Technical Note: Game-Theoretic Interactions of Different Orders

Abstract

In this study, we define interaction components of different orders between two input variables based on game theory. We further prove that interaction components of different orders satisfy several desirable properties.

References in corpus (10)

• Axiomatic Attribution for Deep Networks
• Consistent Individualized Feature Attribution for Tree Ensembles
• Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs
• Hierarchical interpretations for neural network predictions
• Explaining Explanations: Axiomatic Feature Interactions for Deep Networks
• Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models
• Learning Global Pairwise Interactions with Bayesian Neural Networks
• Feature Interaction Interpretability: A Case for Explaining Ad-Recommendation Systems via Neural Interaction Detection
• The Shapley Taylor Interaction Index
• Interpreting and Boosting Dropout from a Game-Theoretic View

Cited by in corpus (3)

• Interpreting and Boosting Dropout from a Game-Theoretic View
• A Unified Game-Theoretic Interpretation of Adversarial Robustness
• Interpreting Attributions and Interactions of Adversarial Attacks