A Causal Bayesian Networks Viewpoint on Fairness

Chiappa, Silvia; Isaac, William

doi:10.1007/978-3-030-16744-8_1

Cited by 40 publications

(47 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Quijano (2000) again speaks to us, posing questions of who is protected by mainstream notions of fairness, and to understand the exclusion of certain groups as "continuities and legacies of colonialism embedded in modern structures of power, control, and hegemony". Such questions speak to a critical practice whose recent efforts, in response, have proposed fairness metrics that attempt to use causality (Chiappa and Isaac, 2018;Mitchell et al, 2018;Nabi and Shpitser, 2018;Madras et al, 2019) or interactivity (Canetti et al, 2019;Jung et al, 2019) to integrate more contextual awareness of human conceptions of fairness.…”

Section: Towards a Critical Technical Practice Of Aimentioning

confidence: 99%

Decolonial AI: Decolonial Theory as Sociotechnical Foresight in Artificial Intelligence

2020

View full text Add to dashboard Cite

This paper explores the important role of critical science, and in particular of post-colonial and decolonial theories, in understanding and shaping the ongoing advances in artificial intelligence. Artificial Intelligence (AI) is viewed as amongst the technological advances that will reshape modern societies and their relations. Whilst the design and deployment of systems that continually adapt holds the promise of far-reaching positive change, they simultaneously pose significant risks, especially to already vulnerable peoples. Values and power are central to this discussion. Decolonial theories use historical hindsight to explain patterns of power that shape our intellectual, political, economic, and social world. By embedding a decolonial critical approach within its technical practice, AI communities can develop foresight and tactics that can better align research and technology development with established ethical principles, centring vulnerable peoples who continue to bear the brunt of negative impacts of innovation and scientific progress. We highlight problematic applications that are instances of coloniality, and using a decolonial lens, submit three tactics that can form a decolonial field of artificial intelligence: creating a critical technical practice of AI, seeking reverse tutelage and reverse pedagogies, and the renewal of affective and political communities. The years ahead will usher in a wave of new scientific breakthroughs and technologies driven by AI research, making it incumbent upon AI communities to strengthen the social contract through ethical foresight and the multiplicity of intellectual perspectives available to us; ultimately supporting future technologies that enable greater well-being, with the goal of beneficence and justice for all. Keywords decolonisation • coloniality • sociotechnical foresight • intercultural ethics • critical technical practice • artificial intelligence • affective community

show abstract

Section: Towards a Critical Technical Practice Of Aimentioning

confidence: 99%

Decolonial AI: Decolonial Theory as Sociotechnical Foresight in Artificial Intelligence

2020

View full text Add to dashboard Cite

show abstract

“…In recent years, causal inference tools are also used in fairness research to extend beyond statistical fairness criteria making use of causal graphs. Similar to individual fairness, which requires similar individuals to be treated similarly (Dwork et al, 2012), counterfactual fairness requires the same model predictions before and after intervention on sensitive attributes in data-generating causal graphs (Kusner et al, 2017;Kilbertus et al, 2017;Chiappa, 2019;Chiappa and Isaac, 2019).…”

Section: Background and Related Workmentioning

confidence: 99%

Reducing Sentiment Bias in Language Models via Counterfactual Evaluation

Huang

Zhang

Jiang

et al. 2020

Findings of the Association for Computational Linguistics: EMNLP 2020

View full text Add to dashboard Cite

Advances in language modeling architectures and the availability of large text corpora have driven progress in automatic text generation. While this results in models capable of generating coherent texts, it also prompts models to internalize social biases present in the training corpus. This paper aims to quantify and reduce a particular type of bias exhibited by language models: bias in the sentiment of generated text. Given a conditioning context (e.g., a writing prompt) and a language model, we analyze if (and how) the sentiment of the generated text is affected by changes in values of sensitive attributes (e.g., country names, occupations, genders) in the conditioning context using a form of counterfactual evaluation. We quantify sentiment bias by adopting individual and group fairness metrics from the fair machine learning literature, and demonstrate that largescale models trained on two different corpora (news articles, and Wikipedia) exhibit considerable levels of bias. We then propose embedding and sentiment prediction-derived regularization on the language model's latent representations. The regularizations improve fairness metrics while retaining comparable levels of perplexity and semantic similarity.♦ Denotes equal contribution. ♥ Work done during an internship at DeepMind.

show abstract

“…In such a case, we want a fairness criterion that formalizes the requirement that only the unfair influence should be absent from the prediction. This can be obtained using the causal Bayesian networks framework as described below (for a more complete explanation, we refer the reader to the Supplementary Material and to Chiappa and Isaac (2019)).…”

Section: Fairness Criteria For Classification and Regressionmentioning

confidence: 99%

“…(referred to as sensitive attributes). This has motivated researchers to investigate techniques for ensuring that learned models satisfy fairness properties (Dwork et al 2012;Feldman et al 2015;Goh et al 2016;Chouldechova 2017;Corbett-Davies et al 2017;Gajane and Pechenizkiy 2017;Kusner et al 2017;Cotter et al 2018;Mitchell, Potash, and Barocas 2018;Verma and Rubin 2018;Zhang and Bareinboim 2018;Chiappa and Isaac 2019;Narasimhan et al 2020). Most often, fairness desiderata are expressed as constraints on the lower order moments or other functions of distributions corresponding to different sensitive attributes.…”

Section: Introductionmentioning

confidence: 99%

A General Approach to Fairness with Optimal Transport

Chiappa

Jiang

Stepleton

et al. 2020

AAAI

View full text Add to dashboard Cite

We propose a general approach to fairness based on transporting distributions corresponding to different sensitive attributes to a common distribution. We use optimal transport theory to derive target distributions and methods that allow us to achieve fairness with minimal changes to the unfair model. Our approach is applicable to both classification and regression problems, can enforce different notions of fairness, and enable us to achieve a Pareto-optimal trade-off between accuracy and fairness. We demonstrate that it outperforms previous approaches in several benchmark fairness datasets.

show abstract

A Causal Bayesian Networks Viewpoint on Fairness

Cited by 40 publications

References 28 publications

Decolonial AI: Decolonial Theory as Sociotechnical Foresight in Artificial Intelligence

Decolonial AI: Decolonial Theory as Sociotechnical Foresight in Artificial Intelligence

Reducing Sentiment Bias in Language Models via Counterfactual Evaluation

A General Approach to Fairness with Optimal Transport

Contact Info

Product

Resources

About