Distributing Synergy Functions: Unifying Game-Theoretic Interaction Methods for Machine-Learning Explainability
This work addresses the need for transparency and trust in AI decision-making by providing a foundational framework for explainability methods, though it appears incremental as it builds on existing game-theoretic concepts.
The paper tackles the problem of unifying game-theory-inspired methods for explaining black-box machine learning models by quantifying attributions and interactions between inputs, showing that a unique full account of interactions (synergies) is possible under modest assumptions and introducing new gradient-based methods.
Deep learning has revolutionized many areas of machine learning, from computer vision to natural language processing, but these high-performance models are generally "black box." Explaining such models would improve transparency and trust in AI-powered decision making and is necessary for understanding other practical needs such as robustness and fairness. A popular means of enhancing model transparency is to quantify how individual inputs contribute to model outputs (called attributions) and the magnitude of interactions between groups of inputs. A growing number of these methods import concepts and results from game theory to produce attributions and interactions. This work presents a unifying framework for game-theory-inspired attribution and $k^\text{th}$-order interaction methods. We show that, given modest assumptions, a unique full account of interactions between features, called synergies, is possible in the continuous input setting. We identify how various methods are characterized by their policy of distributing synergies. We also demonstrate that gradient-based methods are characterized by their actions on monomials, a type of synergy function, and introduce unique gradient-based methods. We show that the combination of various criteria uniquely defines the attribution/interaction methods. Thus, the community needs to identify goals and contexts when developing and employing attribution and interaction methods.