2605.29350v1 May 28, 2026 cs.AI

ConMoE: Expert-Pool Consolidation via Prototype Reassignment for MoE Compression

Yilun Yao
Yilun Yao
Citations: 9
h-index: 1
Elsie Dai
Elsie Dai
Citations: 6
h-index: 1
Yaoming Li
Yaoming Li
Citations: 19
h-index: 3
Jiaming Pan
Jiaming Pan
Citations: 16
h-index: 2
Peizhuang Cong
Peizhuang Cong
Citations: 27
h-index: 3
Tong Yang
Tong Yang
Citations: 22
h-index: 3

Mixture-of-Experts (MoE) language models reduce per-token computation but still require storing and serving all experts, making deployment memory-intensive. Existing post-training compression methods mainly shrink this cost by pruning experts or merging their weights. We formulate post-training MoE compression as expert-pool consolidation: retaining a smaller set of pretrained experts as reusable prototypes and deterministically remapping each original expert reference to one selected prototype. This view separates the reduced expert pool from the reuse structure that represents the original expert slots, and allows prototype sharing within local layer scopes while preserving the original router interface. We propose ConMoE, a train-free prototype remapping framework that selects retained experts using calibration-based contribution and replaceability signals, then redirects original expert calls to the selected prototypes without weight updates or post-compression fine-tuning. Experiments on three pretrained MoE language models show that ConMoE matches or outperforms strong pruning and merging baselines in several settings, achieving the best average score on deepseek-moe-16b-base at both 25% and 50% routed-expert reduction, while remaining competitive on Qwen3-30B-A3B and OLMoE-1B-7B-0125. Ablations indicate that deterministic reassignment is the most stable component, whereas broader cross-layer sharing and post-hoc weight fusion are model-dependent.

0 Citations
0 Influential
1.5 Altmetric
7.5 Score
Original PDF

No Analysis Report Yet

This paper hasn't been analyzed by Gemini yet.

Log in to request an AI analysis.

댓글

댓글을 작성하려면 로그인하세요.

아직 댓글이 없습니다. 첫 번째 댓글을 남겨보세요!