IBPL: Information Bottleneck-based Prompt Learning for graph out-of-distribution detection

Yanan Cao, Fengzhao Shi, Qing Yu, Xixun Lin, Chuan Zhou, Lixin Zou, Peng Zhang, Zhao Li, Dawei Yin

Abstract

Highlights•We study how to eliminate the overlapping features to enlarge the score gap.•We propose the IB-based graph prompt to optimize node features and graph structure.•Our method yields the superior results over existing strong approaches empirically.
BibTeX
@inproceedings{cao2025ibpl,
  author = {Yanan Cao and Fengzhao Shi and Qing Yu and Xixun Lin and Chuan Zhou and Lixin Zou and Peng Zhang and Zhao Li and Dawei Yin},
  title = {{IBPL: Information Bottleneck-based Prompt Learning for graph out-of-distribution detection}},
  booktitle = {Neural Networks},
  year = {2025},
  url = {https://openreview.net/forum?id=q7lrRKaUU3},
}

Loading related content...

Figure