More Like this

1. Fairness without Demographics through Knowledge Distillation.

   Chai, J. (October 2022, Advances in Neural Information Processing Systems Proceedings)

   Koyejo, S.; Mohamed, S.; Agarwal, A.; Belgrave, D.; Cho, K.; Oh, A. (Ed.)

   Most of existing work on fairness assumes available demographic information in the training set. In practice, due to legal or privacy concerns, when demographic information is not available in the training set, it is crucial to find alternative objectives to ensure fairness. Existing work on fairness without demographics follows Rawlsian Max-Min fairness objectives. However, such constraints could be too strict to improve group fairness, and could lead to a great decrease in accuracy. In light of these limitations, in this paper, we propose to solve the problem from a new perspective, i.e., through knowledge distillation. Our method uses soft label from an overfitted teacher model as an alternative, and we show from preliminary experiments that soft labelling is beneficial for improving fairness. We analyze theoretically the fairness of our method, and we show that our method can be treated as an error-based reweighing. Experimental results on three datasets show that our method outperforms state-of-the-art alternatives, with notable improvements in group fairness and with relatively small decrease in accuracy. 

   more » « less
2. FairLP: Towards Fair Link Prediction on Social Network Graphs

   https://doi.org/10.1609/icwsm.v16i1.19321  

   Li, Yanying; Wang, Xiuling; Ning, Yue; Wang, Hui (June 2022, Proceedings of the International AAAI Conference on Web and Social Media)

   Link prediction has been widely applied in social network analysis. Despite its importance, link prediction algorithms can be biased by disfavoring the links between individuals in particular demographic groups. In this paper, we study one particular type of bias, namely, the bias in predicting inter-group links (i.e., links across different demographic groups). First, we formalize the definition of bias in link prediction by providing quantitative measurements of accuracy disparity, which measures the difference in prediction accuracy of inter-group and intra-group links. Second, we unveil the existence of bias in six existing state-of-the-art link prediction algorithms through extensive empirical studies over real world datasets. Third, we identify the imbalanced density across intra-group and inter-group links in training graphs as one of the underlying causes of bias in link prediction. Based on the identified cause, fourth, we design a pre-processing bias mitigation method named FairLP to modify the training graph, aiming to balance the distribution of intra-group and inter-group links while preserving the network characteristics of the graph. FairLP is model-agnostic and thus is compatible with any existing link prediction algorithm. Our experimental results on real-world social network graphs demonstrate that FairLP achieves better trade-off between fairness and prediction accuracy than the existing fairness-enhancing link prediction methods. 

   more » « less
3. Self-Supervised Fair Representation Learning without Demographics

   Chai, J. (October 2022, Advances in Neural Information Processing Systems Proceedings)

   Koyejo, S.; Mohamed, S.; Agarwal, A.; Belgrave, D.; Cho, K.; Oh, A. (Ed.)

   Fairness has become an important topic in machine learning. Generally, most literature on fairness assumes that the sensitive information, such as gender or race, is present in the training set, and uses this information to mitigate bias. However, due to practical concerns like privacy and regulation, applications of these methods are restricted. Also, although much of the literature studies supervised learning, in many real-world scenarios, we want to utilize the large unlabelled dataset to improve the model's accuracy. Can we improve fair classification without sensitive information and without labels? To tackle the problem, in this paper, we propose a novel reweighing-based contrastive learning method. The goal of our method is to learn a generally fair representation without observing sensitive attributes.Our method assigns weights to training samples per iteration based on their gradient directions relative to the validation samples such that the average top-k validation loss is minimized. Compared with past fairness methods without demographics, our method is built on fully unsupervised training data and requires only a small labelled validation set. We provide rigorous theoretical proof of the convergence of our model. Experimental results show that our proposed method achieves better or comparable performance than state-of-the-art methods on three datasets in terms of accuracy and several fairness metrics. 

   more » « less
4. Self-Supervised Fair Representation Learning without Demographics

   Chai, Junyi; Wang, Xiaoqian (December 2022, Advances in neural information processing systems)

   Fairness has become an important topic in machine learning. Generally, most literature on fairness assumes that the sensitive information, such as gender or race, is present in the training set, and uses this information to mitigate bias. However, due to practical concerns like privacy and regulation, applications of these methods are restricted. Also, although much of the literature studies supervised learning, in many real-world scenarios, we want to utilize the large unlabelled dataset to improve the model's accuracy. Can we improve fair classification without sensitive information and without labels? To tackle the problem, in this paper, we propose a novel reweighing-based contrastive learning method. The goal of our method is to learn a generally fair representation without observing sensitive attributes.Our method assigns weights to training samples per iteration based on their gradient directions relative to the validation samples such that the average top-k validation loss is minimized. Compared with past fairness methods without demographics, our method is built on fully unsupervised training data and requires only a small labelled validation set. We provide rigorous theoretical proof of the convergence of our model. Experimental results show that our proposed method achieves better or comparable performance than state-of-the-art methods on three datasets in terms of accuracy and several fairness metrics. 

   more » « less
5. Recovering from Biased Data: Can Fairness Constraints Improve Accuracy?

   Blum, Avrim; Stangl, Kevin (June 2020, Symposium on Foundations of Responsible Computing (FORC))

   Multiple fairness constraints have been proposed in the literature, motivated by a range of concerns about how demographic groups might be treated unfairly by machine learning classifiers. In this work we consider a different motivation; learning from biased training data. We posit several ways in which training data may be biased, including having a more noisy or negatively biased labeling process on members of a disadvantaged group, or a decreased prevalence of positive or negative examples from the disadvantaged group, or both. Given such biased training data, Empirical Risk Minimization (ERM) may produce a classifier that not only is biased but also has suboptimal accuracy on the true data distribution. We examine the ability of fairness-constrained ERM to correct this problem. In particular, we find that the Equal Opportunity fairness constraint [Hardt et al., 2016] combined with ERM will provably recover the Bayes optimal classifier under a range of bias models. We also consider other recovery methods including re-weighting the training data, Equalized Odds, and Demographic Parity, and Calibration. These theoretical results provide additional motivation for considering fairness interventions even if an actor cares primarily about accuracy. 

   more » « less