Bias Begets Bias: The Impact of Biased Embeddings on Diffusion Models

• URL: http://arxiv.org/abs/2409.09569v1
• Date: Sun, 15 Sep 2024 01:09:55 GMT
• Title: Bias Begets Bias: The Impact of Biased Embeddings on Diffusion Models
• Authors: Sahil Kuchlous, Marvin Li, Jeffrey G. Wang,
• Abstract summary: Text-to-Image (TTI) systems have come under increased scrutiny for social biases. We investigate embedding spaces as a source of bias for TTI models. We find that biased multimodal embeddings like CLIP can result in lower alignment scores for representationally balanced TTI models.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With the growing adoption of Text-to-Image (TTI) systems, the social biases of these models have come under increased scrutiny. Herein we conduct a systematic investigation of one such source of bias for diffusion models: embedding spaces. First, because traditional classifier-based fairness definitions require true labels not present in generative modeling, we propose statistical group fairness criteria based on a model's internal representation of the world. Using these definitions, we demonstrate theoretically and empirically that an unbiased text embedding space for input prompts is a necessary condition for representationally balanced diffusion models, meaning the distribution of generated images satisfy diversity requirements with respect to protected attributes. Next, we investigate the impact of biased embeddings on evaluating the alignment between generated images and prompts, a process which is commonly used to assess diffusion models. We find that biased multimodal embeddings like CLIP can result in lower alignment scores for representationally balanced TTI models, thus rewarding unfair behavior. Finally, we develop a theoretical framework through which biases in alignment evaluation can be studied and propose bias mitigation methods. By specifically adapting the perspective of embedding spaces, we establish new fairness conditions for diffusion model development and evaluation.

Related papers

• Comparing Fairness of Generative Mobility Models [3.699135947901772]
  This work examines the fairness of generative mobility models, addressing the often overlooked dimension of equity in model performance across geographic regions. Predictive models built on crowd flow data are instrumental in understanding urban structures and movement patterns. We propose a novel framework for assessing fairness by measuring utility and equity of generated traces.
  arXiv  Detail & Related papers  (2024-11-07T06:01:12Z)
• Editable Fairness: Fine-Grained Bias Mitigation in Language Models [52.66450426729818]
  We propose a novel debiasing approach, Fairness Stamp (FAST), which enables fine-grained calibration of individual social biases. FAST surpasses state-of-the-art baselines with superior debiasing performance. This highlights the potential of fine-grained debiasing strategies to achieve fairness in large language models.
  arXiv  Detail & Related papers  (2024-08-07T17:14:58Z)
• MIST: Mitigating Intersectional Bias with Disentangled Cross-Attention Editing in Text-to-Image Diffusion Models [3.3454373538792552]
  We introduce a method that addresses intersectional bias in diffusion-based text-to-image models by modifying cross-attention maps in a disentangled manner. Our approach utilizes a pre-trained Stable Diffusion model, eliminates the need for an additional set of reference images, and preserves the original quality for unaltered concepts.
  arXiv  Detail & Related papers  (2024-03-28T17:54:38Z)
• Unveil Conditional Diffusion Models with Classifier-free Guidance: A Sharp Statistical Theory [87.00653989457834]
  Conditional diffusion models serve as the foundation of modern image synthesis and find extensive application in fields like computational biology and reinforcement learning. Despite the empirical success, theory of conditional diffusion models is largely missing. This paper bridges the gap by presenting a sharp statistical theory of distribution estimation using conditional diffusion models.
  arXiv  Detail & Related papers  (2024-03-18T17:08:24Z)
• RS-Corrector: Correcting the Racial Stereotypes in Latent Diffusion Models [20.53932777919384]
  We propose a framework called "RS-Corrector" to establish an anti-stereotypical preference in the latent space and update the latent code for refined generated results. Extensive empirical evaluations demonstrate that the introduced themodel effectively corrects the racial stereotypes of the well-trained Stable Diffusion model.
  arXiv  Detail & Related papers  (2023-12-08T02:59:29Z)
• 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)
• Debiasing Vision-Language Models via Biased Prompts [79.04467131711775]
  We propose a general approach for debiasing vision-language foundation models by projecting out biased directions in the text embedding. We show that debiasing only the text embedding with a calibrated projection matrix suffices to yield robust classifiers and fair generative models.
  arXiv  Detail & Related papers  (2023-01-31T20:09:33Z)
• Bi-Noising Diffusion: Towards Conditional Diffusion Models with Generative Restoration Priors [64.24948495708337]
  We introduce a new method that brings predicted samples to the training data manifold using a pretrained unconditional diffusion model. We perform comprehensive experiments to demonstrate the effectiveness of our approach on super-resolution, colorization, turbulence removal, and image-deraining tasks.
  arXiv  Detail & Related papers  (2022-12-14T17:26:35Z)
• General Greedy De-bias Learning [163.65789778416172]
  We propose a General Greedy De-bias learning framework (GGD), which greedily trains the biased models and the base model like gradient descent in functional space. GGD can learn a more robust base model under the settings of both task-specific biased models with prior knowledge and self-ensemble biased model without prior knowledge.
  arXiv  Detail & Related papers  (2021-12-20T14:47:32Z)
• Wasserstein-based fairness interpretability framework for machine learning models [0.2519906683279153]
  We introduce a fairness interpretability framework for measuring and explaining the bias in classification and regression models. We measure the model bias across sub-population distributions in the model output using the Wasserstein metric. We take into account the favorability of both the model and predictors with respect to the non-protected class.
  arXiv  Detail & Related papers  (2020-11-06T02:01:29Z)

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.