Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depth
This addresses a fundamental gap in understanding neural network design for researchers, revealing how architectural scaling influences representation learning, though it is incremental as it builds on prior work on model capacity.
The paper investigates how varying the width and depth of neural networks affects their learned representations, discovering a characteristic block structure in larger capacity models that arises when capacity exceeds training set size, with representations outside this structure being similar across architectures but the block structure unique to each model, and finding that wide and deep models exhibit distinctive error patterns even with similar overall accuracy.
A key factor in the success of deep neural networks is the ability to scale models to improve performance by varying the architecture depth and width. This simple property of neural network design has resulted in highly effective architectures for a variety of tasks. Nevertheless, there is limited understanding of effects of depth and width on the learned representations. In this paper, we study this fundamental question. We begin by investigating how varying depth and width affects model hidden representations, finding a characteristic block structure in the hidden representations of larger capacity (wider or deeper) models. We demonstrate that this block structure arises when model capacity is large relative to the size of the training set, and is indicative of the underlying layers preserving and propagating the dominant principal component of their representations. This discovery has important ramifications for features learned by different models, namely, representations outside the block structure are often similar across architectures with varying widths and depths, but the block structure is unique to each model. We analyze the output predictions of different model architectures, finding that even when the overall accuracy is similar, wide and deep models exhibit distinctive error patterns and variations across classes.