Latent Space Evolution Under Incremental Learning with Concept Drift (Student Abstract)

AAAI 2023 pp. 16166-16167

doi:10.1609/AAAI.V37I13.26943 /aaai/2023/bourbeau2023aaai-latent/

Abstract

This work investigates the evolution of latent space when deep learning models are trained incrementally in non-stationary environments that stem from concept drift. We propose a methodology for visualizing the incurred change in latent representations. We further show that classes not targeted by concept drift can be negatively affected, suggesting that the observation of all classes during learning may regularize the latent space.

PDF AAAI Semantic Scholar

Cite

Text

Bourbeau and Durand. "Latent Space Evolution Under Incremental Learning with Concept Drift (Student Abstract)." AAAI Conference on Artificial Intelligence, 2023. doi:10.1609/AAAI.V37I13.26943

Markdown

[Bourbeau and Durand. "Latent Space Evolution Under Incremental Learning with Concept Drift (Student Abstract)." AAAI Conference on Artificial Intelligence, 2023.](https://mlanthology.org/aaai/2023/bourbeau2023aaai-latent/) doi:10.1609/AAAI.V37I13.26943

BibTeX

@inproceedings{bourbeau2023aaai-latent,
  title     = {{Latent Space Evolution Under Incremental Learning with Concept Drift (Student Abstract)}},
  author    = {Bourbeau, Charles and Durand, Audrey},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2023},
  pages     = {16166-16167},
  doi       = {10.1609/AAAI.V37I13.26943},
  url       = {https://mlanthology.org/aaai/2023/bourbeau2023aaai-latent/}
}