# Uncertainty-Aware Attention for Reliable Interpretation and Prediction

arXiv: https://arxiv.org/abs/1805.09653 · HTML: https://mlsanity.com/paper/1805.09653/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 May 2018.

## Built on by (most cited first, 24 of 24)

- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [Trusted Multi-View Classification with Dynamic Evidential Fusion](https://mlsanity.com/paper/2204.11423/) (2022)
- [Machine Learning with a Reject Option: A survey](https://mlsanity.com/paper/2107.11277/) (2021)
- [Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey](https://mlsanity.com/paper/2503.15850/) (2025)
- [Trusted Multi-View Classification](https://mlsanity.com/paper/2102.02051/) (2021)
- [Visual Attention Methods in Deep Learning: An In-Depth Survey](https://mlsanity.com/paper/2204.07756/) (2022)
- [Dense Learning based Semi-Supervised Object Detection](https://mlsanity.com/paper/2204.07300/) (2022)
- [A Survey on Epistemic (Model) Uncertainty in Supervised Learning: Recent Advances and Applications](https://mlsanity.com/paper/2111.01968/) (2021)
- [Self-Interpretable Time Series Prediction with Counterfactual Explanations](https://mlsanity.com/paper/2306.06024/) (2023)
- [Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution View](https://mlsanity.com/paper/2112.02625/) (2021)
- [Robust and Explainable Identification of Logical Fallacies in Natural Language Arguments](https://mlsanity.com/paper/2212.07425/) (2022)
- [Assessing Cross-dataset Generalization of Pedestrian Crossing Predictors](https://mlsanity.com/paper/2201.12626/) (2022)
- [Calibration Meets Explanation: A Simple and Effective Approach for Model Confidence Estimates](https://mlsanity.com/paper/2211.03041/) (2022)
- [Uncertainty-Aware Image Captioning](https://mlsanity.com/paper/2211.16769/) (2022)
- [Uncertainty-aware abstention in medical diagnosis based on medical texts](https://mlsanity.com/paper/2502.18050/) (2025)
- [EgPDE-Net: Building Continuous Neural Networks for Time Series Prediction with Exogenous Variables](https://mlsanity.com/paper/2208.01913/) (2022)
- [Can Attention Be Used to Explain EHR-Based Mortality Prediction Tasks: A Case Study on Hemorrhagic Stroke](https://mlsanity.com/paper/2308.05110/) (2023)
- [A Hybrid Probabilistic Battery Health Management Approach for Robust Inspection Drone Operations](https://mlsanity.com/paper/2405.00055/) (2024)
- [Credible Remote Sensing Scene Classification Using Evidential Fusion on Aerial-Ground Dual-view Images](https://mlsanity.com/paper/2301.00622/) (2023)
- [A3Rank: Augmentation Alignment Analysis for Prioritizing Overconfident Failing Samples for Deep Learning Models](https://mlsanity.com/paper/2407.14114/) (2024)
- [Calibrating Scientific Foundation Models with Inference-Time Stochastic Attention](https://mlsanity.com/paper/2604.19530/) (2026)
- [Fusing Biomechanical and Spatio-Temporal Features for Fall Prediction: Characterizing and Mitigating the Simulation-to-Reality Gap](https://mlsanity.com/paper/2511.14620/) (2025)
- [Bridging the Missing-Modality Gap: Improving Text-Only Calibration of Vision Language Models](https://mlsanity.com/paper/2605.12517/) (2026)
- [ECUASn: A family of metrics for principled evaluation of uncertainty-augmented systems](https://mlsanity.com/paper/2605.20490/) (2026)

## Abstract (arXiv)

Attention mechanism is effective in both focusing the deep learning models on relevant features and interpreting them. However, attentions may be unreliable since the networks that generate them are often trained in a weakly-supervised manner. To overcome this limitation, we introduce the notion of input-dependent uncertainty to the attention mechanism, such that it generates attention for each feature with varying degrees of noise based on the given input, to learn larger variance on instances it is uncertain about. We learn this Uncertainty-aware Attention (UA) mechanism using variational inference, and validate it on various risk prediction tasks from electronic health records on which our model significantly outperforms existing attention models. The analysis of the learned attentions shows that our model generates attentions that comply with clinicians' interpretation, and provide richer interpretation via learned variance. Further evaluation of both the accuracy of the uncertainty calibration and the prediction performance with "I don't know" decision show that UA yields networks with high reliability as well.