paper-with-me

홈 › Papers

Multi-Source Domain Adaptation with Mixture of Experts

2018-09-07 · EMNLP 2018 10 · Jiang Guo, Darsh J Shah, Regina Barzilay

We propose a mixture-of-experts approach for unsupervised domain adaptation from multiple sources. The key idea is to explicitly capture the relationship between a target example and different source domains. This relationship, expressed by a point-to-set metric, determines how to combine predictors trained on various domains. The metric is learned in an unsupervised fashion using meta-training. Experimental results on sentiment analysis and part-of-speech tagging demonstrate that our approach consistently outperforms multiple baselines and can robustly handle negative transfer.

📄 PDF Abstract BibTeX arXiv:1809.02256

Code (1)

jiangfeng1124/transfer 공식 구현 pytorch

Tasks

Domain AdaptationMixture-of-ExpertsPart-Of-Speech TaggingSentiment AnalysisUnsupervised Domain Adaptation

Similar Papers 제목 키워드 기반

Transformer Based Multi-Source Domain Adaptation

2020-09-16 · EMNLP 2020 11 · Dustin Wright, Isabelle Augenstein

In practical machine learning settings, the data on which a model must make predictions often come from a different distribution than the data it was trained on. Here, we investigate the problem of unsupervised multi-sou…

Domain AdaptationMixture-of-Experts

MALoRA: Mixture of Asymmetric Low-Rank Adaptation for Enhanced Multi-Task Learning

2024-10-30 · Xujia Wang, Haiyan Zhao, Shuo Wang, Hanqing Wang 외

Parameter-Efficient Fine-Tuning (PEFT) methods like LoRA have significantly improved the adaptation of LLMs to downstream tasks in a resource-efficient manner. However, in multi-task scenarios, challenges such as trainin…

Computational EfficiencyMixture-of-ExpertsMulti-Task Learningparameter-efficient fine-tuning

STEM: An Approach to Multi-Source Domain Adaptation With Guarantees

2021-10-01 · Van-Anh Nguyen, Tuan Nguyen, Trung Le, Quan Hung Tran 외

Multi-source Domain Adaptation (MSDA) is more practical but challenging than the conventional unsupervised domain adaptation due to the involvement of diverse multiple data sources. Two fundamental challenges of MSDA are…

STEM: An Approach to Multi-Source Domain Adaptation With Guarantees

2021-01-01 · ICCV 2021 10 · Van-Anh Nguyen, Tuan Nguyen, Trung Le, Quan Hung Tran 외

Multi-source Domain Adaptation (MSDA) is more practical but challenging than the conventional unsupervised domain adaptation due to the involvement of diverse multiple data sources. Two fundamental challenges of MSDA…

Domain AdaptationMulti-Source Unsupervised Domain AdaptationUnsupervised Domain Adaptation

Scalable Multi-Domain Adaptation of Language Models using Modular Experts

2024-10-14 · Peter Schafhalter, Shun Liao, Yanqi Zhou, Chih-Kuan Yeh 외

Domain-specific adaptation is critical to maximizing the performance of pre-trained language models (PLMs) on one or multiple targeted tasks, especially under resource-constrained use cases, such as edge devices. However…

Domain AdaptationGeneral KnowledgeMixture-of-Experts