Dissecting and Mitigating Diffusion Bias via Mechanistic Interpretability

• URL: http://arxiv.org/abs/2503.20483v1
• Date: Wed, 26 Mar 2025 12:13:35 GMT
• Title: Dissecting and Mitigating Diffusion Bias via Mechanistic Interpretability
• Authors: Yingdong Shi, Changming Li, Yifan Wang, Yongxiang Zhao, Anqi Pang, Sibei Yang, Jingyi Yu, Kan Ren,
• Abstract summary: Diffusion models have demonstrated impressive capabilities in diverse content.<n>These models often perpetuate social biases, including those related to gender and race.<n>We investigate the internal processes of diffusion models, identifying specific decision-making mechanisms.
• Score: 42.286648800681846
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion models have demonstrated impressive capabilities in synthesizing diverse content. However, despite their high-quality outputs, these models often perpetuate social biases, including those related to gender and race. These biases can potentially contribute to harmful real-world consequences, reinforcing stereotypes and exacerbating inequalities in various social contexts. While existing research on diffusion bias mitigation has predominantly focused on guiding content generation, it often neglects the intrinsic mechanisms within diffusion models that causally drive biased outputs. In this paper, we investigate the internal processes of diffusion models, identifying specific decision-making mechanisms, termed bias features, embedded within the model architecture. By directly manipulating these features, our method precisely isolates and adjusts the elements responsible for bias generation, permitting granular control over the bias levels in the generated content. Through experiments on both unconditional and conditional diffusion models across various social bias attributes, we demonstrate our method's efficacy in managing generation distribution while preserving image quality. We also dissect the discovered model mechanism, revealing different intrinsic features controlling fine-grained aspects of generation, boosting further research on mechanistic interpretability of diffusion models.

Related papers

• FairGen: Controlling Sensitive Attributes for Fair Generations in Diffusion Models via Adaptive Latent Guidance [19.65226469682089]
  Text-to-image diffusion models often exhibit biases toward specific demographic groups. In this paper, we tackle the challenge of mitigating generation bias towards any target attribute value. We propose FairGen, an adaptive latent guidance mechanism which controls the generation distribution during inference.
  arXiv  Detail & Related papers  (2025-02-25T23:47:22Z)
• Simple Guidance Mechanisms for Discrete Diffusion Models [44.377206440698586]
  We develop a new class of diffusion models that leverage uniform noise and that are more guidable because they can continuously edit their outputs.<n>We improve the quality of these models with a novel continuous-time variational lower bound that yields state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-12-13T15:08:30Z)
• Generative Intervention Models for Causal Perturbation Modeling [80.72074987374141]
  In many applications, it is a priori unknown which mechanisms of a system are modified by an external perturbation. We propose a generative intervention model (GIM) that learns to map these perturbation features to distributions over atomic interventions.
  arXiv  Detail & Related papers  (2024-11-21T10:37:57Z)
• Predicting Cascading Failures with a Hyperparametric Diffusion Model [66.89499978864741]
  We study cascading failures in power grids through the lens of diffusion models. Our model integrates viral diffusion principles with physics-based concepts. We show that this diffusion model can be learned from traces of cascading failures.
  arXiv  Detail & Related papers  (2024-06-12T02:34:24Z)
• Theoretical Insights for Diffusion Guidance: A Case Study for Gaussian Mixture Models [59.331993845831946]
  Diffusion models benefit from instillation of task-specific information into the score function to steer the sample generation towards desired properties. This paper provides the first theoretical study towards understanding the influence of guidance on diffusion models in the context of Gaussian mixture models.
  arXiv  Detail & Related papers  (2024-03-03T23:15:48Z)
• The Emergence of Reproducibility and Generalizability in Diffusion Models [10.188731323681575]
  Given the same starting noise input and a deterministic sampler, different diffusion models often yield remarkably similar outputs. We show that diffusion models are learning distinct distributions affected by the training data size. This valuable property generalizes to many variants of diffusion models, including those for conditional use, solving inverse problems, and model fine-tuning.
  arXiv  Detail & Related papers  (2023-10-08T19:02:46Z)
• Analyzing Bias in Diffusion-based Face Generation Models [75.80072686374564]
  Diffusion models are increasingly popular in synthetic data generation and image editing applications. We investigate the presence of bias in diffusion-based face generation models with respect to attributes such as gender, race, and age. We examine how dataset size affects the attribute composition and perceptual quality of both diffusion and Generative Adversarial Network (GAN) based face generation models.
  arXiv  Detail & Related papers  (2023-05-10T18:22:31Z)
• Diffusion Models in Vision: A Survey [73.10116197883303]
  A diffusion model is a deep generative model that is based on two stages, a forward diffusion stage and a reverse diffusion stage.<n> Diffusion models are widely appreciated for the quality and diversity of the generated samples, despite their known computational burdens.
  arXiv  Detail & Related papers  (2022-09-10T22:00:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.