Graph Out-of-Distribution Detection Goes Neighborhood Shaping

Tianyi Bao, Qitian Wu, Zetian Jiang, Yiting Chen, Jiawei Sun, Junchi Yan
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2923-2943, 2024.

Abstract

Despite the rich line of research works on out-of-distribution (OOD) detection on images, the literature on OOD detection for interdependent data, e.g., graphs, is still relatively limited. To fill this gap, we introduce TopoOOD as a principled approach that accommodates graph topology and neighborhood context for detecting OOD node instances on graphs. Meanwhile, we enrich the experiment settings by splitting in-distribution (ID) and OOD data based on distinct topological distributions, which presents new benchmarks for a more comprehensive analysis of graph-based OOD detection. The latter is designed to thoroughly assess the performance of these discriminators under distribution shifts involving structural information, providing a rigorous evaluation of methods in the emerging area of OOD detection on graphs. Our experimental results show the competitiveness of the proposed model across multiple datasets, as evidenced by up to a 15% increase in the AUROC and a 50% decrease in the FPR compared to existing state-of-the-art methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-bao24c, title = {Graph Out-of-Distribution Detection Goes Neighborhood Shaping}, author = {Bao, Tianyi and Wu, Qitian and Jiang, Zetian and Chen, Yiting and Sun, Jiawei and Yan, Junchi}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {2923--2943}, 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/bao24c/bao24c.pdf}, url = {https://proceedings.mlr.press/v235/bao24c.html}, abstract = {Despite the rich line of research works on out-of-distribution (OOD) detection on images, the literature on OOD detection for interdependent data, e.g., graphs, is still relatively limited. To fill this gap, we introduce TopoOOD as a principled approach that accommodates graph topology and neighborhood context for detecting OOD node instances on graphs. Meanwhile, we enrich the experiment settings by splitting in-distribution (ID) and OOD data based on distinct topological distributions, which presents new benchmarks for a more comprehensive analysis of graph-based OOD detection. The latter is designed to thoroughly assess the performance of these discriminators under distribution shifts involving structural information, providing a rigorous evaluation of methods in the emerging area of OOD detection on graphs. Our experimental results show the competitiveness of the proposed model across multiple datasets, as evidenced by up to a 15% increase in the AUROC and a 50% decrease in the FPR compared to existing state-of-the-art methods.} }
Endnote
%0 Conference Paper %T Graph Out-of-Distribution Detection Goes Neighborhood Shaping %A Tianyi Bao %A Qitian Wu %A Zetian Jiang %A Yiting Chen %A Jiawei Sun %A Junchi Yan %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-bao24c %I PMLR %P 2923--2943 %U https://proceedings.mlr.press/v235/bao24c.html %V 235 %X Despite the rich line of research works on out-of-distribution (OOD) detection on images, the literature on OOD detection for interdependent data, e.g., graphs, is still relatively limited. To fill this gap, we introduce TopoOOD as a principled approach that accommodates graph topology and neighborhood context for detecting OOD node instances on graphs. Meanwhile, we enrich the experiment settings by splitting in-distribution (ID) and OOD data based on distinct topological distributions, which presents new benchmarks for a more comprehensive analysis of graph-based OOD detection. The latter is designed to thoroughly assess the performance of these discriminators under distribution shifts involving structural information, providing a rigorous evaluation of methods in the emerging area of OOD detection on graphs. Our experimental results show the competitiveness of the proposed model across multiple datasets, as evidenced by up to a 15% increase in the AUROC and a 50% decrease in the FPR compared to existing state-of-the-art methods.
APA
Bao, T., Wu, Q., Jiang, Z., Chen, Y., Sun, J. & Yan, J.. (2024). Graph Out-of-Distribution Detection Goes Neighborhood Shaping. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:2923-2943 Available from https://proceedings.mlr.press/v235/bao24c.html.

Related Material