16 skills found
divelab / GOODGOOD: A Graph Out-of-Distribution Benchmark [NeurIPS 2022 Datasets and Benchmarks]
THUMNLab / Awesome Graph OodPapers about out-of-distribution generalization on graphs.
qitianwu / GraphOOD EERMThe official implementation for ICLR22 paper "Handling Distribution Shifts on Graphs: An Invariance Perspective"
qitianwu / GraphOOD GNNSafeThe official implementation for ICLR23 paper "GNNSafe: Energy-based Out-of-Distribution Detection for Graph Neural Networks"
kaize0409 / Awesome Graph OODNo description available
AndrewZhou924 / Graph Ood DetectionA curated list of resources for OOD detection with graph data.
ZhuYun97 / MARIOOfficial implementation of MARIO: Model Agnostic Recipe for Improving OOD Generalization of Graph Contrastive Learning
Samyu0304 / LiSACode for Mind the Label Shift of Augmentation-based Graph OOD generalization (LiSA) in CVPR 2023. LiSA is a model-agnostic Graph OOD framework.
YangLing0818 / GraphOODThe official Implementation for TKDE paper "Individual and Structural Graph Information Bottlenecks for Out-of-Distribution Generalization"
likuanppd / GOOD ATThe code of ICLR 2024 paper: Boosting the Adversarial Robustness of Graph Neural Networks: An OOD Perspective
handsome999KK / GSP OODCode for ICCV2025: Exploiting Vision Language Model for Training-Free 3D Point Cloud OOD Detection via Graph Score Propagation
ellenzhuwang / ImplicitOODAn end-to-end vision and language model incorporating explicit knowledge graphs and OOD-detection.
stvsd1314 / PPGN Physics Preserved Graph NetworksThe increasing number of variable renewable energy (solar and wind power) causes power grids to have more abnormal conditions or faults. Faults may further trigger power blackouts or wildfires without timely monitoring and control strategy. Machine learning is a promising technology to accelerate the automation and intelligence of power grid monitoring systems. Unfortunately, the black-box machine learning methods are weak to the realistic challenges in power grids: low observation, insufficient labels, and stochastic environments. To overcome the vulnerability of black-box machine learning, we preserve the physics of power grids through graph networks to efficiently and accurately locate the faults even with limited observability and low label rates. We first calculate the graph embedding of power grid infrastructure by establishing a reduced graph network with the observed nodes, then efficiently locate the fault on the node level using the low-dimensional graph embedding. To augment the location accuracy at low label rates, we build another graph network representing the physical similarity of labeled and unlabeled data samples. Importantly, we provide the physical interpretations of the benefits of the graph design through a random walk equivalence. We conduct comprehensive numerical experiments in the IEEE 123-node. Our proposed method shows superior performance than three baseline classifiers for different fault types, label rates, and robustness to out-of-distribution (OOD) data. Additionally, we extend the proposed method to the IEEE 37-node benchmark system and validate the effectiveness of the proposed training strategy.
ellenzhuwang / Implicit VkoodAn end-to-end vision-language framework incorporating explicit knowledge graphs and OOD-detection. (NeurIPS 23)
deeplearning-wisc / Graph Spectral Ood[NeurIPS 2024] Official Implementation of "Bridging OOD Generalization and Detection: A Graph-Theoretic View"
victor-armegioiu / OOD Detection In Molecular Complexes Via Diffusion Models For Irregular GraphsNo description available
