Gradual Fine-Tuning with Graph Routing for Multi-Source Unsupervised Domain Adaptation

Yao Ma, Samuel Louvan, Zhunxuan Wang
Proceedings of The 3rd Conference on Lifelong Learning Agents, PMLR 274:324-341, 2025.

Abstract

Multi-source unsupervised domain adaptation aims to leverage labeled data from multiple source domains for training a machine learning model to generalize well on a target domain without labels. Source domain selection plays a crucial role in determining the model’s performance. It relies on the similarities amongst source and target domains. Nonetheless, existing work for source domain selection often involves heavyweight computational procedures, especially when dealing with numerous source domains and the need to identify the best ones from them. In this paper, we introduce a framework for gradual fine tuning (GFT) of machine learning models on multiple source domains. We represent multiple source domains as an undirected weighted graph. We then give a new generalization error bound for GFT along any path within the graph, which is used to determine the optimal path corresponding to the optimal training order. With this formulation, we introduce three lightweight graph-routing strategies which tend to minimize the error bound. Our best strategy improves 2.3% of accuracy over the state-of-the-art on Natural Language Inference (NLI) task and achieves competitive performance on Sentiment Analysis (SA) task, especially a 3.9% improvement on a more diverse subset of data we use for SA.

Cite this Paper


BibTeX
@InProceedings{pmlr-v274-ma25a, title = {Gradual Fine-Tuning with Graph Routing for Multi-Source Unsupervised Domain Adaptation}, author = {Ma, Yao and Louvan, Samuel and Wang, Zhunxuan}, booktitle = {Proceedings of The 3rd Conference on Lifelong Learning Agents}, pages = {324--341}, year = {2025}, editor = {Lomonaco, Vincenzo and Melacci, Stefano and Tuytelaars, Tinne and Chandar, Sarath and Pascanu, Razvan}, volume = {274}, series = {Proceedings of Machine Learning Research}, month = {29 Jul--01 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v274/main/assets/ma25a/ma25a.pdf}, url = {https://proceedings.mlr.press/v274/ma25a.html}, abstract = {Multi-source unsupervised domain adaptation aims to leverage labeled data from multiple source domains for training a machine learning model to generalize well on a target domain without labels. Source domain selection plays a crucial role in determining the model’s performance. It relies on the similarities amongst source and target domains. Nonetheless, existing work for source domain selection often involves heavyweight computational procedures, especially when dealing with numerous source domains and the need to identify the best ones from them. In this paper, we introduce a framework for gradual fine tuning (GFT) of machine learning models on multiple source domains. We represent multiple source domains as an undirected weighted graph. We then give a new generalization error bound for GFT along any path within the graph, which is used to determine the optimal path corresponding to the optimal training order. With this formulation, we introduce three lightweight graph-routing strategies which tend to minimize the error bound. Our best strategy improves 2.3% of accuracy over the state-of-the-art on Natural Language Inference (NLI) task and achieves competitive performance on Sentiment Analysis (SA) task, especially a 3.9% improvement on a more diverse subset of data we use for SA.} }
Endnote
%0 Conference Paper %T Gradual Fine-Tuning with Graph Routing for Multi-Source Unsupervised Domain Adaptation %A Yao Ma %A Samuel Louvan %A Zhunxuan Wang %B Proceedings of The 3rd Conference on Lifelong Learning Agents %C Proceedings of Machine Learning Research %D 2025 %E Vincenzo Lomonaco %E Stefano Melacci %E Tinne Tuytelaars %E Sarath Chandar %E Razvan Pascanu %F pmlr-v274-ma25a %I PMLR %P 324--341 %U https://proceedings.mlr.press/v274/ma25a.html %V 274 %X Multi-source unsupervised domain adaptation aims to leverage labeled data from multiple source domains for training a machine learning model to generalize well on a target domain without labels. Source domain selection plays a crucial role in determining the model’s performance. It relies on the similarities amongst source and target domains. Nonetheless, existing work for source domain selection often involves heavyweight computational procedures, especially when dealing with numerous source domains and the need to identify the best ones from them. In this paper, we introduce a framework for gradual fine tuning (GFT) of machine learning models on multiple source domains. We represent multiple source domains as an undirected weighted graph. We then give a new generalization error bound for GFT along any path within the graph, which is used to determine the optimal path corresponding to the optimal training order. With this formulation, we introduce three lightweight graph-routing strategies which tend to minimize the error bound. Our best strategy improves 2.3% of accuracy over the state-of-the-art on Natural Language Inference (NLI) task and achieves competitive performance on Sentiment Analysis (SA) task, especially a 3.9% improvement on a more diverse subset of data we use for SA.
APA
Ma, Y., Louvan, S. & Wang, Z.. (2025). Gradual Fine-Tuning with Graph Routing for Multi-Source Unsupervised Domain Adaptation. Proceedings of The 3rd Conference on Lifelong Learning Agents, in Proceedings of Machine Learning Research 274:324-341 Available from https://proceedings.mlr.press/v274/ma25a.html.

Related Material