A Density-Driven Iterative Prototype Optimization for Transductive Few-Shot Learning
Abstract
We introduce a notion of conditional independence in (flat) assumption-based argumentation (ABA), where independence between (sets of) assumptions amounts to the presence of information about one set of assumptions not impacting the acceptability of another. We study general properties, computational complexity, and the relation to independence in abstract argumentation. In light of the high computational complexity of deciding independence, we introduce sound methods for checking independence in polynomial time via two different routes: the first utilizes the strongly connected components (SCCs) of the instantiated abstract argumentation framework; the second exploits the structure of the ABA framework directly. Along the way, we introduce the notion of SCC-recursiveness for ABA.
Cite
Text
Li et al. "A Density-Driven Iterative Prototype Optimization for Transductive Few-Shot Learning." International Joint Conference on Artificial Intelligence, 2024. doi:10.24963/ijcai.2024/488Markdown
[Li et al. "A Density-Driven Iterative Prototype Optimization for Transductive Few-Shot Learning." International Joint Conference on Artificial Intelligence, 2024.](https://mlanthology.org/ijcai/2024/li2024ijcai-density/) doi:10.24963/ijcai.2024/488BibTeX
@inproceedings{li2024ijcai-density,
title = {{A Density-Driven Iterative Prototype Optimization for Transductive Few-Shot Learning}},
author = {Li, Jingcong and Ye, Chunjin and Wang, Fei and Pan, Jiahui},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2024},
pages = {4416-4424},
doi = {10.24963/ijcai.2024/488},
url = {https://mlanthology.org/ijcai/2024/li2024ijcai-density/}
}