Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Variational Imbalanced Regression: Fair Uncertainty Quantification via Probabilistic Smoothing
Authors: Ziyan Wang, Hao Wang
NeurIPS 2023 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments in several real-world datasets show that our VIR can outperform state-of-the-art imbalanced regression models in terms of both accuracy and uncertainty estimation. |
| Researcher Affiliation | Academia | Ziyan Wang Georgia Institute of Technology EMAIL Hao Wang Rutgers University EMAIL |
| Pseudocode | No | The paper describes methods using prose and mathematical equations but does not include structured pseudocode or algorithm blocks. |
| Open Source Code | No | Code will soon be available at https: //github.com/Wang-ML-Lab/variational-imbalanced-regression. |
| Open Datasets | Yes | We evaluate our methods in terms of prediction accuracy and uncertainty estimation on four imbalanced datasets1, Age DB-DIR [30], IMDB-WIKI-DIR [33], STS-B-DIR [7], and NYUD2-DIR [35]. |
| Dataset Splits | Yes | Age DB-DIR: We use Age DB-DIR constructed in DIR [49], which contains 12.2K images for training and 2.1K images for validation and testing. |
| Hardware Specification | No | The paper mentions receiving 'Amazon Web Service for providing cloud computing credit' but does not provide specific hardware details like GPU or CPU models used for the experiments. |
| Software Dependencies | No | We use Py Torch to implement our method. |
| Experiment Setup | Yes | We use the Adam optimizer [24] to train all models for 100 epochs, with same learning rate and decay by 0.1 and the 60-th and 90-th epoch, respectively. In order to determine the optimal batch size for training, we try different batch sizes and corroborate the conclusion from [49], i.e., the optimal batch size is 256 when other hyperparameters are fixed. |