Attention Is All You Need For Mixture-of-Depths Routing
Keywords: Mixture of Depths, attention, parameter free routing.
TL;DR: We propose an integrated routing mechanism for Mixture of Depths using attention.
Abstract: Advancements in deep learning are driven by training models with increasingly larger numbers of parameters, which in turn heightens the computational demands. To address this issue, Mixture-of-Depths (MoD) models have been proposed to dynamically assign computations only to the most relevant parts of the inputs, thereby enabling the deployment of large-parameter models with high efficiency during inference and training. These MoD models utilize a routing mechanism to determine which tokens should be processed by a layer, or skipped. However, conventional MoD models employ additional network layers specifically for the routing which are difficult to train, and add complexity and deployment overhead to the model. In this paper, we introduce a novel attention-based routing mechanism *A-MoD* that leverages the existing attention map of the preceding layer for routing decisions within the current layer. Compared to standard routing, *A-MoD* allows for more efficient training as it introduces no additional trainable parameters and can be easily adapted from pretrained transformer models. Furthermore, it can increase the performance of the MoD model. For instance, we observe up to $2$\% higher accuracy on ImageNet compared to standard routing and isoFLOP ViT baselines. Furthermore, *A-MoD* improves the MoD training convergence, leading to up to $2\times$ faster transfer learning.
Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 6431
Loading