Turn Waste into Worth: Rectifying Top-k Router of MoE
Paper
•
2402.12399
•
Published
•
2
Papers - MoE - Router
-
-
CompeteSMoE -- Effective Training of Sparse Mixture of Experts via Competition
Paper • 2402.02526 • Published • 3 -
Buffer Overflow in Mixture of Experts
Paper • 2402.05526 • Published • 8 -
OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models
Paper • 2402.01739 • Published • 26 -
LocMoE: A Low-overhead MoE for Large Language Model Training
Paper • 2401.13920 • Published • 2 -
HyperRouter: Towards Efficient Training and Inference of Sparse Mixture of Experts
Paper • 2312.07035 • Published • 2 -
Routers in Vision Mixture of Experts: An Empirical Study
Paper • 2401.15969 • Published • 2 -
BASE Layers: Simplifying Training of Large, Sparse Models
Paper • 2103.16716 • Published • 3 -
Hash Layers For Large Sparse Models
Paper • 2106.04426 • Published • 2 -
Direct Neural Machine Translation with Task-level Mixture of Experts models
Paper • 2310.12236 • Published • 2 -
Adaptive Gating in Mixture-of-Experts based Language Models
Paper • 2310.07188 • Published • 2 -
Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy
Paper • 2310.01334 • Published • 2 -
Sparse Backpropagation for MoE Training
Paper • 2310.00811 • Published • 2 -
A Review of Sparse Expert Models in Deep Learning
Paper • 2209.01667 • Published • 3 -
SpeechMoE2: Mixture-of-Experts Model with Improved Routing
Paper • 2111.11831 • Published • 2 -
Towards More Effective and Economic Sparsely-Activated Model
Paper • 2110.07431 • Published • 2 -
Taming Sparsely Activated Transformer with Stochastic Experts
Paper • 2110.04260 • Published • 2 -
Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference
Paper • 2110.03742 • Published • 3 -
Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts
Paper • 2306.04845 • Published • 3 -
Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks
Paper • 2306.04073 • Published • 2 -
Unified Scaling Laws for Routed Language Models
Paper • 2202.01169 • Published • 2