AI Paper Atlas

Research map / Architectures and efficiency / Mixture of experts

C-GNN-PRUNE: A Unified Graph-Based Framework for Structure-Aware Pruning of Mixture-of-Experts Models

Lin Li, Yan Wang, Zhuopeng Wang

AAAI 2026 · Architectures and efficiency › Mixture of experts · approach: Expert routing and specialization · 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
add GNN structure-aware embedding module (ablation)C-GNN-PRUNE · MMLU Computer Science (Qwen1.5-MoE-A2.7B, 20% pruning)accuracy: 44.99 -> 50.50Improved
add GNN structure-aware embedding module (ablation)C-GNN-PRUNE · MMLU Business (Qwen1.5-MoE-A2.7B, 20% pruning)accuracy: 42.18 -> 45.69Improved
add GNN structure-aware embedding module (ablation)C-GNN-PRUNE · MMLU average (Qwen1.5-MoE-A2.7B)accuracy: 40.59 -> 43.96Improved
add entropy-guided layer-wise pruning allocation instead of uniform ratio (ablation)C-GNN-PRUNE · MMLU Computer Science (Qwen1.5-MoE-A2.7B, 20% pruning)accuracy: 45.49 -> 50.50Improved
add entropy-guided layer-wise pruning allocation (ablation)C-GNN-PRUNE · MMLU Math (Qwen1.5-MoE-A2.7B, 20% pruning)accuracy: 34.68 -> 35.68No clear effect
mix output similarity and routing divergence in graph (omega 0.3) instead of output-only (omega 0.0) (ablation)C-GNN-PRUNE · ARC-e (Mixtral 8x7B, 20% pruning)accuracy: 78.87 -> 80.47Improved
mix output similarity and routing divergence (omega 0.3) instead of routing-only (omega 1.0) (ablation)C-GNN-PRUNE · BoolQ (Mixtral 8x7B, 20% pruning)accuracy: 76.26 -> 84.49Improved
use Girvan-Newman community detection instead of KMeans (ablation)C-GNN-PRUNE · BoolQ (Mixtral 8x7B)accuracy: 80.52 -> 84.49Improved
use Girvan-Newman instead of Agglomerative clustering (ablation)C-GNN-PRUNE · BoolQ and WinoGrande (Mixtral 8x7B)accuracy: BoolQ 85.50 vs 84.49; ARC-e 78.87 vs 80.47Mixed
C-GNN-PRUNE vs C-PRUNE at 20% pruningC-GNN-PRUNE · DeepSeek-V2-Lite MMLU Computer Scienceaccuracy: 51.50 -> 50.10Hurt
C-GNN-PRUNE vs C-PRUNE at 20% pruningC-GNN-PRUNE · Qwen1.5-MoE-A2.7B averagescore: 37.65 -> 43.38Improved
C-GNN-PRUNE vs EEMoE at 50% pruningC-GNN-PRUNE · Mixtral 8x7B average over seven benchmarksaccuracy: 61.10 -> 62.49Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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