Metraipolis › archive › dc_c4dc0f74b480
Beyond Retraining-Free MoE Compression: A Cost-Normalized Study of Post-Compression Adjustment — arXiv:2609.06076
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.06076
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T13:56:33.251Z
- SHA-256 of the archived text
9c0adf2a635e6fb64fc4c4e4214740276e3b3ecd2c2f08db1d3c933f21e8f9ff- Stable URL of this page
https://metraipolis.com/documento/dc_c4dc0f74b480
How to cite
Beyond Retraining-Free MoE Compression: A Cost-Normalized Study of Post-Compression Adjustment — arXiv:2609.06076 — arXiv (en), https://arxiv.org/abs/2609.06076 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c4dc0f74b480 (Metraipolis archive dc_c4dc0f74b480, sha256 9c0adf2a635e6fb64fc4c4e4214740276e3b3ecd2c2f08db1d3c933f21e8f9ff)
BibTeX
@misc{dcc4dc0f74b480,
title = {Beyond Retraining-Free MoE Compression: A Cost-Normalized Study of Post-Compression Adjustment — arXiv:2609.06076},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.06076},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c4dc0f74b480; sha256 9c0adf2a635e6fb64fc4c4e4214740276e3b3ecd2c2f08db1d3c933f21e8f9ff},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06076. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Retraining-free MoE compression reduces deployment memory by pruning or merging experts, but often treats the compressed checkpoint as the final artifact. We argue that this view is incomplete: compressed MoE checkpoints are better understood as compressed initializations that benefit from a tiny post-compression adjustment stage. Across two MoE LLM backbones, four pruning/merging methods, three expert-retention ratios, and 28 benchmarks, we compare LM fine-tuning and teacher-based KD under matched small-data budgets and measured GPU costs. Using only 3,000 C4 examples and a single epoch of adjustment, Full FT recovers 37.3% of the original-to-compressed performance gap on average. Moreover, LM fine-tuning is more cost-effective than standard token-level KD, and full-parameter adjustment gives the strongest cost--recovery trade-off among the tested scopes. These results suggest that retraining-free compression should be paired with small post-compression adjustment to recover a substantial portion of the performance lost during compression. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.06076 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T13:39:42.840Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).