More Like this

1. Sample Selection for Fair and Robust Training

   Roh, Yuji; Lee, Kangwook; Whang, Steven; Suh, Changho (January 2021, Advances in neural information processing systems)

   Ranzato, M.; Beygelzimer, A.; Liang, P.S.; Vaughan, J.W.; Dauphin, Y. (Ed.)

   Fairness and robustness are critical elements of Trustworthy AI that need to be addressed together. Fairness is about learning an unbiased model while robustness is about learning from corrupted data, and it is known that addressing only one of them may have an adverse affect on the other. In this work, we propose a sample selection-based algorithm for fair and robust training. To this end, we formulate a combinatorial optimization problem for the unbiased selection of samples in the presence of data corruption. Observing that solving this optimization problem is strongly NP-hard, we propose a greedy algorithm that is efficient and effective in practice. Experiments show that our method obtains fairness and robustness that are better than or comparable to the state-of-the-art technique, both on synthetic and benchmark real datasets. Moreover, unlike other fair and robust training baselines, our algorithm can be used by only modifying the sampling step in batch selection without changing the training algorithm or leveraging additional clean data. 

   more » « less
2. Fairness of Interaction in Ranking under Position, Selection, and Trust Bias

   https://doi.org/10.1145/3652864  

   Ovaisi, Zohreh; Saadatpanah, Parsa; Sefati, Shahin; Ohannessian, Mesrob; Zheleva, Elena (April 2024, ACM Transactions on Recommender Systems)

   Ranking algorithms in online platforms serve not only users on the demand side, but also items on the supply side. While ranking has traditionally presented items in an order that maximizes their utility to users, the uneven interactions that different items receive as a result of such a ranking can pose item fairness concerns. Moreover, interaction is affected by various forms of bias, two of which have received considerable attention: position bias and selection bias. Position bias occurs due to lower likelihood of observation for items in lower ranked positions. Selection bias occurs because interaction is not possible with items below an arbitrary cutoff position chosen by the front-end application at deployment time (i.e., showing only the top-kitems). A less studied, third form of bias, trust bias, is equally important, as it makes interaction dependent on rank even after observation, by influencing the item’s perceived relevance. To capture interaction disparity in the presence of all three biases, in this paper we introduce a flexible fairness metric. Using this metric, we develop a post-processing algorithm that optimizes fairness in ranking through greedy exploration and allows a tradeoff between fairness and utility. Our algorithm outperforms state-of-the-art fair ranking algorithms on several datasets. 

   more » « less
3. User Fairness, Item Fairness, and Diversity for Rankings in Two-Sided Markets

   https://doi.org/10.1145/3471158.3472260  

   Wang, Lequn; Joachims, Thorsten (January 2021, ACM Conference on the Theory of Information Retrieval)

   Ranking items by their probability of relevance has long been the goal of conventional ranking systems. While this maximizes traditional criteria of ranking performance, there is a growing understanding that it is an oversimplification in online platforms that serve not only a diverse user population, but also the producers of the items. In particular, ranking algorithms are expected to be fair in how they serve all groups of users --- not just the majority group --- and they also need to be fair in how they divide exposure among the items. These fairness considerations can partially be met by adding diversity to the rankings, as done in several recent works. However, we show in this paper that user fairness, item fairness and diversity are fundamentally different concepts. In particular, we find that algorithms that consider only one of the three desiderata can fail to satisfy and even harm the other two. To overcome this shortcoming, we present the first ranking algorithm that explicitly enforces all three desiderata. The algorithm optimizes user and item fairness as a convex optimization problem which can be solved optimally. From its solution, a ranking policy can be derived via a novel Birkhoff-von Neumann decomposition algorithm that optimizes diversity. Beyond the theoretical analysis, we investigate empirically on a new benchmark dataset how effectively the proposed ranking algorithm can control user fairness, item fairness and diversity, as well as the trade-offs between them. 

   more » « less
4. Fair Link Prediction with Multi-Armed Bandit Algorithms

   https://doi.org/10.1145/3578503.3583624  

   Wang, Weixiang; Soundarajan, Sucheta (April 2023, WebSci '23: Proceedings of the 15th ACM Web Science Conference 2023)

   Recommendation systems have been used in many domains, and in recent years, ethical problems associated with such systems have gained serious attention. The problem of unfairness in friendship or link recommendation systems in social networks has begun attracting attention, as such unfairness can cause problems like segmentation and echo chambers. One challenge in this problem is that there are many fairness metrics for networks, and existing methods only consider the improvement of a single specific fairness indicator. In this work, we model the fair link prediction problem as a multi-armed bandit problem. We propose FairLink, a multi-armed bandit based framework that predicts new edges that are both accurate and well-behaved with respect to a fairness property of choice. This method allows the user to specify the desired fairness metric. Experiments on five real-world datasets show that FairLink can achieve a significant fairness improvement as compared to a standard recommendation algorithm, with only a small reduction in accuracy. 

   more » « less
5. An Empirical Study of Rich Subgroup Fairness for Machine Learning

   https://doi.org/10.1145/3287560.3287592  

   Kearns, Michael; Neel, Seth; Roth, Aaron; Wu, Zhiwei Steven (January 2019, ACM FAT* 2019)

   Kearns, Neel, Roth, and Wu [ICML 2018] recently proposed a notion of rich subgroup fairness intended to bridge the gap between statistical and individual notions of fairness. Rich subgroup fairness picks a statistical fairness constraint (say, equalizing false positive rates across protected groups), but then asks that this constraint hold over an exponentially or infinitely large collection of subgroups defined by a class of functions with bounded VC dimension. They give an algorithm guaranteed to learn subject to this constraint, under the condition that it has access to oracles for perfectly learning absent a fairness constraint. In this paper, we undertake an extensive empirical evaluation of the algorithm of Kearns et al. On four real datasets for which fairness is a concern, we investigate the basic convergence of the algorithm when instantiated with fast heuristics in place of learning oracles, measure the tradeoffs between fairness and accuracy, and compare this approach with the recent algorithm of Agarwal, Beygelzeimer, Dudik, Langford, and Wallach [ICML 2018], which implements weaker and more traditional marginal fairness constraints defined by individual protected attributes. We find that in general, the Kearns et al. algorithm converges quickly, large gains in fairness can be obtained with mild costs to accuracy, and that optimizing accuracy subject only to marginal fairness leads to classifiers with substantial subgroup unfairness. We also provide a number of analyses and visualizations of the dynamics and behavior of the Kearns et al. algorithm. Overall we find this algorithm to be effective on real data, and rich subgroup fairness to be a viable notion in practice 

   more » « less