Recent work highlights the role of causality in designing equitable decision-making algorithms. It is not immediately clear, however, how existing causal conceptions of fairness relate to one another, or what the consequences are of using these definitions as design principles. Here, we first assemble and categorize popular causal definitions of algorithmic fairness into two broad families: (1) those that constrain the effects of decisions on counterfactual disparities; and (2) those that constrain the effects of legally protected characteristics, like race and gender, on decisions. We then show, analytically and empirically, that both families of definitions \emph{almost always} -- in a measure theoretic sense -- result in strongly Pareto dominated decision policies, meaning there is an alternative, unconstrained policy favored by every stakeholder with preferences drawn from a large, natural class. For example, in the case of college admissions decisions, policies constrained to satisfy causal fairness definitions would be disfavored by every stakeholder with neutral or positive preferences for both academic preparedness and diversity. Indeed, under a prominent definition of causal fairness, we prove the resulting policies require admitting all students with the same probability, regardless of academic qualifications or group membership. Our results highlight formal limitations and potential adverse consequences of common mathematical notions of causal fairness.

The popularity of machine learning has increased the risk of unfair models getting deployed in high-stake applications, such as justice system, drug/vaccination design, and medical diagnosis. Although there are effective methods to train fair models from scratch, how to automatically reveal and explain the unfairness of a trained model remains a challenging task. Revealing unfairness of machine learning models in interpretable fashion is a critical step towards fair and trustworthy AI. In this paper, we systematically tackle the novel task of revealing unfair models by mining interpretable evidence (RUMIE). The key idea is to find solid evidence in the form of a group of data instances discriminated most by the model. To make the evidence interpretable, we also find a set of human-understandable key attributes and decision rules that characterize the discriminated data instances and distinguish them from the other non-discriminated data. As demonstrated by extensive experiments on many real-world data sets, our method finds highly interpretable and solid evidence to effectively reveal the unfairness of trained models. Moreover, it is much more scalable than all of the baseline methods.

Recent works have shown how the reasoning capabilities of Large Language Models (LLMs) can be applied to domains beyond natural language processing, such as planning and interaction for robots. These embodied problems require an agent to understand many semantic aspects of the world: the repertoire of skills available, how these skills influence the world, and how changes to the world map back to the language. LLMs planning in embodied environments need to consider not just what skills to do, but also how and when to do them - answers that change over time in response to the agent's own choices. In this work, we investigate to what extent LLMs used in such embodied contexts can reason over sources of feedback provided through natural language, without any additional training. We propose that by leveraging environment feedback, LLMs are able to form an inner monologue that allows them to more richly process and plan in robotic control scenarios. We investigate a variety of sources of feedback, such as success detection, scene description, and human interaction. We find that closed-loop language feedback significantly improves high-level instruction completion on three domains, including simulated and real table top rearrangement tasks and long-horizon mobile manipulation tasks in a kitchen environment in the real world.

Seventeenth-century Amsterdam is known for three things: Rembrandt, the Bubonic Plague and Tulip Mania. It was 1637, the height of the Dutch Golden Age. Tulip bulbs were scarce and demand for them soared. They were also a symbol of status. Acres of land were swapped for seeds that would yield no more than a few flowers.

These categorization systems go deeper than the broader asset class based classification (equity, fixed income, etc) and provide Categorization of mutual funds or Exchange-Traded-funds (ETFs) further granular categories based on the portfolio breakdown. They have long served the financial analysts to perform peer analysis have been used to identify the top performing as well as worst for various purposes starting from competitor analysis, to quantifying performing funds within their peer groups, called peer analysis portfolio diversification. The categorization methodology of funds; to identify a home-grown fund to recommend against a usually relies on fund composition data in the structured format competitor's fund; to explain similarities and advantages of homegrown extracted from the Form N-1A. Here, we initiate a study to learn products compared to competitors' products for marketing the categorization system directly from the unstructured data as purposes; to quantify portfolio diversification of a given fund of depicted in the forms using natural language processing (NLP).

