AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Partial Fusion of Neural Networks: Efficient Tradeoffs Between Ensembles and Weight Aggregation

Fabian Morelli, Stephan Eckstein

ICML 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Sparse training from scratch · 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
raise alpha from 0 to 1 (fewer to no isolated neurons to full ensemble) before fine-tuning (ablation)Partial OT Fusion MLP · Split MNIST MLP, fused (no fine-tuning)accuracy (%): 84.1 -> 88.1Improved
raise alpha from 0 to 1 before fine-tuning (ablation)Partial OT Fusion ResNet-18 · Split CIFAR-10 ResNet-18, fused (no fine-tuning)accuracy (%): 66.4 -> 91.3Improved
fine-tune the fused model on 1% data (alpha=0)Partial OT Fusion MLP · Split MNIST, fine-tuned with 1% dataaccuracy (%): 84.1 -> 95.1Improved
fine-tune the fused model on 5% data (alpha=0)Partial OT Fusion ResNet-18 · Split CIFAR-10, fine-tuned with 5% dataaccuracy (%): 66.4 -> 85.3Improved
raise alpha from 0 to 1 after fine-tuning (ablation)Partial OT Fusion ResNet-18 · Split CIFAR-10, fine-tuned with 5% dataaccuracy (%): 85.3 -> 91.8Improved
raise alpha from 0 to 1 after fine-tuning (ablation)Partial OT Fusion MLP · Split MNIST, fine-tuned with 1% dataaccuracy (%): 95.1 -> 96.5Improved
use partial fusion (alpha=1.0) instead of random widening of Model A (ablation)fine-tuned wider network · Split CIFAR-10, fine-tuned with 5% dataaccuracy (%): 49.0 -> 91.7Improved
use partial fusion instead of Net2WiderNet widening, alpha=1.0 (ablation)fine-tuned wider network · Split CIFAR-10, fine-tuned with 5% dataaccuracy (%): 86.6 -> 91.7Improved
use partial fusion instead of Net2WiderNet widening, alpha=1.0 (ablation)fine-tuned wider network · Split MNIST, fine-tuned with 1% dataaccuracy (%): 95.0 -> 96.5Improved
increase alpha from 0 to 0.4 at width 25 (ablation)Partial OT Fusion MLP · MNIST MLP same data, hidden width 25accuracy (%): 64.7 -> 85.0Improved
increase alpha from 0 to 1 at width 400 (ablation)Partial OT Fusion MLP · MNIST MLP same data, hidden width 400accuracy (%): 97.2 -> 97.9No clear effect
use fixed-point iteration instead of greedy weight-based or activation-based matching (ablation)Partial OT Fusion · Split MNIST MLPaccuracyImproved

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