Self-Supervised Weighted Information Bottleneck for Multi-View Clustering

Abstract

The responsibility gap is a set of outcomes of a collective decision-making mechanism in which no single agent is individually responsible. In general, when designing a decision-making process, it is desirable to minimise the gap. The paper studies the class of mechanisms for which the gap is empty and proposes a concept of an elected dictatorship. It shows that, in a perfect information setting, the gap is empty if and only if the mechanism is an elected dictatorship. It also proves that in an imperfect information setting, the class of gap-free mechanisms is positioned strictly between two variations of the class of elected dictatorships.

Cite

Text

Lou et al. "Self-Supervised Weighted Information Bottleneck for Multi-View Clustering." International Joint Conference on Artificial Intelligence, 2024. doi:10.24963/ijcai.2024/513

Markdown

[Lou et al. "Self-Supervised Weighted Information Bottleneck for Multi-View Clustering." International Joint Conference on Artificial Intelligence, 2024.](https://mlanthology.org/ijcai/2024/lou2024ijcai-self/) doi:10.24963/ijcai.2024/513

BibTeX

@inproceedings{lou2024ijcai-self,
  title     = {{Self-Supervised Weighted Information Bottleneck for Multi-View Clustering}},
  author    = {Lou, Zhengzheng and Zhang, Chaoyang and Xue, Hang and Ye, Yangdong and Zhou, Qinglei and Hu, Shizhe},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2024},
  pages     = {4643-4650},
  doi       = {10.24963/ijcai.2024/513},
  url       = {https://mlanthology.org/ijcai/2024/lou2024ijcai-self/}
}