A Neurosymbolic Approach to Counterfactual Fairness | Xenia Heilmann

💬 Discord: https://discord.gg/h8NVzwnysW 💻 GitHub: https://github.com/centaurinstitute 🤝 LinkedIn: https://www.linkedin.com/company/centaur-ai-institute/ 📢 New Initiative: Neuro-Symbolic Agentic Protocol ⭐ Star us on GitHub https://github.com/centaurinstitute/neuro-symbolic-agentic-protocol — ​​​​​Abstract: Integrating fairness into machine learning models has been an important consideration for the last decade. Here, neurosymbolic models offer a valuable opportunity, as they allow the specification of symbolic, logical constraints that are often guaranteed to be satisfied. However, research on neurosymbolic applications to algorithmic fairness is still in an early stage. In this talk, we will see how to integrate counterfactual fairness into the neurosymbolic framework of Logic Tensor Networks (LTN). We use LTN to express accuracy and counterfactual fairness constraints in first-order logic and employ them to achieve desirable levels of both performance and fairness at training time. We will show, through examples on benchmark datasets, that logical reasoning about counterfactual fairness has some important advantages, among which its intrinsic interpretability, and its flexibility in handling subgroup fairness. ​Paper: https://journals.sagepub.com/doi/full/10.1177/29498732261443184 ​Bio: Xenia Heilmann is a PhD student in the Algorithms group at Johannes Gutenberg University Mainz, Germany, where her research lies at the intersection of privacy and algorithmic fairness in machine‑learning systems, with a special focus on federated and neurosymbolic approaches. During a 2024 research visit to the Belle Lab (University of Edinburgh) she collaborated with Dr. Vaishak Belle on fairness in neurosymbolic settings. — 🗨️ ​Join us for an interactive session exploring Neuro-Symbolic AI, the emerging paradigm that blends the strengths of neural networks with symbolic reasoning. We will discuss how hybrid approaches can enhance generalization, interpretability, and reasoning, and how these methods are shaping the future of intelligent systems. Whether you’re a researcher, engineer, or simply curious about the cutting edge of AI, you’ll find an engaging space to learn, connect, and exchange ideas. Event Format: 🔍 Reading Group 🎙️ Panel Discussion 🧩 Tutorials/Workshop Series 💬 Research Roundtable 🛠️ Open-Source Project Review 📄 Paper Pitch 🤝 Collaboration Hour 🍵 Networking Mixer #AI #NeuroSymbolic #FutureOfAI