Inflammatory bowel disease (IBD), in particular ulcerative colitis (UC), is graded by endoscopists and this assessment is the basis for risk stratification and therapy monitoring. Presently, endoscopic characterisation is largely operator dependant leading to sometimes undesirable clinical outcomes for patients with IBD. We focus on the Mayo Endoscopic Scoring (MES) system which is widely used but requires the reliable identification of subtle changes in mucosal inflammation. Most existing deep learning classification methods cannot detect these fine-grained changes which make UC grading such a challenging task. In this work, we introduce a novel patch-level instance-group discrimination with pretext-invariant representation learning (PLD-PIRL) for self-supervised learning (SSL). Our experiments demonstrate both improved accuracy and robustness compared to the baseline supervised network and several state-of-the-art SSL methods. Compared to the baseline (ResNet50) supervised classification our proposed PLD-PIRL obtained an improvement of 4.75% on hold-out test data and 6.64% on unseen center test data for top-1 accuracy.

The ability to collect and process large amounts of data represents additional value for many companies in today's market. The world of sports has been no exception, starting with baseball with the emergence of SABRmetrics in the 1980s, through motor racing to sports such as basketball and soccer more recently. The creation of models and metrics through artificial intelligence allows sports fans to analyze the game from another perspective and, for their professionals, to gain a competitive advantage over their rivals. In the case of soccer, probably the most popular metric is the one known as expected goal (xG). The xG is intended to measure the probability that a shot will result in a goal, taking into account variables such as the position of the shot, the position of the goalkeeper or the part of the body with which the shot is taken. As it is a probability, it should take values between 0 and 1, so that for the clearest opportunities (for example, a shot inside the small area without a goalkeeper) it takes values close to 1, and for shots further away or with greater difficulty it tends to 0. This metric is very useful for coaching staffs and scouting teams to evaluate the finishing or chance-creating ability of different players.

Originally published on Towards AI the World's Leading AI and Technology News and Media Company. If you are building an AI-related product or service, we invite you to consider becoming an AI sponsor. At Towards AI, we help scale AI and technology startups. Let us help you unleash your technology to the masses. This article is the third part of the AI Ethics for Data Science essential series.

Active speaker detection (ASD) systems are important modules for analyzing multi-talker conversations. They aim to detect which speakers or none are talking in a visual scene at any given time. Existing research on ASD does not agree on the definition of active speakers. We clarify the definition in this work and require synchronization between the audio and visual speaking activities. This clarification of definition is motivated by our extensive experiments, through which we discover that existing ASD methods fail in modeling the audio-visual synchronization and often classify unsynchronized videos as active speaking. To address this problem, we propose a cross-modal contrastive learning strategy and apply positional encoding in attention modules for supervised ASD models to leverage the synchronization cue. Experimental results suggest that our model can successfully detect unsynchronized speaking as not speaking, addressing the limitation of current models.

In this work we use Equal Oppportunity (EO) doctrines from political philosophy to make explicit the normative judgements embedded in different conceptions of algorithmic fairness. We contrast formal EO approaches that narrowly focus on fair contests at discrete decision points, with substantive EO doctrines that look at people's fair life chances more holistically over the course of a lifetime. We use this taxonomy to provide a moral interpretation of the impossibility results as the incompatibility between different conceptions of a fair contest -- foward-facing versus backward-facing -- when people do not have fair life chances. We use this result to motivate substantive conceptions of algorithmic fairness and outline two plausible fair decision procedures based on the luck-egalitarian doctrine of EO, and Rawls's principle of fair equality of opportunity. Equality of Opportunity (EO) is a philosophical doctrine that objects to morally arbitrary and irrelevant factors affecting people's access to desirable positions, and the social goods attached to them (such as opportunity and wealth). In an EO-respecting society, all people, irrespective of their morally arbitrary characteristics, such as socio-economic background, gender, race, or disability status, have comparable access to the opportunities that they desire. Similarly, in fair machine learning (fair-ML), we are usually interested in ensuring that the outputs of algorithmic systems, specially those used in critical social contexts, do not systematically skew along the lines of membership in protected groups based on gender, race, or disability. In so far as protected groups are constructed on the basis of morally arbitrary factors, the moral desiderata of EO doctrines from political philosophy align exactly with the fairness-related concerns in machine learning. In this work, we employ ideas from the rich literature on Equality of Opportunity from political philosophy [1-11] to clarify the normative foundations of fairness and justice-related interventions, and gauge the efficacy of current algorithmic approaches that attempt to codify these criteria. There are two broad principles of EO, namely, the principle of fair contests and the principle of fair life chances. Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. The principle of fair contests, commonly understood as the nondiscrimination principle, says that competitions for desirable positions should be open to all and should be adjudicated based on competitors' relevant merits, or qualifications.