ExplainabilityTransparencyTrustworthinesscs.AI
Advancing Explainable AI with Causal Analysis in Large-Scale Fuzzy Cognitive Maps
Marios Tyrovolas, Nikolaos D. Kallimanis, Chrysostomos Stylios
May 15, 2024
arXiv.org
4 citations
Key Takeaways
-
FCMs offer a practical bridge between human expertise and data: Fuzzy Cognitive Maps combine expert knowledge with machine learning insights, making AI systems more transparent than traditional "black box" models—a key requirement for responsible AI deployment in high-stakes domains.
-
New algorithm solves a real scalability problem: The TCEC-FCM algorithm enables causal effect analysis in large-scale systems for the first time by using efficient computational techniques (binary search and graph traversal), overcoming previous limitations that restricted FCMs to smaller applications.
-
Causal reasoning improves AI accountability: By calculating "total causal effects" between concepts, this approach helps stakeholders understand not just what an AI system predicts, but why—tracing how different factors influence decisions through explicit causal pathways rather than opaque correlations.
-
Interpretability enables broader responsible AI use: The paper demonstrates that FCMs can now scale to "modern complex XAI applications," meaning explainable AI methods can be applied to real-world problems where understanding AI reasoning is essential for trust and regulatory compliance.
Abstract
In the quest for accurate and interpretable AI models, eXplainable AI (XAI) has become crucial. Fuzzy Cognitive Maps (FCMs) stand out as an advanced XAI method because of their ability to synergistically combine and exploit both expert knowledge and data-driven insights, providing transparency and intrinsic interpretability. This letter introduces and investigates the "Total Causal Effect Calculation for FCMs" (TCEC-FCM) algorithm, an innovative approach that, for the first time, enables the efficient calculation of total causal effects among concepts in large-scale FCMs by leveraging binary search and graph traversal techniques, thereby overcoming the challenge of exhaustive causal path exploration that hinder existing methods. We evaluate the proposed method across various synthetic FCMs that demonstrate TCEC-FCM's superior performance over exhaustive methods, marking a significant advancement in causal effect analysis within FCMs, thus broadening their usability for modern complex XAI applications.