Hyperbolic VAE via Latent Gaussian Distributions
Authors: Seunghyuk Cho, Juyong Lee, Dongwoo Kim
NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We demonstrate the efficacy of GM-VAE on two different tasks: density estimation of image datasets and state representation learning for model-based reinforcement learning. GM-VAE outperforms the other variants of hyperbolic- and Euclidean-VAEs on density estimation tasks and shows competitive performance in model-based reinforcement learning. ... The results are reported at Table 1. GM-VAE outperforms the baselines in all the settings, except one case of Breakout. |
| Researcher Affiliation | Academia | Seunghyuk Cho POSTECH GSAI shhj1998@postech.ac.kr Juyong Lee KAIST AI agi.is@kaist.ac.kr Dongwoo Kim POSTECH GSAI & CSED dongwoo.kim@postech.ac.kr |
| Pseudocode | Yes | Algorithm 1 Decoder Input Parameter (α, β) Gc, γ, Decoding layers Dec( ) Output Reconstruction x 1: Sample µ N(α, β2γ2) 2: Sample log σ2 Gamma 1 4cγ2 + 1, 1 4cβ2γ2 3: x = Dec([µ, log σ2]) 4: return x |
| Open Source Code | Yes | The implementation is available at https://github.com/ml-postech/GM-VAE. |
| Open Datasets | Yes | We use three datasets: the images from Atari2600 Breakout with binarization (Breakout) (Nagano et al., 2019), Oxford 102 Flower (Oxford102) (Nilsback & Zisserman, 2008), Food101 (Bossard et al., 2014), and Caltech-UCSD Birds200-2011 (CUB) (Wah et al., 2011). |
| Dataset Splits | Yes | We split the datasets into train, validation, and test. For Breakout and CUB, we split the original train set into train and validation sets. For Oxford102, because the original train set is too small, we merge the original train and test set and then split it into three splits. For Food101, we randomly sample the train set and validation set from the original train set, and also randomly sample the test set from the original test set. Split Breakout CUB Food101 Oxford102 Train 80,000 4,795 6,000 5,120 Validation 9,503 1,199 1,000 1,228 Test 9,934 5,794 1,000 1,025 |
| Hardware Specification | Yes | GM-VAE is 1.93x faster than P-VAE and 1.41x faster than L-VAE in the experiments held on a single A100 40GB PCI GPU. |
| Software Dependencies | No | We use the official TensorFlow implementation from Dreamerv21 to reproduce the baseline results, i.e., with Euclidean and discrete latent space. This mentions TensorFlow and Dreamerv2 but does not specify their version numbers or other key software components with versions. |
| Experiment Setup | Yes | We use learning rate 1e-3, batch size 100, and Adam optimizer for training. We use Bernoulli loss as the reconstruction loss for Breakout experiments and negative log-likelihood loss as the reconstruction loss for CUB, Food101, and Oxford102 experiments. |