Simple Contrastive Multi-View Clustering with Data-Level Fusion

Abstract

In this paper, we investigate verification of quantized Graph Neural Networks (GNNs), where some fixed-width arithmetic is used to represent numbers. We introduce the linear-constrained validity (LVP) problem for verifying GNNs properties, and provide an efficient translation from LVP instances into a logical language. We show that LVP is in PSPACE, for any reasonable activation functions. We provide a proof system. We also prove PSPACE-hardness, indicating that while reasoning about quantized GNNs is feasible, it remains generally computationally challenging.

Cite

Text

Luo et al. "Simple Contrastive Multi-View Clustering with Data-Level Fusion." International Joint Conference on Artificial Intelligence, 2024. doi:10.24963/ijcai.2024/519

Markdown

[Luo et al. "Simple Contrastive Multi-View Clustering with Data-Level Fusion." International Joint Conference on Artificial Intelligence, 2024.](https://mlanthology.org/ijcai/2024/luo2024ijcai-simple/) doi:10.24963/ijcai.2024/519

BibTeX

@inproceedings{luo2024ijcai-simple,
  title     = {{Simple Contrastive Multi-View Clustering with Data-Level Fusion}},
  author    = {Luo, Caixuan and Xu, Jie and Ren, Yazhou and Ma, Junbo and Zhu, Xiaofeng},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2024},
  pages     = {4697-4705},
  doi       = {10.24963/ijcai.2024/519},
  url       = {https://mlanthology.org/ijcai/2024/luo2024ijcai-simple/}
}