Disentangling Learning Representations with Density Estimation

Authors: Eric Yeats, Frank Y Liu, Hai Li

ICLR 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In our experiments, GCAE achieves highly competitive and reliable disentanglement scores compared with state-of-the-art baselines. and Experiments1 which demonstrate competitive performance of GCAE against leading disentanglement baselines on multiple datasets using existing metrics
Researcher Affiliation Collaboration Eric Yeats1 Frank Liu2 Hai Li1 1Department of Electrical and Computer Engineering, Duke University 2Computer Science and Mathematics Division, Oak Ridge National Laboratory {eric.yeats, hai.li}@duke.edu liufy@ornl.gov
Pseudocode No The paper describes algorithms and methods using mathematical notation and text, but it does not include any explicitly labeled pseudocode or algorithm blocks.
Open Source Code Yes 1Code available at https://github.com/ericyeats/gcae-disentanglement
Open Datasets Yes We consider two datasets which cover different data modalities. The Beamsynthesis dataset Yeats et al. (2022) is a collection of 360 timeseries data from a linear particle accelerator beamforming simulation. The waveforms are 1000 values long and are made of two independent data generating factors: duty cycle (continuous) and frequency (categorical). The d Sprites dataset Matthey et al. (2017) is a collection of 737280 synthetic images of simple white shapes on a black background.
Dataset Splits Yes For Beamsynthesis, we calculate MIG on the full dataset using a histogram estimate of the latent space with 50 bins (evenly spaced maximum to minimum). For d Sprites, we calculate MIG using 10000 samples, and we use 20 histogram bins following Locatello et al. (2019). and For Beamsynthesis, we train the majority-vote classifier on 1000 training points and evaluate on 200 separate points. For d Sprites, we train the majority-vote classifier on 5000 training points and evaluate on 1000 separate points. and For Beamsynthesis, we use a training size of 240 and a test size of 120. For d Sprites, we use a training size of 5000 and a test size of 1000. and For Beamsynthesis, we use 240 training points and 120 testing points. For d Sprites, we use 5000 training points and 1000 testing points.
Hardware Specification Yes All experiments are run using the Py Torch framework Paszke et al. (2019) using 4 NVIDIA Tesla V100 GPUs
Software Dependencies No The paper mentions using the 'Py Torch framework Paszke et al. (2019)' but does not specify a version number for PyTorch or any other software libraries required for replication.
Experiment Setup Yes In all experiments, the GCAE AE and discriminator learning rates are 5e 5 and 2e 4, respectively. The VAE learning rate is 1e 4 and the Factor VAE discriminator learning rate is 2e 4. All methods use the Adam optimizer with (β1, β2) = (0.9, 0.999) for the AE subset of parameters and (β1, β2) = (0.5, 0.9) for the discriminator(s) subset of parameters (if applicable). The number of discriminator updates per AE update k is set to 5 when m = 10 and 10 when m = 20. All discriminators are warmed up with 500 batches before training begins to ensure they approximate a valid density. (From Appendix B) and Table 1: MLP Architecture... Batch Size=64... 2000 Iterations... Batch Size=256... 20000 Iterations