A Survey on Bias and Fairness in Machine Learning

Mehrabi, Ninareh; Saxena, Nripsuta; Lerman, Kristina; Galstyan, Aram

doi:10.48550/arxiv.1908.09635

Cited by 229 publications

(341 citation statements)

References 63 publications

Supporting

Mentioning

335

Contrasting

Unclassified

Order By: Relevance

“…Several formulations of fairness have been proposed in the ML community [18], [5]. The first and most basic formulation is to ignore sensitive attributes with attribute unaware fairness: if a model cannot use a sensitive attribute in its prediction, the model is fair [5].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

FairMod: Fair Link Prediction and Recommendation via Graph Modification

Current¹,

He²,

Gurukar³

et al. 2022

Preprint

View full text Add to dashboard Cite

As machine learning becomes more widely adopted across domains, it is critical that researchers and ML engineers think about the inherent biases in the data that may be perpetuated by the model. Recently, many studies have shown that such biases are also imbibed in Graph Neural Network (GNN) models if the input graph is biased. In this work, we aim to mitigate the bias learned by GNNs through modifying the input graph. To that end, we propose FairMod, a Fair Graph Modification methodology with three formulations: the Global Fairness Optimization (GFO), Community Fairness Optimization (CFO), and Fair Edge Weighting (FEW) models. Our proposed models perform either microscopic or macroscopic edits to the input graph while training GNNs and learn node embeddings that are both accurate and fair under the context of link recommendations. We demonstrate the effectiveness of our approach on four real world datasets and show that we can improve the recommendation fairness by several factors at negligible cost to link prediction accuracy.CCS Concepts: • Computing methodologies → Neural networks.

show abstract

Section: Related Workmentioning

confidence: 99%

“…We select demographic parity [5] as our fairness criteria. Informally, demographic parity is satisfied if the output of the model is not dependent on a given sensitive attribute [18]. Formally, we define demographic parity fairness criteria on the link prediction problem as follows.…”

Section: Definition 1 (Graph Representation Learning [? ]mentioning

confidence: 99%

FairMod: Fair Link Prediction and Recommendation via Graph Modification

Current¹,

He²,

Gurukar³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Manifestations of different kinds of biases have been shown to exist in various components used to develop NLP and ML systems, from training data to pre-trained models to algorithms and resources [9,12,30,31,39]. Although several papers discussed various methodologies to de-bias word embedding models, these techniques have been scrutinized on several occasions [4,18].…”

Section: Word Embedding Biasmentioning

confidence: 99%

Gender Bias in Text: Labeled Datasets and Lexicons

Doughman¹,

Khreich²

2022

Preprint

View full text Add to dashboard Cite

Language has a profound impact on our thoughts, perceptions, and conceptions of gender roles. Genderinclusive language is, therefore, a key tool to promote social inclusion and contribute to achieving gender equality. Consequently, detecting and mitigating gender bias in texts is instrumental in halting its propagation and societal implications. However, there is a lack of gender bias datasets and lexicons for automating the detection of gender bias using supervised and unsupervised machine learning (ML) and natural language processing (NLP) techniques. Therefore, the main contribution of this work is to publicly provide labeled datasets and exhaustive lexicons by collecting, annotating, and augmenting relevant sentences to facilitate the detection of gender bias in English text. Towards this end, we present an updated version of our previously proposed taxonomy by re-formalizing its structure, adding a new bias type, and mapping each bias subtype to an appropriate detection methodology. The released datasets and lexicons span multiple bias subtypes including: Generic He, Generic She, Explicit Marking of Sex, and Gendered Neologisms. We leveraged the use of word embedding models to further augment the collected lexicons. The underlying motivation of our work is to enable the technical community to combat gender bias in text and halt its propagation using ML and NLP techniques.CCS Concepts: • Social and professional topics → Gender; • Computing methodologies → Language resources; Natural language processing.

show abstract

“…This means that if the ML algorithms had been trained on the modified training data, it would not have exhibited the unexpected or undesirable behavior or would have exhibited this behavior to a lesser degree. Explanations generated by our framework, which complement existing approaches in XAI, are crucial for helping system developers and ML practitioners to debug ML algorithms for data errors and bias in training data, such as measurement errors and misclassifications [35,42,94], data imbalance [27], missing data and selection bias [29,62,63], covariate shift [74,82], technical biases introduced during data preparation [85], and poisonous data points injected through adversarial attacks [36,43,65,83]. It is known in the algorithmic fairness literature that information about the source of bias is critically needed to build fair ML algorithms because no current bias mitigation solution fits all situations [27,31,36,82,94].…”

Section: Introductionmentioning

confidence: 99%

“…More compact and coherent descriptions are needed. Furthermore, sources of bias and discrimination in training data are typically not randomly distributed across different sub-populations; rather they manifest systematic errors in data collection, selection, feature engineering, and curation [29,35,42,62,63,70,94]. That is, more often than not, certain cohesive subsets of training data are responsible for bias.…”

Section: Introductionmentioning

confidence: 99%

Interpretable Data-Based Explanations for Fairness Debugging

Pradhan¹,

Zhu²,

Glavic³

et al. 2021

Preprint

View full text Add to dashboard Cite

A wide variety of fairness metrics and eXplainable Artificial Intelligence (XAI) approaches have been proposed in the literature to identify bias in machine learning models that are used in critical real-life contexts. However, merely reporting on a model's bias, or generating explanations using existing XAI techniques is insufficient to locate and eventually mitigate sources of bias. In this work, we introduce Gopher, a system that produces compact, interpretable and causal explanations for bias or unexpected model behavior by identifying coherent subsets of the training data that are root-causes for this behavior. Specifically, we introduce the concept of causal responsibility that quantifies the extent to which intervening on training data by removing or updating subsets of it can resolve the bias. Building on this concept, we develop an efficient approach for generating the top-𝑘 patterns that explain model bias that utilizes techniques from the ML community to approximate causal responsibility and uses pruning rules to manage the large search space for patterns. Our experimental evaluation demonstrates the effectiveness of Gopher in generating interpretable explanations for identifying and debugging sources of bias.

show abstract

A Survey on Bias and Fairness in Machine Learning

Cited by 229 publications

References 63 publications

FairMod: Fair Link Prediction and Recommendation via Graph Modification

FairMod: Fair Link Prediction and Recommendation via Graph Modification

Gender Bias in Text: Labeled Datasets and Lexicons

Interpretable Data-Based Explanations for Fairness Debugging

Contact Info

Product

Resources

About