AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Manifold-Aligned Guided Integrated Gradients for Reliable Feature Attribution

Soyeon Kim, Seongwoo Lim, Kyowoon Lee, Jaesik Choi

ICML 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Sparse graphical and tensor models · 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
Construct guided attribution path in VAE latent space (MA-GIG) instead of input space (GIG)Guided IG · Oxford-IIIT PetDiffID: 0.3634 -> 0.4637Improved
Latent-space guided path instead of GIGGuided IG · ImageNet2012 (500 images)DiffID: 0.2842 -> 0.3262 (VGG16)Improved
MA-GIG vs IG2 on Pet with VGG16MA-GIG · Oxford-IIIT Pet (VGG16)DiffID: 0.6075 (IG2) vs 0.5913 (MA-GIG)Hurt
MA-GIG vs GIG on deletion AUCMA-GIG · Oxford-IIIT Pet (VGG16) / ImageNet (5000 images)Deletion AUC: 0.0333 (GIG) vs 0.0817 (MA-GIG) on Pet VGG16Hurt
Vary selection fraction q among 0.05, 0.1, 0.2 (ablation)MA-GIG · Pet, Flower, ImageNetDiffID: 0.4474 / 0.4360 / 0.4345 (Pet ResNet18)No clear effect
Use Spherical Linear Interpolation (Slerp) instead of linear interpolation (ablation)MA-GIG · Oxford-IIIT Pet (ResNet18)DiffID: 0.4637 -> 0.4565Mixed
Use a domain-matched VAE (MAR, ImageNet-trained) instead of larger SD2 VAE (ablation)MA-GIG · ImageNet (ResNet18)DiffID: 0.2627 (MAR) vs 0.2638 (SD2)No clear effect
Use a VAE with lower reconstruction MSE (KD) (ablation)MA-GIG · ImageNet (ResNet18)DiffID: MSE 0.00247, DiffID 0.2333Hurt
Latent-space path vs input-space GIG on completeness residualMA-GIG · ResNet18, K=200completeness residual reduction: 9.8% ImageNet; 33.0% Pet; 30.9% FlowerImproved
MA-GIG vs GIG on MPRT sanity checkMA-GIG · ImageNet ResNet18MPRT: 0.308 -> 0.625Improved

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