A Case Study of Beta-Variational Auto-encoders, Disentanglement Impacts of Input Distribution and Beta-Variation Based Upon a Computational Multi-modal Particle Packing Simulation
Source abstract
Abstract
We present work that quantifies the disentanglement of the reconstruction of beta-variational auto-encoders ((eta )-VAEs) varying the hyper-parameter (eta ) for three different input distributions (Hall, https://zenodo.org/record/8003522, 2023). Currently the majority use of VAEs are for image processing and little work has been done in the field of material science using this machine learning technique to create reconstructions to explore the search for new designs. This work highlights the importance of the distribution shape can be more important than the quantity of data in creating neural network reconstructions such as (eta )-VAEs which has been used for this effort. Furthermore, this work highlights that the best disentangled reconstruction doesn’t necessarily create the best reconstruction.
Source: expertdata · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Machine Learning in Materials Science · Integrated Circuits and Semiconductor Failure Analysis · Electron and X-Ray Spectroscopy Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (15)
Show source-provided references
1. Hall J (2023) Beta-variational auto-encoder disentanglement with different input distributions for computational multi-modal particle packing. https://zenodo.org/record/8003522
2. Welling M, Kingma DP (2013) Auto-encoding variational bayes. arXiv:1312.6114
3. Rath SR (2020) Getting started with variational autoencoders using PyTorch. https://debuggercafe.com/getting-started-with-variational-autoencoders-using-pytorch/ [Online; accessed 29-Jan-2023]
4. Higgins I et al (2017) $$\beta $$-vae: learning basic visual concepts with a constrained variational framework. ICLR Conference Paper
5. Stein HS et al (2019) Machine learning of optical properties of materials–predicting spectra from images and images from spectra. Chem Sci 10:47–5510.1039/C8SC03077D ↗
6. Groener AM, Richards RJ (2022) Conditional $$\beta $$-VAE for de novo molecular generation. arXiv:2205.0159210.26434/chemrxiv-2022-g3gvz ↗
7. Gundersen K et al (2021) Semi-conditional variational auto-encoder for flow reconstruction and uncertainty quantification from limited observations. Phys Fluids 33:01711910.1063/5.0025779 ↗
8. Yu J et al (2022) Structure-aware conditional variational auto-encoder for constrained molecule optimization. Pattern Recogn 125:10858110.1016/j.patcog.2022.108581 ↗
9. Fardina FA, Shehu A (2022) Data size and quality matter: generating physically-realistic distance maps of protein tertiary structures. Biomolecules 12(7):90810.3390/biom12070908 ↗
10. Hall JR, Kauwe SK, Sparks TD (2021) Sequential machine learning applications of particle packing with large size variations. Integr Mater Manuf Innov 10:559–56710.1007/s40192-021-00230-7 ↗
11. Mathieu E et al (2019) Disentangling disentanglement in variational autoencoders. arXiv: 1812.02833v3
12. de Rijke M, Sepliarskaia A, Kiseleva J (2021) How to not measure disentanglement. arXiv: 1910.05587
13. Gray R (1990) Entropy and information theory, 1st edn. Springer Verlag, Cham10.1007/978-1-4757-3982-4 ↗
14. Chen RTQ et al (2019) Isolating sources of disentanglement in VAEs. arXiv:1802.04942v5
15. Sikka H et al (2019) A closer look at disentangling in $$\beta $$-VAE. arXiv:1912.05127v110.1109/IEEECONF44664.2019.9048921 ↗