# Dense Backpropagation Improves Training for Sparse Mixture-of-Experts

arXiv: https://arxiv.org/abs/2504.12463 · HTML: https://mlsanity.com/paper/2504.12463/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Expert routing strategies, one of 12 directions in Mixture-of-experts.
- Builds on 22 of its 40 references that are in the map.
- First posted on arXiv 16 Apr 2025.

## Placed in

- Mixture-of-experts / [Expert routing strategies](https://mlsanity.com/moe/expert-routing-strategies/)

## Builds on (most cited first, 22 of 22)

- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [The LAMBADA dataset: Word prediction requiring a broad discourse context](https://mlsanity.com/paper/1606.06031/) (2016)
- [GLaM: Efficient Scaling of Language Models with Mixture-of-Experts](https://mlsanity.com/paper/2112.06905/) (2021)
- [Mixture-of-Experts with Expert Choice Routing](https://mlsanity.com/paper/2202.09368/) (2022)
- [MegaBlocks: Efficient Sparse Training with Mixture-of-Experts](https://mlsanity.com/paper/2211.15841/) (2022)
- [Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Experts](https://mlsanity.com/paper/2408.15664/) (2024)
- [DeepNet: Scaling Transformers to 1,000 Layers](https://mlsanity.com/paper/2203.00555/) (2022)
- [Transformers without Tears: Improving the Normalization of Self-Attention](https://mlsanity.com/paper/1910.05895/) (2019)
- [Liger Kernel: Efficient Triton Kernels for LLM Training](https://mlsanity.com/paper/2410.10989/) (2024)
- [Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent](https://mlsanity.com/paper/2411.02265/) (2024)
- [ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing](https://mlsanity.com/paper/2412.14711/) (2024)
- [Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models](https://mlsanity.com/paper/2501.11873/) (2025)
- [Sparse Backpropagation for MoE Training](https://mlsanity.com/paper/2310.00811/) (2023)

## Built on by (most cited first, 10 of 10)

- [Routing Manifold Alignment Improves Generalization of Mixture-of-Experts LLMs](https://mlsanity.com/paper/2511.07419/) (2025)
- [Transformer as an Euler Discretization of Score-based Variational Flow](https://mlsanity.com/paper/2604.23740/) (2026)
- [Uncovering Intra-expert Activation Sparsity for Efficient Mixture-of-Expert Model Execution](https://mlsanity.com/paper/2605.08575/) (2026)
- [UB-SMoE: Universally Balanced Sparse Mixture-of-Experts for Resource-adaptive Federated Fine-tuning of Foundation Models](https://mlsanity.com/paper/2605.16690/) (2026)
- [TEXAS: Task-Expert-Aware Supervision for Downstream Mixture-of-Experts LLM Adaptation](https://mlsanity.com/paper/2608.06396/) (2026)
- [Beyond Routing: Decoupling Expert Dispatch and Aggregation in Sparse Mixture-of-Experts](https://mlsanity.com/paper/2608.08853/) (2026)
- [RECLAIM: Can Agents Reproduce the Claims of Machine Learning Papers?](https://mlsanity.com/paper/2609.28850/) (2026)
- [Score the Update, Not the Token: Descent-Aligned Routing for Combinatorial LoRA Experts](https://mlsanity.com/paper/2610.00493/) (2026)
- [Dense Mixture-of-Experts as a Reparameterized Wide FFN: A Granularity Sweep at Fixed Compute](https://mlsanity.com/paper/2610.02584/) (2026)
- [Principled Top-k Selection for Language Models with Hybrid Gradients](https://mlsanity.com/paper/2610.04162/) (2026)

## Abstract (arXiv)

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 training instability and suboptimal performance. We present a lightweight approximation method that gives the MoE router a dense gradient update while continuing to sparsely activate its parameters. Our method, which we refer to as Default MoE, substitutes missing expert activations with default outputs consisting of an exponential moving average of expert outputs previously seen over the course of training. This allows the router to receive signals from every expert for each token, leading to significant improvements in training performance. Our Default MoE outperforms standard TopK routing in a variety of settings without requiring significant computational overhead. Code: https://github.com/vatsal0/default-moe.