Events

Operationalizing Responsible Machine Learning: From Equality Towards Equity

With the widespread proliferation of machine learning, there arises both the opportunity for societal benefit as well as the risk of harm. Approaching responsible machine learning is challenging because technical approaches may prioritize a mathematical definition of fairness that correlates poorly to real-world constructs of fairness due to too many layers of abstraction. Conversely, social approaches that engage with prescriptive theories may produce findings that are too abstract to effectively translate into practice. In her research, Angelina Wang bridges these approaches and utilizes social implications to guide technical work. Wang will discuss three research directions that show how, despite the technically convenient approach of considering equality acontextually, a stronger engagement with societal context allows us to operationalize a more equitable formulation. First, Wang will introduce a dataset tool that she developed to analyze complex, socially-grounded forms of visual bias. Then, Wang will provide empirical evidence to support how we should incorporate societal context in bringing intersectionality into machine learning. Finally, Wang will discuss how in the excitement of using LLMs for tasks like human participant replacement, we have neglected to consider the importance of human positionality. Overall, Wang will explore how we can expand a narrow focus on equality in responsible machine learning to encompass a broader understanding of equity that substantively engages with societal context.