Dense Backpropagation Improves Routing for Sparsely-Gated Mixture-of-Experts
Keywords: Mixtureofexperts, MoE, routing, transformer, LLM
Abstract: Mixture of Experts (MoE) pretraining is more scalable than dense Transformer pretraining, because MoEs learn to route inputs to a sparse set of their feedforward parameters. However, this means that MoEs only receive a sparse backward update, leading to problems such as router load imbalance where some experts receive more tokens than others. We present a lightweight approximation method that gives the MoE a dense gradient while only sparsely activating its parameters. A key insight into the design of our method is that at scale, many tokens not routed to a given expert may nonetheless lie in the span of tokens that were routed to that expert, allowing us to create an approximation for the expert output of that token from existing expert outputs. Our dense backpropagation outperforms standard TopK routing across multiple settings without significantly increasing runtime.
Primary Area: foundation or frontier models, including LLMs
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: 3936
Loading