ProbLog4Fairness: A Neurosymbolic Approach to Modeling and Mitigating Bias

TL;DR

ProbLog4Fairness introduces a neurosymbolic framework that formalizes bias assumptions as probabilistic logic programs, enabling flexible, interpretable mitigation of algorithmic bias in diverse datasets.

Contribution

It develops a novel ProbLog-based approach to model and mitigate bias, combining probabilistic logic programming with neural training for the first time.

Findings

Outperforms baseline methods in bias mitigation tasks.

Effectively models various bias types through probabilistic logic templates.

Successfully reduces bias in both synthetic and real-world datasets.

Abstract

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.