Graph Neural Stochastic Diffusion for Estimating Uncertainty in Node Classification

Xixun Lin, Wenxiao Zhang, Fengzhao Shi, Chuan Zhou, Lixin Zou, Xiangyu Zhao, Dawei Yin, Shirui Pan, Yanan Cao
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30457-30478, 2024.

Abstract

Graph neural networks (GNNs) have advanced the state of the art in various domains. Despite their remarkable success, the uncertainty estimation of GNN predictions remains under-explored, which limits their practical applications especially in risk-sensitive areas. Current works suffer from either intractable posteriors or inflexible prior specifications, leading to sub-optimal empirical results. In this paper, we present graph neural stochastic diffusion (GNSD), a novel framework for estimating predictive uncertainty on graphs by establishing theoretical connections between GNNs and stochastic partial differential equation. GNSD represents a GNN-based parameterization of the proposed graph stochastic diffusion equation which includes a $Q$-Wiener process to model the stochastic evolution of node representations. GNSD introduces a drift network to guarantee accurate prediction and a stochastic forcing network to model the propagation of epistemic uncertainty among nodes. Extensive experiments are conducted on multiple detection tasks, demonstrating that GNSD yields the superior performance over existing strong approaches.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-lin24x, title = {Graph Neural Stochastic Diffusion for Estimating Uncertainty in Node Classification}, author = {Lin, Xixun and Zhang, Wenxiao and Shi, Fengzhao and Zhou, Chuan and Zou, Lixin and Zhao, Xiangyu and Yin, Dawei and Pan, Shirui and Cao, Yanan}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {30457--30478}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/lin24x/lin24x.pdf}, url = {https://proceedings.mlr.press/v235/lin24x.html}, abstract = {Graph neural networks (GNNs) have advanced the state of the art in various domains. Despite their remarkable success, the uncertainty estimation of GNN predictions remains under-explored, which limits their practical applications especially in risk-sensitive areas. Current works suffer from either intractable posteriors or inflexible prior specifications, leading to sub-optimal empirical results. In this paper, we present graph neural stochastic diffusion (GNSD), a novel framework for estimating predictive uncertainty on graphs by establishing theoretical connections between GNNs and stochastic partial differential equation. GNSD represents a GNN-based parameterization of the proposed graph stochastic diffusion equation which includes a $Q$-Wiener process to model the stochastic evolution of node representations. GNSD introduces a drift network to guarantee accurate prediction and a stochastic forcing network to model the propagation of epistemic uncertainty among nodes. Extensive experiments are conducted on multiple detection tasks, demonstrating that GNSD yields the superior performance over existing strong approaches.} }
Endnote
%0 Conference Paper %T Graph Neural Stochastic Diffusion for Estimating Uncertainty in Node Classification %A Xixun Lin %A Wenxiao Zhang %A Fengzhao Shi %A Chuan Zhou %A Lixin Zou %A Xiangyu Zhao %A Dawei Yin %A Shirui Pan %A Yanan Cao %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-lin24x %I PMLR %P 30457--30478 %U https://proceedings.mlr.press/v235/lin24x.html %V 235 %X Graph neural networks (GNNs) have advanced the state of the art in various domains. Despite their remarkable success, the uncertainty estimation of GNN predictions remains under-explored, which limits their practical applications especially in risk-sensitive areas. Current works suffer from either intractable posteriors or inflexible prior specifications, leading to sub-optimal empirical results. In this paper, we present graph neural stochastic diffusion (GNSD), a novel framework for estimating predictive uncertainty on graphs by establishing theoretical connections between GNNs and stochastic partial differential equation. GNSD represents a GNN-based parameterization of the proposed graph stochastic diffusion equation which includes a $Q$-Wiener process to model the stochastic evolution of node representations. GNSD introduces a drift network to guarantee accurate prediction and a stochastic forcing network to model the propagation of epistemic uncertainty among nodes. Extensive experiments are conducted on multiple detection tasks, demonstrating that GNSD yields the superior performance over existing strong approaches.
APA
Lin, X., Zhang, W., Shi, F., Zhou, C., Zou, L., Zhao, X., Yin, D., Pan, S. & Cao, Y.. (2024). Graph Neural Stochastic Diffusion for Estimating Uncertainty in Node Classification. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:30457-30478 Available from https://proceedings.mlr.press/v235/lin24x.html.

Related Material