Proximity-Based Evidence Retrieval for Uncertainty-Aware Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gharoun, Hassan, Khorshidi, Mohammad Sadegh, Ranjbarigderi, Kasra, Chen, Fang, Gandomi, Amir H.
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