.png){kind=icon}
返回
eVAE: Evolutionary Variational Autoencoder
.png){kind=icon}
OA
AI
DOI：10.1109/TNNLS.2024.3359275.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Variational autoencoders (VAEs) are challenged by the imbalance between representation inference and task fitting caused by surrogate loss. To address this issue, existing methods adjust their balance by directly tuning their coefficients. However, these methods suffer from a tradeoff uncertainty, i.e., nondynamic regulation over iterations and inflexible hyperparameters for learning tasks. Accordingly, we make the first attempt to introduce an evolutionary VAE (eVAE), building on the variational information bottleneck (VIB) theory and integrative evolutionary neural learning. eVAE integrates a variational genetic algorithm (VGA) into VAE with variational evolutionary operators, including variational mutation (V-mutation), crossover, and evolution. Its training mechanism synergistically and dynamically addresses and updates the learning tradeoff uncertainty in the evidence lower bound (ELBO) without additional constraints and hyperparameter tuning. Furthermore, eVAE presents an evolutionary paradigm to tune critical factors of VAEs and addresses the premature convergence and random search problem in integrating evolutionary optimization into deep learning. Experiments show that eVAE addresses the KL-vanishing problem for text generation with low reconstruction loss, generates all the disentangled factors with sharp images, and improves image generation quality. eVAE achieves better disentanglement, generation performance, and generation-inference balance than its competitors. Code available at: https://github.com/amasawa/eVAE.
Keyword:
Task analysis
Training
Fitting
Convergence
Tuning
Probabilistic logic
Deep learning
Evolutionary variational autoencoder (eVAE)
variational autoencoder (VAE)
variational genetic algorithm (VGA)
期刊
IF:
8.9
论文数:
7.5K
被引数:
7.2W
机构
引用论文
Conservative Policy Construction Using Variational Autoencoders for Logged Data With Missing Values使用变分自动编码器构建具有缺失值的记录数据的保守策略OAAI
OAAI分享收藏Detecting out-of-distribution samples via variational auto-encoder with reliable uncertainty estimation.png)
NEURAL NETWORKS
OAAI
NEURAL NETWORKSIF6.3
OAAI分享收藏Electrical properties of sputtered A1N films and interface analyses by Auger electron spectroscopy
PREAI
分享收藏
查看更多内容