AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

MoE^2: A Mixture-of-Mixtures of Experts for Ensemble-Free Domain Generalization

Ahmed Radwan, Mahmoud Soliman, Omar Abdelaziz, Ahmad Abdel-Qader, Mohamed S. Shehata

AAAI 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Optimization-based domain generalization · 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
synthesize instance-specific adapters from a bank of MoA experts (MoE2) instead of a single static adapterfrozen CLIP ViT-B/16 · DG benchmarks averageaverage accuracy (%): 74.1 -> 78.1 (ERM Attention to MoE2)Improved
replace full fine-tuning with MoE2 adapters on frozen backboneCLIP ViT-B/16 · DG benchmarks averageaverage accuracy (%): 67.1 -> 78.1Improved
use single MoE2 model instead of large model-pool ensembleSIMPLE+ · DG benchmarks averageaverage accuracy (%): 78.1 -> 78.1No clear effect
increase MoA experts per layer in a standard mixture of adapters (ablation)MoA · OfficeHomeaverage accuracy (%)No clear effect
set router temperature to 0.5 instead of 0.3 (ablation)MoE2 · OfficeHomeaverage accuracy (%): 90.58 -> 90.90Improved
vary expert initialization noise from 1e-5 to 1e-3 (ablation)MoE2 · OfficeHomeaverage accuracy (%): 90.90 / 90.95 / 90.80No clear effect
change diversity loss form (cosine, KL, Euclidean) (ablation)MoE2 · OfficeHomeaverage accuracy (%): 90.70 -> 90.95No clear effect
vary diversity loss weight from 0.1 to 0.6 (ablation)MoE2 · OfficeHomeaverage accuracy (%): 90.82 -> 90.95 (best at 0.2)No clear effect
MoE2 versus the best ensemble on TerraIncognita and DomainNetMoE2 · TerraIncognitaaccuracy (%): GMDG 60.7 vs MoE2 56.2Mixed

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