EGonc : Energy-based Open-Set Node Classification with substitute Unknowns
Qin Zhang, Zelin Shi, Shirui Pan, Junyang Chen, Huisi Wu, Xiaojun Chen
Abstract
Open-set Classification (OSC) is a critical requirement for safely deploying machine learning models in the open world, which aims to classify samples from known classes and reject samples from out-of-distribution (OOD). Existing methods exploit the feature space of trained network and attempt at estimating the uncertainty in the predictions. However, softmax-based neural networks are found to be overly confident in their predictions even on data they have never seen before and the immense diversity of the OOD examples also makes such methods fragile. To this end, we follow the idea of estimating the underlying density of the training data to decide whether a given input is close to the in-distribution (IND) data and adopt Energy-based models (EBMs) as density estimators. A novel energy-based generative open-set node classification method, EGonc, is proposed to achieve open-set graph learning. Specifically, we generate substitute unknowns to mimic the distribution of real open-set samples firstly, based on the information of graph structures. Then, an additional energy logit representing the virtual OOD class is learned from the residual of the feature against the principal space, and matched with the original logits by a constant scaling. This virtual logit serves as the indicator of OOD-ness. EGonc has nice theoretical properties that guarantee an overall distinguishable margin between the detection scores for IND and OOD samples. Comprehensive experimental evaluations of EGonc also demonstrate its superiority.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
2 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Energy-based Out-of-distribution Detection cites Your classifier is secretly an energy based model and you should treat it like one
- Subspace-Aware Feature Reshaping for Open-Set Graph Class-Incremental Learning cites Open Graph Benchmark: Datasets for Machine Learning on Graphs
- Out-of-Distribution Detection with Deep Nearest Neighbors cites Energy-based Out-of-distribution Detection
- From Subtle to Significant: Prompt-Driven Self-Improving Optimization in Test-Time Graph OOD Detection cites Energy-based Out-of-distribution Detection
Cited by top-tier papers2
- Subspace-Aware Feature Reshaping for Open-Set Graph Class-Incremental LearningWeichao Zhang, Shuai Zheng, Yeyu Yan, Zhizhe Liu et al.ICML 2026
- From Subtle to Significant: Prompt-Driven Self-Improving Optimization in Test-Time Graph OOD DetectionLuzhi Wang, Xuanshuo Fu, He Zhang, Chuang Liu et al.AAAI 2026
Builds on17
- Open Graph Benchmark: Datasets for Machine Learning on GraphsWeihua Hu, Matthias Fey, Marinka Zitnik, Yuxiao Dong et al.NeurIPS 2020 · 3,935 citations
- Energy-based Out-of-distribution DetectionWeitang Liu, Xiaoyun Wang, John D. Owens, Yixuan LiNeurIPS 2020 · 2,213 citations
- Simple and Deep Graph Convolutional NetworksMing Chen, Zhewei Wei, Zengfeng Huang, Bolin Ding et al.ICML 2020 · 1,910 citations
- Out-of-Distribution Detection with Deep Nearest NeighborsYiyou Sun, Yifei Ming, Xiaojin Zhu, Yixuan LiICML 2022 · 789 citations
- Your classifier is secretly an energy based model and you should treat it like oneWill Grathwohl, Kuan-Chieh Wang, Jörn-Henrik Jacobsen, David Duvenaud et al.ICLR 2020 · 643 citations
Related papers
- An Energy-centric Framework for Category-free Out-of-distribution Node Detection in GraphsZheng Gong, Ying SunKDD 2024 · 4 citations
- EVINET: Towards Open-World Graph Learning via Evidential Reasoning NetworkWeijie Guan, Haohui Wang, Jian Kang, Lihui Liu et al.KDD 2025
- Decoupled Graph Energy-based Model for Node Out-of-Distribution Detection on Heterophilic GraphsYuhan Chen, Yihong Luo, Yifan Song, Pengwen Dai et al.ICLR 2025
- negMIX: Negative Mixup for OOD Generalization in Open-Set Node ClassificationJunwei Gong, Xiao Shen, Zhihao Chen, Shirui Pan et al.WWW 2026
- Hybrid Energy Based Model in the Feature Space for Out-of-Distribution DetectionMarc Lafon, Elias Ramzi, Clément Rambour, Nicolas ThomeICML 2023 · 14 citations
