non-causal environmental features as the environment evolves can cause discriminative disagreements~(termed \emph{environmental disagreement}), thereby resulting in negative transfer. To address this, we propose Reducing Environmental Disagreement~(RED), which disentangles each sample into domain-invariant causal features and domain-specific non-causal environmental features via adversarially training domain-specific environmental feature extractors in the opposite domains. Subsequently, RED estimates and reduces environmental disagreement based on domain-specific non-causal environmental features. Experimental results confirm that RED effectively mitigates negative transfer and achieves state-of-the-art performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_24044 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Mitigating Negative Transfer via Reducing Environmental Disagreement Sun, Hui Xie, Zheng He, Hao-Yuan Li, Ming Machine Learning Unsupervised Domain Adaptation~(UDA) focuses on transferring knowledge from a labeled source domain to an unlabeled target domain, addressing the challenge of \emph{domain shift}. Significant domain shifts hinder effective knowledge transfer, leading to \emph{negative transfer} and deteriorating model performance. Therefore, mitigating negative transfer is essential. This study revisits negative transfer through the lens of causally disentangled learning, emphasizing cross-domain discriminative disagreement on non-causal environmental features as a critical factor. Our theoretical analysis reveals that overreliance on non-causal environmental features as the environment evolves can cause discriminative disagreements~(termed \emph{environmental disagreement}), thereby resulting in negative transfer. To address this, we propose Reducing Environmental Disagreement~(RED), which disentangles each sample into domain-invariant causal features and domain-specific non-causal environmental features via adversarially training domain-specific environmental feature extractors in the opposite domains. Subsequently, RED estimates and reduces environmental disagreement based on domain-specific non-causal environmental features. Experimental results confirm that RED effectively mitigates negative transfer and achieves state-of-the-art performance. |
| title | Mitigating Negative Transfer via Reducing Environmental Disagreement |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2510.24044 |