paper-with-me

Papers

Matching Distributions between Model and Data: Cross-domain Knowledge Distillation for Unsupervised Domain Adaptation

2021-08-01 · ACL 2021 5 · Bo Zhang, XiaoMing Zhang, Yun Liu, Lei Cheng, Zhoujun Li

Unsupervised Domain Adaptation (UDA) aims to transfer the knowledge of source domain to the unlabeled target domain. Existing methods typically require to learn to adapt the target model by exploiting the source data and sharing the network architecture across domains. However, this pipeline makes the source data risky and is inflexible for deploying the target model. This paper tackles a novel setting where only a trained source model is available and different network architectures can be adapted for target domain in terms of deployment environments. We propose a generic framework named \textit{Cross-domain Knowledge Distillation} (CdKD) without needing any source data. CdKD matches the joint distributions between a trained source model and a set of target data during distilling the knowledge from the source model to the target domain. As a type of important knowledge in the source domain, for the first time, the gradient information is exploited to boost the transfer performance. Experiments on cross-domain text classification demonstrate that CdKD achieves superior performance, which verifies the effectiveness in this novel setting.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Cross-Domain Text ClassificationDomain AdaptationKnowledge Distillationtext-classificationText ClassificationUnsupervised Domain Adaptation

Similar Papers 제목 키워드 기반

Domain Generalisation via Risk Distribution Matching

2023-10-28 · Toan Nguyen, Kien Do, Bao Duong, Thin Nguyen

We propose a novel approach for domain generalisation (DG) leveraging risk distributions to characterise domains, thereby achieving domain invariance. In our findings, risk distributions effectively highlight differences…

Cross-Domain Matching for Bag-of-Words Data via Kernel Embeddings of Latent Distributions

2015-12-01 · NeurIPS 2015 12 · Yuya Yoshikawa, Tomoharu Iwata, Hiroshi Sawada, Takeshi Yamada

We propose a kernel-based method for finding matching between instances across different domains, such as multilingual documents and images with annotations. Each instance is assumed to be represented as a multiset of fe…

Articles

Learning to Match Distributions for Domain Adaptation

2020-07-17 · Chaohui Yu, Jindong Wang, Chang Liu, Tao Qin 외

When the training and test data are from different distributions, domain adaptation is needed to reduce dataset bias to improve the model's generalization ability. Since it is difficult to directly match the cross-domain…

Domain AdaptationInductive Bias

Flexible Transfer Learning under Support and Model Shift

2014-12-01 · NeurIPS 2014 12 · Xuezhi Wang, Jeff Schneider

Transfer learning algorithms are used when one has sufficient training data for one supervised learning task (the source/training domain) but only very limited training data for a second task (the target/test domain) tha…

Transfer Learning

A Class-aware Optimal Transport Approach with Higher-Order Moment Matching for Unsupervised Domain Adaptation

2024-01-29 · Tuan Nguyen, Van Nguyen, Trung Le, He Zhao 외

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. In this paper, we introduce a novel approach called class-aware optimal transport (OT), which me…

Domain AdaptationUnsupervised Domain Adaptation