A Maximal Correlation Framework for Fair Machine Learning

As machine learning algorithms grow in popularity and diversify to many industries, ethical and legal concerns regarding their fairness have become increasingly relevant. We explore the problem of algorithmic fairness, taking an information–theoretic view. The maximal correlation framework is introduced for expressing fairness constraints and is shown to be capable of being used to derive regularizers that enforce independence and separation-based fairness criteria, which admit optimization algorithms for both discrete and continuous variables that are more computationally efficient than existing algorithms. We show that these algorithms provide smooth performance–fairness tradeoff curves and perform competitively with state-of-the-art methods on both discrete datasets (COMPAS, Adult) and continuous datasets (Communities and Crimes).     

Interventional Fairness with Indirect Knowledge of Unobserved Protected Attributes

The deployment of machine learning (ML) systems in applications with societal impact has motivated the study of fairness for marginalized groups. Often, the protected attribute is absent from the training dataset for legal reasons. However, datasets still contain proxy attributes that capture protected information and can inject unfairness in the ML model. Some deployed systems allow auditors, decision makers, or affected users to report issues or seek recourse by flagging individual samples. In this work, we examine such systems and consider a feedback-based framework where the protected attribute is unavailable and the flagged samples are indirect knowledge. The reported samples are used as guidance to identify the proxy attributes that are causally dependent on the (unknown) protected attribute. We work under the causal interventional fairness paradigm. Without requiring the underlying structural causal model a priori, we propose an approach that performs conditional independence tests on observed data to identify such proxy attributes. We theoretically prove the optimality of our algorithm, bound its complexity, and complement it with an empirical evaluation demonstrating its efficacy on various real-world and synthetic datasets.     

Efficient One‐Step Synthesis of a Key Intermediate for the Synthesis of Azole Antifungals Using the Mitsunobu Protocol

A simple and single‐step process for coupling (2R,1S)‐1‐[2‐(2,4‐difluorophenyl)‐2‐oxiranyl]ethanol and various 1,2,4‐triazolones utilizing the Mitsunobu protocol is described. The product so formed is a key intermediate in the synthesis of azole antifungals with potent and broad‐spectrum activity against yeast and filamentous fungi.     

Efficient and Selective Demethylation of Heteroaryl Methyl Ethers in the Presence of Aryl Methyl Ethers

A new and efficient method for the demethylation of 6-membered aza-heterocyclic methyl ethers is described using lithium chloride and para-toluenesulfonic acid. This process is chemoselective for aza-heterocyclic methyl ethers in the presence of aryl methyl ethers.

Synthesis of 2[(1R,2R)-2-(2,4-Difluorophenyl)-2-hydroxy-1-methyl-3-(1H-1,2,4-triazol-yl)propyl]-4-[4-tetrafluoropropoxy)phenyl]-3-(2H,4H)-1,2,4-triazol-3-thione—A Novel and Potent Azole Antifungal Agent

A simple approach involving refluxing appropriately disubstituted thiosemicarbazide 8 in presence of formic acid for the synthesis of 1, a potent azole antifungal agent, has been described.