Author name cluster

Ryan Brown

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

1 author row

NeurIPS Conference 2025 Conference Paper

FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Models

Zihao Fu
Ryan Brown
Shun Shao
Kai Rawal
Eoin Delaney
Chris Russell

Text-to-image diffusion models, such as Stable Diffusion, have demonstrated remarkable capabilities in generating high-quality and diverse images from natural language prompts. However, recent studies reveal that these models often replicate and amplify societal biases, particularly along demographic attributes like gender and race. In this paper, we introduce FairImagen (https: //github. com/fuzihaofzh/FairImagen), a post-hoc debiasing framework that operates on prompt embeddings to mitigate such biases without retraining or modifying the underlying diffusion model. Our method integrates Fair Principal Component Analysis to project CLIP-based input embeddings into a subspace that minimizes group-specific information while preserving semantic content. We further enhance debiasing effectiveness through empirical noise injection and propose a unified cross-demographic projection method that enables simultaneous debiasing across multiple demographic attributes. Extensive experiments across gender, race, and intersectional settings demonstrate that FairImagen significantly improves fairness with a moderate trade-off in image quality and prompt fidelity. Our framework outperforms existing post-hoc methods and offers a simple, scalable, and model-agnostic solution for equitable text-to-image generation.

PDF Details

AAAI Conference 2021 Conference Paper

Fair Influence Maximization: a Welfare Optimization Approach

Aida Rahmattalabi
Shahin Jabbari
Himabindu Lakkaraju
Phebe Vayanos
Max Izenberg
Ryan Brown
Eric Rice
Milind Tambe

Several behavioral, social, and public health interventions, such as suicide/HIV prevention or community preparedness against natural disasters, leverage social network information to maximize outreach. Algorithmic influence maximization techniques have been proposed to aid with the choice of “peer leaders” or “influencers” in such interventions. Yet, traditional algorithms for influence maximization have not been designed with these interventions in mind. As a result, they may disproportionately exclude minority communities from the benefits of the intervention. This has motivated research on fair influence maximization. Existing techniques come with two major drawbacks. First, they require committing to a single fairness measure. Second, these measures are typically imposed as strict constraints leading to undesirable properties such as wastage of resources. To address these shortcomings, we provide a principled characterization of the properties that a fair influence maximization algorithm should satisfy. In particular, we propose a framework based on social welfare theory, wherein the cardinal utilities derived by each community are aggregated using the isoelastic social welfare functions. Under this framework, the trade-off between fairness and efficiency can be controlled by a single inequality aversion design parameter. We then show under what circumstances our proposed principles can be satisfied by a welfare function. The resulting optimization problem is monotone and submodular and can be solved efficiently with optimality guarantees. Our framework encompasses as special cases leximin and proportional fairness. Extensive experiments on synthetic and real world datasets including a case study on landslide risk management demonstrate the efficacy of the proposed framework12

PDF Details

YNIMG Journal 2016 Journal Article

A nested phosphorus and proton coil array for brain magnetic resonance imaging and spectroscopy

Ryan Brown
Karthik Lakshmanan
Guillaume Madelin
Prodromos Parasoglou

A dual-nuclei radiofrequency coil array was constructed for phosphorus and proton magnetic resonance imaging and spectroscopy of the human brain at 7T. An eight-channel transceive degenerate birdcage phosphorus module was implemented to provide whole-brain coverage and significant sensitivity improvement over a standard dual-tuned loop coil. A nested eight-channel proton module provided adequate sensitivity for anatomical localization without substantially sacrificing performance on the phosphorus module. The developed array enabled phosphorus spectroscopy, a saturation transfer technique to calculate the global creatine kinase forward reaction rate, and single-metabolite whole-brain imaging with 1. 4cm nominal isotropic resolution in 15min (2. 3cm actual resolution), while additionally enabling 1mm isotropic proton imaging. This study demonstrates that a multi-channel array can be utilized for phosphorus and proton applications with improved coverage and/or sensitivity over traditional single-channel coils. The efficient multi-channel coil array, time-efficient pulse sequences, and the enhanced signal strength available at ultra-high fields can be combined to allow volumetric assessment of the brain and could provide new insights into the underlying energy metabolism impairment in several neurodegenerative conditions, such as Alzheimer's and Parkinson's diseases, as well as mental disorders such as schizophrenia.

Details DOI