Systemizing Multiplicity: The Curious Case of Arbitrariness in Machine Learning
This work addresses the issue of arbitrariness in ML decisions for researchers and practitioners, but it is incremental as it primarily organizes existing knowledge without introducing new methods or data.
The paper tackles the problem of arbitrariness in machine learning by systemizing the literature on multiplicity, which studies arbitrariness across good models, and formalizes terminology, expands definitions, clarifies distinctions, and distills trends to situate it within responsible AI.
Algorithmic modeling relies on limited information in data to extrapolate outcomes for unseen scenarios, often embedding an element of arbitrariness in its decisions. A perspective on this arbitrariness that has recently gained interest is multiplicity-the study of arbitrariness across a set of "good models", i.e., those likely to be deployed in practice. In this work, we systemize the literature on multiplicity by: (a) formalizing the terminology around model design choices and their contribution to arbitrariness, (b) expanding the definition of multiplicity to incorporate underrepresented forms beyond just predictions and explanations, (c) clarifying the distinction between multiplicity and other lenses of arbitrariness, i.e., uncertainty and variance, and (d) distilling the benefits and potential risks of multiplicity into overarching trends, situating it within the broader landscape of responsible AI. We conclude by identifying open research questions and highlighting emerging trends in this young but rapidly growing area of research.