AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

DeepCSHAP: Utilizing Shapley Values to Explain Deep Complex-Valued Neural Networks

Florian Eilers, Xiaoyi Jiang

TPAMI 2026 · Learning theory and algorithms › Prediction and decision losses · approach: Shapley value attribution

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 sum of real and imaginary parts instead of absolute value for complex gradient saliency (ablation)gradient-based explanation methods · MNISTchange in log-odds after masking 20% pixelsImproved
use CReLU-projection variant instead of zReLU variant in Guided Backpropagation (ablation)Guided Backpropagation · MNISTchange in log-odds after masking 20% pixelsImproved
use DeepCSHAP instead of complex gradient-based methodsexplanation of complex CNN · MNISTchange in log-odds after masking 20% pixelsImproved
use DeepCSHAP instead of complex gradient-based methodsexplanation of complex ResNet18 · S1SLC_CVDL two-patch channel attributionfraction of attribution in correct channelsImproved
use absolute value of gradient instead of R+I (ablation)gradient-based methods · S1SLC_CVDL two-patch channel attributionfraction of attribution in correct channels: median scores around 0.5 vs around 1 with R+IHurt
apply Guided Backpropagation variantsgradient-based methods · S1SLC_CVDL two-patch channel attributionfraction of attribution in correct channelsHurt
replace multiplier denominators below 1e-6 with Wirtinger derivative for numerical stabilityDeepCSHAP · MNIST / S1SLC_CVDLLocal Accuracy Error: 9.8 x 10^-6 on MNIST, 3.5 x 10^-3 on S1SLC_CVDLMixed
use integrated gradients with 5 integrands instead of plain gradientGrad · MNISTruntime (ms): 5.0 -> 22.6Hurt
use DeepCSHAP instead of gradient methodsexplanation cost · S1SLC_CVDLruntime (ms): 57.2 -> 380Hurt

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