AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Flow-Disentangled Feature Importance

Xingshu Chen, Yifeng Guo, Jin-Hong Du

ICLR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Feature attribution methods

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
strong correlation (rho=0.8) between X1 and X2 in a linear modelLOCO and nLOCO · Simulation M1importance of X1Hurt
use DFI (disentangled attribution) instead of LOCO/nLOCO under strong correlationfeature importance · Simulation M1 (rho=0.8)importance assigned to X1: DFI >= 16 for X1Improved
use DFI instead of LOCO variants and Shapley in additive nonlinear modelfeature importance · Simulation M2total importance vs signal varianceImproved
use DFI instead of LOCO-based methods (except dLOCO) with interactionsfeature importance · Simulation M3importance ranking of correlated featuresImproved
random-forest regression estimate instead of oracle regression function (ablation)DFI · Simulation M3magnitude of DFI estimatesHurt
nonlinear but linearly uncorrelated X1, X2 (misspecified for DFI)DFI · Simulation M4attribution to X2Mixed
vary entropic regularization epsilon from 0 to 1 (ablation)DFI · Simulation M1 null-feature coveragecoverage: 0.942 (eps=0) vs 0.904-0.910 (eps>0) at rho=0, n=100No clear effect
avoid refitting submodels and conditional distribution estimation (DFI vs dLOCO and sampled Shapley)DFI · Simulation computation timecomputational timeImproved
group-level DFI attribution on HIV-1 neutralization dataDFI · HIV-1 neutralization resistancesignificant features: 19 of 832 -> 30 of 832 (disentangled vs original space)Improved

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