REVIEW 7 cited by
A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts
read the original abstract
The sparsely gated mixture of experts (MoE) architecture sends different inputs to different subnetworks, i.e., experts, through trainable routers. MoE reduces the training computation significantly for large models, but its deployment can be still memory or computation expensive for some downstream tasks. Model pruning is a popular approach to reduce inference computation, but its application in MoE architecture is largely unexplored. To the best of our knowledge, this paper provides the first provably efficient technique for pruning experts in finetuned MoE models. We theoretically prove that prioritizing the pruning of the experts with a smaller change of the routers l2 norm from the pretrained model guarantees the preservation of test accuracy, while significantly reducing the model size and the computational requirements. Although our theoretical analysis is centered on binary classification tasks on simplified MoE architecture, our expert pruning method is verified on large vision MoE models such as VMoE and E3MoE finetuned on benchmark datasets such as CIFAR10, CIFAR100, and ImageNet.
Forward citations
Cited by 7 Pith papers
-
Communication-Aware Placement and Pruning for Efficient Mixture-of-Experts Inference
Communication-aware expert placement plus device-level pruning yields 1.23–1.86× MoE inference throughput and better accuracy at equal speedup than load-balance or sequential baselines.
-
Attribution-Guided and Coverage-Maximized Pruning for Structural MoE Compression
A structural pruning framework for MoE models that solves channel-score coverage maximization via attribution approximation, preserving accuracy at 50% or 25% pruning plus 4-bit quantization on DeepSeek and Qwen models.
-
dMoE: dLLMs with Learnable Block Experts
dMoE aggregates token expert distributions to block level in dLLMs, cutting unique experts from 69.5 to 14.6, memory by 76-80%, and latency by 1.14-1.66x while retaining 99.11% performance.
-
FluxMoE: Decoupling Expert Residency for High-Performance MoE Serving
FluxMoE decouples MoE expert weights from persistent GPU residency via on-demand paging, achieving up to 3x throughput gains over vLLM in memory-constrained inference without accuracy loss.
-
How Can Mamba Learn In Context with Outliers and Generalize Provably?
A simplified one-layer Mamba provably learns in-context binary classification tolerating outlier fractions approaching 1, whereas a linear Transformer can only tolerate α < 1/2.
-
Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs
DERN prunes SMoE LLMs by decomposing removed experts into neuron segments, reassigning the best-matching ones to kept experts, and clustering them into compact replacements, beating prior pruning baselines without retraining.
-
Does a Global Perspective Help Prune Sparse MoEs Elegantly?
GRAPE is a global redundancy-aware pruning strategy for sparse MoEs that dynamically allocates pruning budgets across layers and improves average accuracy by 1.40% over the best local baseline across tested models and...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.