ProbLog4Fairness: A Neurosymbolic Approach to Modeling and Mitigating Bias
This work addresses the problem of modeling and mitigating bias in AI systems for practitioners, offering a flexible and interpretable approach, though it is incremental in combining existing neurosymbolic methods with fairness applications.
The paper tackles the challenge of operationalizing fairness in machine learning by proposing ProbLog4Fairness, a neurosymbolic framework that formalizes bias assumptions as probabilistic logic programs to mitigate algorithmic bias, showing success on synthetic and real-world datasets.
Operationalizing definitions of fairness is difficult in practice, as multiple definitions can be incompatible while each being arguably desirable. Instead, it may be easier to directly describe algorithmic bias through ad-hoc assumptions specific to a particular real-world task, e.g., based on background information on systemic biases in its context. Such assumptions can, in turn, be used to mitigate this bias during training. Yet, a framework for incorporating such assumptions that is simultaneously principled, flexible, and interpretable is currently lacking. Our approach is to formalize bias assumptions as programs in ProbLog, a probabilistic logic programming language that allows for the description of probabilistic causal relationships through logic. Neurosymbolic extensions of ProbLog then allow for easy integration of these assumptions in a neural network's training process. We propose a set of templates to express different types of bias and show the versatility of our approach on synthetic tabular datasets with known biases. Using estimates of the bias distortions present, we also succeed in mitigating algorithmic bias in real-world tabular and image data. We conclude that ProbLog4Fairness outperforms baselines due to its ability to flexibly model the relevant bias assumptions, where other methods typically uphold a fixed bias type or notion of fairness.