Diffusion models have shown their effectiveness in generation tasks by well-approximating the underlying probability distribution. However, diffusion models are known to suffer from an amplified inherent bias from the training data in terms of fairness. While the sampling process of diffusion models can be controlled by conditional guidance, previous works have attempted to find empirical guidance to achieve quantitative fairness. To address this limitation, we propose a fairness-aware sampling method called \textit{attribute switching} mechanism for diffusion models. Without additional training, the proposed sampling can obfuscate sensitive attributes in generated data without relying on classifiers. We mathematically prove and experimentally demonstrate the effectiveness of the proposed method on two key aspects: (i) the generation of fair data and (ii) the preservation of the utility of the generated data.
Switched Flow Matching: Eliminating Singularities via Switching ODEs
Research Institute of Intelligent Complex Systems, Fudan University(复旦大学智能复杂系统研究院);Institutes of Brain Science, Fudan University(复旦大学脑科学研究院);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室)
Fairness-Regularized Online Optimization with Switching Costs
School of Information(信息学院);Rochester Institute of Technology(罗切斯特技术学院);Electrical and Computer Engineering(电气与计算机工程);University of California, Riverside(加州大学河滨分校);Computing & Mathematical Sciences(计算与数学科学);California Institute of Technology(加州理工学院)
LightFair: Towards an Efficient Alternative for Fair T2I Diffusion via Debiasing Pre-trained Text Encoders
State Key Laboratory of AI Safety, Institute of Computing Technology, CAS(人工智能安全国家重点实验室,计算技术研究所,中国科学院);School of Computer Science and Tech., University of Chinese Academy of Sciences(中国科学院大学计算机科学与技术学院);Peng Cheng Laboratory(鹏城实验室)
Thompson Sampling for Combinatorial Semi-bandits with Sleeping Arms and Long-Term Fairness Constraints
University of Victoria(维多利亚大学);Southeast University(东南大学);Harbin Institute of Technology(哈尔滨工业大学)
研究了具有长期公平性约束的组合睡眠多臂半强盗问题~(CSMAB-F)。针对该问题,采用Thompson Sampling~(TS)方法最大化总报酬,采用虚拟队列技术处理公平性约束,并设计了一种算法\emph{TS with beta priors and Bernoulli likelihoods for CSMAB-F~(TSCSF-B)}。进一步,我们证明了TSCSF-B能满足公平性约束,并且时间平均后悔的上界为$\frac{N}{2η} + O\left(\frac{\sqrt{mNT\ln T}}{T}\right)$,其中$N$是总的手臂数,$m$是每轮中能同时拉动的最大手臂数~(基数约束),$η$是公平性与奖励的权衡参数.通过放松公平性约束(即,令$η\rightarrow \infty$),该界归结为组合睡眠多臂半强盗问题TS算法的第一个与问题无关的界。最后,我们进行了数值实验,并使用一个高收视率的电影推荐应用程序,以显示所提出的算法的有效性和效率。
On the Origins of Sampling Bias: Implications on Fairness Measurement and Mitigation
University of Doha for Science and Technology (UDST)(多哈科技大学);CISPA Helmholtz Center for Information Security(CISPA亥姆霍兹信息安全中心);Université Claude Bernard Lyon 1(里昂第一大学);Université de Sousse(苏塞大学)
Automatic Fairness Testing of Neural Classifiers through Adversarial Sampling
Zhejiang University(浙江大学);Singapore Management University(新加坡管理大学);Huawei International Pte. Ltd.(华为国际私人有限公司);National University of Singapore(新加坡国立大学)
Bipartite Graph Variational Auto-Encoder with Fair Latent Representation to Account for Sampling Bias in Ecological Networks
agroparistech(巴黎农业学院);MNHN, CNRS, SU(法国国家自然博物馆、国家科学研究中心、苏弗尔(SU));Sorbonne Université, CNRS, IRD, INRAE, Université Paris Est Créteil, Université Paris Cité, Institute of Ecology and Environmental Sciences (iEES-Paris)(索邦大学、国家科学研究中心、国际发展研究所、法国国家农业食品研究咨询中心、巴黎东部大学、巴黎城市大学、生态与环境科学研究所(iEES-巴黎))
Breaking the Spurious Causality of Conditional Generation via Fairness Intervention with Corrective Sampling
Samsung Advanced Institute of Technology (SAIT)(三星先进技术研究院);Korea Advanced Institute of Science & Technology (KAIST)(韩国科学技术院);Pohang University of Science and Technology (POSTECH)(浦项科技大学)
Sampling a Near Neighbor in High Dimensions -- Who is the Fairest of Them All?
IT University of Copenhagen(哥本哈根信息技术大学);University of Illinois at Urbana-Champaign (UIUC)(伊利诺伊大学厄巴纳-香槟分校(UIUC));Toyota Technological Institute at Chicago (TTIC)(芝加哥丰田理工学院(TTIC));University of Copenhagen(哥本哈根大学);University of Padova(帕多瓦大学)
Physics-Guided Fair Graph Sampling for Water Temperature Prediction in River Networks
University of Pittsburgh(匹兹堡大学);University of Maryland(马里兰大学);U.S. Geological Survey(美国地质调查局);University of Florida(佛罗里达大学);University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校)
Achieving Hilbert-Schmidt Independence Under Rényi Differential Privacy for Fair and Private Data Generation
Department of Mathematics and Computer Science University of Southern Denmark(丹麦南部大学数学与计算机科学系);Department of Mathematics and Computer Science Freie Universität Berlin(柏林自由大学数学与计算机科学系);Faculty for Informatik Universität der Bundeswehr München(联邦国防军大学慕尼黑信息学院)