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..
Learning Disentangled Joint Continuous and Discrete Representations
Authors: Emilien Dupont
NeurIPS 2018 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments show that the framework disentangles continuous and discrete generative factors on various datasets and outperforms current disentangling methods when a discrete generative factor is prominent. |
| Researcher Affiliation | Industry | Emilien Dupont Schlumberger Software Technology Innovation Center Menlo Park, CA, USA EMAIL |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. Figure 1 shows an architecture diagram, not pseudocode. |
| Open Source Code | Yes | The code, along with all experiments and trained models presented in this paper, is available at https://github.com/ Schlumberger/joint-vae. |
| Open Datasets | Yes | We perform experiments on several datasets including MNIST, Fashion MNIST (Xiao et al. (2017)), Celeb A (Liu et al. (2015)) and Chairs (Aubry et al. (2014)). We quantitatively evaluate our model on the d Sprites dataset using the metric recently proposed by Kim & Mnih (2018). |
| Dataset Splits | No | The paper does not provide specific dataset split information (exact percentages, sample counts, or detailed splitting methodology) for training, validation, or testing. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., exact GPU/CPU models, processor types, or memory amounts) used for running its experiments. |
| Software Dependencies | No | The paper does not provide specific ancillary software details with version numbers (e.g., library or solver names with version numbers) needed to replicate the experiment. |
| Experiment Setup | Yes | The model was trained with 10 continuous latent variables and one discrete 10-dimensional latent variable [for MNIST]. For Celeb A we used a model with 32 continuous latent variables and one 10 dimensional discrete latent variable. For the chairs dataset we used a model with 32 continuous latent variables and 3 binary discrete latent variables. The Joint VAE loss in equation 7 depends on the hyperparameters γ, Cc and Cz. All hyperparameters needed to reproduce the results in this paper are given in the appendix. |