Proximity-Based Evidence Retrieval for Uncertainty-Aware Neural Networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909791610208256 |
|---|---|
| author | Gharoun, Hassan Khorshidi, Mohammad Sadegh Ranjbarigderi, Kasra Chen, Fang Gandomi, Amir H. |
| author_facet | Gharoun, Hassan Khorshidi, Mohammad Sadegh Ranjbarigderi, Kasra Chen, Fang Gandomi, Amir H. |
| contents | This work proposes an evidence-retrieval mechanism for uncertainty-aware decision-making that replaces a single global cutoff with an evidence-conditioned, instance-adaptive criterion. For each test instance, proximal exemplars are retrieved in an embedding space; their predictive distributions are fused via Dempster-Shafer theory. The resulting fused belief acts as a per-instance thresholding mechanism. Because the supporting evidences are explicit, decisions are transparent and auditable. Experiments on CIFAR-10/100 with BiT and ViT backbones show higher or comparable uncertainty-aware performance with materially fewer confidently incorrect outcomes and a sustainable review load compared with applying threshold on prediction entropy. Notably, only a few evidences are sufficient to realize these gains; increasing the evidence set yields only modest changes. These results indicate that evidence-conditioned tagging provides a more reliable and interpretable alternative to fixed prediction entropy thresholds for operational uncertainty-aware decision-making. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_13338 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Proximity-Based Evidence Retrieval for Uncertainty-Aware Neural Networks Gharoun, Hassan Khorshidi, Mohammad Sadegh Ranjbarigderi, Kasra Chen, Fang Gandomi, Amir H. Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Neural and Evolutionary Computing 68T07, 68T09 This work proposes an evidence-retrieval mechanism for uncertainty-aware decision-making that replaces a single global cutoff with an evidence-conditioned, instance-adaptive criterion. For each test instance, proximal exemplars are retrieved in an embedding space; their predictive distributions are fused via Dempster-Shafer theory. The resulting fused belief acts as a per-instance thresholding mechanism. Because the supporting evidences are explicit, decisions are transparent and auditable. Experiments on CIFAR-10/100 with BiT and ViT backbones show higher or comparable uncertainty-aware performance with materially fewer confidently incorrect outcomes and a sustainable review load compared with applying threshold on prediction entropy. Notably, only a few evidences are sufficient to realize these gains; increasing the evidence set yields only modest changes. These results indicate that evidence-conditioned tagging provides a more reliable and interpretable alternative to fixed prediction entropy thresholds for operational uncertainty-aware decision-making. |
| title | Proximity-Based Evidence Retrieval for Uncertainty-Aware Neural Networks |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Neural and Evolutionary Computing 68T07, 68T09 |
| url | https://arxiv.org/abs/2509.13338 |