Functional Similarity Metric for Neural Networks: Overcoming Parametric Ambiguity via Activation Region Analysis

ArXi:2604.16426v1 Announce Type: new As modern deep learning architectures grow in complexity, representational ambiguity emerges as a critical barrier to their interpretability and reliable merging. For ReLU networks, identical functional mappings can be achieved through entirely different weight configurations due to algebraic symmetries: neuron permutation and positive diagonal scaling. Consequently, traditional parameter-based comparison methods exhibit extreme instability to slight weight perturbations during.