AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Rethinking Parameter Sharing as Graph Coloring for Structured Compression

Boyang Zhang, Daning Cheng, Yunquan Zhang, Fangming Liu

ICML 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Joint pruning and quantization · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace Basis Sharing heuristic with Geo-Sharing coloringLLaMA-7B 20% · WikiText-2perplexity: 7.74 -> 7.07Improved
replace Basis Sharing with Geo-SharingLLaMA-7B 50% · WikiText-2perplexity: 19.99 -> 18.95Improved
replace Basis Sharing with Geo-SharingLLaMA-7B 50% · PTBperplexity: 126.35 -> 117.23Improved
replace Basis Sharing with Geo-SharingLLaMA-7B 20% · 7 zero-shot tasksaverage accuracy: 48.0 -> 49.1Improved
replace Basis Sharing with Geo-SharingLLaMA2-7B 50% · WikiText-2perplexity: 21.3 -> 20.16Improved
replace Basis Sharing with Geo-SharingLLaMA-7B 80% · C4perplexity: 2465.999 -> 995.33Improved
replace Basis Sharing with Geo-SharingOPT-6.7B 20% · WikiText-2perplexity: 11.79 -> 11.68Improved
replace FiPS with Geo-SharingSwin-L · ImageNetTop-1 drop: 0.03 -> 0.01Improved
share parameters with Geo-SharingDeiT-B · CIFAR-100 transferaccuracy: 72.80 -> 70.30Hurt
share parameters with Geo-SharingSwin-B · CIFAR-100 transferaccuracy: 67.39 -> 68.05No clear effect
increase number of short-axis eigenvalues t (ablation)Geo-Sharing · LLaMA perplexityperplexityImproved
increase amplitude factor beta beyond 1e-1 (ablation)Geo-Sharing · LLaMA perplexityperplexityHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy