Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.00476 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916638515789824 |
|---|---|
| author | Dong, Yicong He, Rundong Chen, Guangyao Zhang, Wentao Han, Zhongyi Shi, Jieming Yin, Yilong |
| author_facet | Dong, Yicong He, Rundong Chen, Guangyao Zhang, Wentao Han, Zhongyi Shi, Jieming Yin, Yilong |
| contents | Graph Neural Networks (GNNs) have achieved significant success in machine learning, with wide applications in social networks, bioinformatics, knowledge graphs, and other fields. Most research assumes ideal closed-set environments. However, in real-world open-set environments, graph learning models face challenges in robustness and reliability due to unseen classes. This highlights the need for Graph Open-Set Recognition (GOSR) methods to address these issues and ensure effective GNN application in practical scenarios. Research in GOSR is in its early stages, with a lack of a comprehensive benchmark spanning diverse tasks and datasets to evaluate methods. Moreover, traditional methods, Graph Out-of-Distribution Detection (GOODD), GOSR, and Graph Anomaly Detection (GAD) have mostly evolved in isolation, with little exploration of their interconnections or potential applications to GOSR. To fill these gaps, we introduce \textbf{G-OSR}, a comprehensive benchmark for evaluating GOSR methods at both the node and graph levels, using datasets from multiple domains to ensure fair and standardized comparisons of effectiveness and efficiency across traditional, GOODD, GOSR, and GAD methods. The results offer critical insights into the generalizability and limitations of current GOSR methods and provide valuable resources for advancing research in this field through systematic analysis of diverse approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_00476 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | G-OSR: A Comprehensive Benchmark for Graph Open-Set Recognition Dong, Yicong He, Rundong Chen, Guangyao Zhang, Wentao Han, Zhongyi Shi, Jieming Yin, Yilong Machine Learning Graph Neural Networks (GNNs) have achieved significant success in machine learning, with wide applications in social networks, bioinformatics, knowledge graphs, and other fields. Most research assumes ideal closed-set environments. However, in real-world open-set environments, graph learning models face challenges in robustness and reliability due to unseen classes. This highlights the need for Graph Open-Set Recognition (GOSR) methods to address these issues and ensure effective GNN application in practical scenarios. Research in GOSR is in its early stages, with a lack of a comprehensive benchmark spanning diverse tasks and datasets to evaluate methods. Moreover, traditional methods, Graph Out-of-Distribution Detection (GOODD), GOSR, and Graph Anomaly Detection (GAD) have mostly evolved in isolation, with little exploration of their interconnections or potential applications to GOSR. To fill these gaps, we introduce \textbf{G-OSR}, a comprehensive benchmark for evaluating GOSR methods at both the node and graph levels, using datasets from multiple domains to ensure fair and standardized comparisons of effectiveness and efficiency across traditional, GOODD, GOSR, and GAD methods. The results offer critical insights into the generalizability and limitations of current GOSR methods and provide valuable resources for advancing research in this field through systematic analysis of diverse approaches. |
| title | G-OSR: A Comprehensive Benchmark for Graph Open-Set Recognition |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2503.00476 |