Fair & Bias-Aware AI: MAMMOth Concludes

31 October 2025

MAMMOth Project Concludes with UniBw Advancing Multidimensional Bias Mitigation in AI

31 October 2025

The Horizon Europe-funded project MAMMOth (Multi-Attribute, Multimodal Bias Mitigation in AI Systems) concluded on 31 October 2025 after three years of advancing fair, inclusive, and accountable AI. The project brought together academic, industrial, and societal partners to address bias in AI systems and deliver practical tools for fairness-aware AI.

A key contribution of MAMMOth is moving beyond single-attribute fairness towards multidimensional bias mitigation, enabling more realistic and effective analysis of bias in complex AI systems.

Contributions from team UniBw

As a leading contributor to the project’s work on multidimensional bias mitigation (WP3), team UniBw played a central role in shaping its scientific and technical outcomes through the development of methods and tools for defining, analysing, mitigating, and explaining bias across multiple dimensions. These include:

Foundations and Definitions

• A generic formulation of multidimensional discrimination 
• Contributions to the AI Fairness Definition Guide

Bias Mitigation Methods & Optimization

• Multi-objective optimisation approaches for multi-attribute fairness
• Methods for bias mitigation across multiple tasks and bias analysis in multimodal fusion
• Definining and achieving socio-economic fairness aligned with principles of the EU AI Act
• Techniques for assessing  disparity in adversarial robustness and  adversarial attacks on autoencoders
• Methods for analysing the fairness–utility tradeoff in graph clustering

Fairness-aware Synthetic Tabular Data Generation

• Synthetic data generators for class imbalance and fairness
• the TABFAIRGDT tabular data generator
• methods for fairness-aware and privacy-preserving synthetic data

Broader Achievements of the MAMMOth Project

Tools & Software

• MMM-Fair, an open-source library for multidimensional fairness analysis with interactive visualisation, tradeoff exploration, a no-code chat-based along with CLI interface, and LLM-powered explanations

According to the official project press release, MAMMOth delivered wide-reaching results beyond scientific development, including:

• The MAI-BIAS Toolkit, enabling detection, analysis, and mitigation of bias in datasets and AI models
• Fairness-aware libraries and methods applied to finance, identity verification, multimodal fusion, and academic impact analysis
• Extensive training and public engagement, with more than 30 workshops, five webinars, podcasts, and public exhibitions
• Policy briefs aligned with the EU AI Act, offering practical guidance for fairness-oriented AI governance
• Outreach to more than 12,000 organisations, supported by broad dissemination activities

Impact and Legacy

MAMMOth has significantly advanced the foundations of intersectional, multimodal, and multidimensional fairness in AI. By pairing methodological innovation with practical tools, the project has set new standards for evaluating and mitigating bias in real-world AI systems.

The project’s open-source software, datasets, methodological frameworks, and policy recommendations remain accessible via the AI-on-Demand platform, GitHub, and mammoth-ai.eu, ensuring sustained impact beyond the project’s completion.