Uncertainty-Aware Attention for Reliable Interpretation and Prediction

Authors: Jay Heo, Hae Beom Lee, Saehoon Kim, Juho Lee, Kwang Joon Kim, Eunho Yang, Sung Ju Hwang

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We validate UA on tasks such as sepsis prediction in ICU and disease risk prediction from electronic health records (EHR) that have large degree of uncertainties in the input, on which our model outperforms the baseline attention models by large margins.
Researcher Affiliation Collaboration Jay Heo1,2,4 , Hae Beom Lee1,2 , Saehoon Kim2, Juho Lee2,5, Kwang Joon Kim3, Eunho Yang1,2, Sung Ju Hwang1,2 KAIST1, AItrics2, Yonsei University College of Medicine3, UNIST4, South Korea, University of Oxford5, United Kingdom
Pseudocode No No pseudocode or algorithm blocks were found.
Open Source Code Yes The source codes are publicly available at https://github.com/jayheo/UA.
Open Datasets Yes 1) Physio Net This dataset [11] contains 4,000 medical records from ICU... 3) MIMIC-Sepsis This is the subset of the MIMIC III dataset [12] for sepsis prediction... [12] A. E. Johnson, T. J. Pollard, L. Shen, L. wei H. Lehman, M. Feng, M. Ghassemi, B. Moody, P. Szolovits, L. A. Celi, and R. G. Mark. Mimic-iii, a freely accessible critical care database.
Dataset Splits Yes For all datasets, we generates five random splits of training/validation/test with the ratio of 80% : 10% : 10%.
Hardware Specification No No specific hardware details (e.g., GPU/CPU models, memory, or cloud instance types) were mentioned for running experiments.
Software Dependencies No The paper mentions that 'The source codes are publicly available at https://github.com/jayheo/UA' but does not explicitly list specific software dependencies with version numbers in the text.
Experiment Setup No The paper states, 'Detailed description of the datasets, network configuration, and hyperparameters are fully described in the appendix section.' However, this information is not provided in the main paper body.