AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Magnitude-Modulated Equivariant Adapter for Parameter-Efficient Fine-Tuning of Equivariant Graph Neural Networks

Dian Jin, Yancheng Yuan, Xiaoming Tao

AAAI 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Adapter-based parameter-efficient tuning · 1 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
use MMEA scalar gating instead of ELoRAMACE-OFF · rMD17 Aspirin (50 train samples)force MAE: 18.3 -> 16.4Improved
add scalar-channel modulation (ablation)MMEA · rMD17 Aspirin (50 train samples)force MAE: 30.5 -> 16.4Improved
add high-order modulation (ablation)MMEA · rMD17 Aspirin (50 train samples)energy MAE: 8.3 -> 7.3Improved
add high-order modulation (ablation)MMEA · rMD17 Aspirin (50 train samples)force MAE: 16.6 -> 16.4No clear effect
add nonlinear activation (ablation)MMEA · rMD17 Aspirin (50 train samples)force MAE: 16.4 -> 16.4No clear effect
share input-head MLP (reuse) between orders (ablation)MMEA · rMD17 Aspirin (50 train samples)energy MAE: 9.2 -> 7.3Improved
use per-channel (not shared) high-order modulation (ablation)MMEA · rMD17 Aspirin (50 train samples)force MAE: 16.6 -> 16.4No clear effect
use equivariant MMEA instead of conventional Adapter (ablation)MACE-OFF · rMD17 Aspirin (50 train samples)force MAE: 26.3 -> 16.4Improved
use MMEA instead of ELoRA on extreme out-of-distribution targetMACE-MP · rMD17 Aspirin (out-of-distribution, MACE-MP)force MAE: 31.1 -> 31.9Hurt
increase MMEA rank from 16 to 32MMEA · AcAc 600 K testenergy RMSE: 3.6 -> 3.2Improved
use MMEA instead of ELoRA at 1200 KMACE-OFF · 3BPA 1200 K testforce RMSE: 42.0 -> 39.7Improved

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