Unveiling Concept Attribution in Diffusion Models

Nguyen Hung-Quang, Hoang Phan, Khoa D Doan

Keywords: generative models, diffusion models, interpretability, concept erasure

TL;DR: We propose a framework to study how each component in diffusion models contributes to a concept.

Abstract:

Diffusion models have shown remarkable abilities in generating realistic and high-quality images from text prompts. However, a trained model remains black-box; little do we know about the role of its components in exhibiting a concept such as object or style.
Recent works employ causal tracing to localize layers storing knowledge in generative models.
In this work, we approach from a more general perspective and pose a question: \textit{``How do model components work jointly to demonstrate knowledge?''}.
We adapt component attribution to decompose diffusion models, unveiling how a component contributes to a concept.
Our framework allows effective model editing, in particular, we can erase a concept from diffusion models by removing positive components while remaining knowledge of other concepts.
Surprisingly, we also show that there exist components that contribute negatively to a concept that has not been discovered in the knowledge localization approach.
Experimental results confirm the role of positive and negative components pinpointed by our framework, depicting a complete view of interpreting generative models.

Primary Area: generative models

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 13622