There is growing interest in designing recommender systems that aim at being fair towards item producers or their least satisfied users. Inspired by the domain of inequality measurement in economics, this paper explores the use of generalized Gini welfare functions (GGFs) as a means to specify the normative criterion that recommender systems should optimize for. GGFs weight individuals depending on their ranks in the population, giving more weight to worse-off individuals to promote equality. Depending on these weights, GGFs minimize the Gini index of item exposure to promote equality between items, or focus on the performance on specific quantiles of least satisfied users. GGFs for ranking are challenging to optimize because they are non-differentiable. We resolve this challenge by leveraging tools from non-smooth optimization and projection operators used in differentiable sorting. We present experiments using real datasets with up to 15k users and items, which show that our approach obtains better trade-offs than the baselines on a variety of recommendation tasks and fairness criteria.

While the world watches anxiously for signs of US President Donald Trump's next move vis-a-vis China, Chinese leaders remain focused on the next stage of their country's ongoing economic transformation. What they do should interest everyone ― especially US policymakers. China's industrialization process, like that of other successful East Asian economies, has combined profit-led investment, active industrial policy, and export discipline. But that approach has its limits, exemplified in the numerous developing countries that have attempted to climb the same development ladder, only to become stuck on the middle rungs or even to fall back, owing to what Harvard University economist Dani Rodrik has called "premature deindustrialization." China hopes to avoid this fate, with the help of "China Manufacturing 2025" (CM2025), a roadmap released by Premier Li Keqiang in 2015 to guide the country's industrial modernization.