AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

Theoretical Analysis of the Optimal Free Responses of Graph-Based SFA for the Design of Training Graphs

Alberto N. Escalante-B., Laurenz Wiskott

JMLR 2016 · Graph learning › Graph algorithms and clustering · approach: Graph embedding and spectral sparsification · 6 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
add 9 auxiliary cosine labels to the gender label (10 target labels) (ablation)ELL^g graph, HGSFA · Gender estimation, artificial faces (soft GC, 1F)RMSE: 0.364 -> 0.353Improved
add 39 auxiliary labels (40 target labels) (ablation)ELL^g graph, HGSFA · Gender estimation, artificial faces (soft GC, 1F)RMSE: 0.364 -> 0.346Improved
raise target labels from 40 to 50 (ablation)ELL^g graph, HGSFA · Gender estimation, artificial faces (soft GC, 1F)RMSE: 0.346 -> 0.351Hurt
replace linear scaling mapping by soft Gaussian classifier mapping (ablation)ELL^g-40 · Gender estimation, artificial facesRMSE: 0.368 -> 0.346Improved
use ELL^g-40 instead of serial graphGSFA training graph · Gender estimation, artificial faces (soft GC, 1F)RMSE: 0.351 -> 0.346Improved
code gender and color jointly (2x5 labels) instead of gender only (ablation)ELL graph · Gender estimation, artificial faces (soft GC, 3F)RMSE: 0.345 -> 0.277Improved
increase auxiliary labels in joint gender-color graph with 1 feature (ablation)ELL^{g,c} · Gender estimation, artificial faces (soft GC, 1F)RMSE: 0.289 -> 0.499Hurt
code gender and color jointly instead of color only (3 features) (ablation)ELL graph · Color estimation, artificial faces (soft GC, 3F)RMSE: 1.867 -> 1.140Improved
add 30 auxiliary labels (compact+31 vs compact+5) at d=5 (ablation)compact graph · GTSRB 32 classes, d=5error rate (%): 11.67% -> 12.42%Hurt
use compact+5 graph instead of clustered graph at d=5GSFA · GTSRB 32 classes, d=5error rate (%): 29.74% -> 11.67%Improved
use compact+31 graph instead of clustered graph at d=31GSFA · GTSRB 32 classes, d=31error rate (%): 2.89% -> 2.89%No clear effect
preserve more than 5 features with compact+5 graph (ablation)compact+5 · GTSRB 32 classeserror rate (%)Hurt

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