Search

Partial Information Decomposition (PID) is a body of work within information theory that allows one to quantify the information that several random variables provide about another random variable, either individually (unique information), redundantly (shared information), or only jointly (synergistic information). This review article aims to provide a survey of some recent and emerging applications of partial information decomposition in algorithmic fairness and explainability, which are of immense importance given the growing use of machine learning in high-stakes applications. For instance, PID, in conjunction with causality, has enabled the disentanglement of the non-exempt disparity which is the part of the overall disparity that is not due to critical job necessities. Similarly, in federated learning, PID has enabled the quantification of tradeoffs between local and global disparities. We introduce a taxonomy that highlights the role of PID in algorithmic fairness and explainability in three main avenues: (i) Quantifying the legally non-exempt disparity for auditing or training; (ii) Explaining contributions of various features or data points; and (iii) Formalizing tradeoffs among different disparities in federated learning. Lastly, we also review techniques for the estimation of PID measures, as well as discuss some challenges and future directions.

Antioxidants are naturally occurring substances that combat oxidative damage in biological entities. An antioxidant achieves this by slowing or preventing the oxidation process that can damage cells in the body. It does this by getting oxidized itself in place of the cells. The aim of the present study was to evaluate the in vitro antioxidant and free radical scavenging activities of aqueous and 95% methanol leaf extracts of four herbs viz. Trigonella foenum-graecum L, Murraya koenigii, Coriandrum sativum and Centella asiatica which have frequent use in Indian cuisine. Both aqueous and 95% methanol leaf extracts have shown significant amount reducing power. Both aqueous and 95% methanol leaf extracts of Coriandrum sativum had significant DPPH radical scavenging activity with IC50 value of 0.21± 0.3 mg/L and 0.176 ± 0.008 mg/L respectively. The aqueous leaf extract of Trigonella foenum-graecum L showed low scavenging activity. Among all the leaf extracts, the aqueous leaf extract of Centella asiatica has exhibited significantly high NO radical scavenging activity (80%) with IC50 value of 0.11 ± 0.17 mg/L. The aqueous leaf extracts of the samples have showed significantly high superoxide radical scavenging activity. The activity was maximum for the aqueous leaf extract of Centella asiatica, IC50 value is 4.36 ± 0.41 mg/L. anti lipid peroxide activities were very high ( 90 %) for aqueous leaf extracts of Coriandrum sativum (IC50 = 0.064 ± 0.85 mg/L) and Centella asiatica (IC50 = 0.066 ± 0.9mg/L) at a concentration of 0.16 mg/L. The aqueous leaf extracts of the samples were found to contain large amounts of flavonoids and phenolic compounds and exhibited high antioxidant and free radical scavenging activities. These in vitro assays indicate that these plant extracts are significant source of natural antioxidants which might be helpful in preventing the progress of various oxidative stresses.