Towards the first principles of explaining DNNs: interactions explain the learning dynamics

• Interaction theory offers an axiomatic framework that translates DNN decision logic into symbolic interaction concepts, moving beyond empirical explanation methods. • It provides a unified mathematical account of diverse deep learning phenomena, including generalization, adversarial sensitivity, representation bottleneck, and learning dynamics. • The theory reveals that learning dynamics follow a two-phase evolution of interaction complexity, explaining why generalization and adversarial sensitivity change during training. • By unifying empirical attribution and adversarial-transferability-boosting methods, interaction theory advances toward a first-principles explanation for explainable AI.