Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2412.14738 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917515828920320 |
|---|---|
| author | Wang, Yongyu |
| author_facet | Wang, Yongyu |
| contents | Graph-learning algorithms can fail when graph structure is adversarially perturbed, intrinsically noisy or constructed from imperfect observations. Here we show that some nodes bear much greater responsibility than others for allowing adversarial perturbations and intrinsic noise to harm graph-learning algorithms. Building on graph-spectral distortion analysis, we identify these failure-driving nodes and introduce a reliability-aware intervention that isolates them from the main learning step. The target algorithm is applied to a stable induced subgraph, and predictions for isolated nodes are recovered through topology- or centroid-based propagation. Across graph neural networks under targeted and non-targeted structural attacks, spectral hypergraph clustering and multi-view spectral clustering, this principle improves reliability under both adversarial and intrinsic noise. These results suggest that node-level spectral instability provides a common mechanism for understanding and mitigating reliability failures in graph learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_14738 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Spectrally unstable nodes drive reliability failures in graph learning Wang, Yongyu Machine Learning Graph-learning algorithms can fail when graph structure is adversarially perturbed, intrinsically noisy or constructed from imperfect observations. Here we show that some nodes bear much greater responsibility than others for allowing adversarial perturbations and intrinsic noise to harm graph-learning algorithms. Building on graph-spectral distortion analysis, we identify these failure-driving nodes and introduce a reliability-aware intervention that isolates them from the main learning step. The target algorithm is applied to a stable induced subgraph, and predictions for isolated nodes are recovered through topology- or centroid-based propagation. Across graph neural networks under targeted and non-targeted structural attacks, spectral hypergraph clustering and multi-view spectral clustering, this principle improves reliability under both adversarial and intrinsic noise. These results suggest that node-level spectral instability provides a common mechanism for understanding and mitigating reliability failures in graph learning. |
| title | Spectrally unstable nodes drive reliability failures in graph learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2412.14738 |