Rank and Align: Towards Effective Source-Free Graph Domain Adaptation
Abstract
In this work, we show how the class of improvement operators --- a general class of iterated belief change operators --- can be used to define a learning model. Focusing on binary classification, we present learning and inference algorithms suited to this learning model and we evaluate them empirically. Our findings highlight two key insights: first, that iterated belief change can be viewed as an effective form of online learning, and second, that the well-established axiomatic foundations of belief change operators offer a promising avenue for the axiomatic study of classification tasks.
Cite
Text
Luo et al. "Rank and Align: Towards Effective Source-Free Graph Domain Adaptation." International Joint Conference on Artificial Intelligence, 2024. doi:10.24963/ijcai.2024/520Markdown
[Luo et al. "Rank and Align: Towards Effective Source-Free Graph Domain Adaptation." International Joint Conference on Artificial Intelligence, 2024.](https://mlanthology.org/ijcai/2024/luo2024ijcai-rank/) doi:10.24963/ijcai.2024/520BibTeX
@inproceedings{luo2024ijcai-rank,
title = {{Rank and Align: Towards Effective Source-Free Graph Domain Adaptation}},
author = {Luo, Junyu and Xiao, Zhiping and Wang, Yifan and Luo, Xiao and Yuan, Jingyang and Ju, Wei and Liu, Langechuan and Zhang, Ming},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2024},
pages = {4706-4714},
doi = {10.24963/ijcai.2024/520},
url = {https://mlanthology.org/ijcai/2024/luo2024ijcai-rank/}
}