NeuCEPT: Locally Discover Neural Networks' Mechanism via Critical Neurons Identification with Precision Guarantee
This work addresses the interpretability of deep neural networks for researchers and practitioners, but it is incremental as it builds on existing studies of model understanding.
The authors tackled the problem of understanding how deep neural networks generate predictions by proposing NeuCEPT, a method to locally discover critical neurons and identify model mechanisms, showing that identified neurons strongly influence predictions and hold meaningful information about mechanisms.
Despite recent studies on understanding deep neural networks (DNNs), there exists numerous questions on how DNNs generate their predictions. Especially, given similar predictions on different input samples, are the underlying mechanisms generating those predictions the same? In this work, we propose NeuCEPT, a method to locally discover critical neurons that play a major role in the model's predictions and identify model's mechanisms in generating those predictions. We first formulate a critical neurons identification problem as maximizing a sequence of mutual-information objectives and provide a theoretical framework to efficiently solve for critical neurons while keeping the precision under control. NeuCEPT next heuristically learns different model's mechanisms in an unsupervised manner. Our experimental results show that neurons identified by NeuCEPT not only have strong influence on the model's predictions but also hold meaningful information about model's mechanisms.