Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models, Alvin Heng★, Harold Soh★, Neural Information Processing Systems (NeurIPS), 2023
Links:
The recent proliferation of large-scale text-to-image models has led to growing concerns that such models may be misused to generate harmful, misleading, and inappropriate content. Motivated by this issue, we derive a technique inspired by continual learning to selectively forget concepts in pretrained deep generative models.
Our method, dubbed Selective Amnesia, enables controllable forgetting where a user can specify how a concept should be forgotten. Selective Amnesia can be applied to conditional variational likelihood models, which encompass a variety of popular deep generative frameworks, including variational autoencoders and large-scale text-to-image diffusion models.
Experiments across different models demonstrate that our approach induces forgetting on a variety of concepts, from entire classes in standard datasets to celebrity and nudity prompts in text-to-image models.
Resources
You can find our paper here. Check out our repository here on github
Citation
Please consider citing our paper if you build upon our results and ideas.
Alvin Heng★, Harold Soh★, “Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models”, Neural Information Processing Systems (NeurIPS), 2023
@article{heng2023selective,
title={Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models},
author={Heng, Alvin and Soh, Harold},
journal={arXiv preprint arXiv:2305.10120},
year={2023}
}
Contact
If you have questions or comments, please contact Alvin or Harold.
Acknowledgements
This research/project is supported by the National Research Foundation Singapore and DSO National Laboratories under the AI Singapore Programme (AISG Award No: AISG2-RP-2020-017).
