AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Learning the Right Layers a Data-Driven Layer-Aggregation Strategy for Semi-Supervised Learning on Multilayer Graphs

Sara Venturini, Andrea Cristofari, Francesco Rinaldi, Francesco Tudisco

ICML 2023 · Label-efficient and robust learning › Semi-supervised learning · approach: Holistic semi-supervised pipelines

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
learned generalized mean aggregation with bilevel Frank-Wolfe (BINOM vs MULTI)multilayer SSL on synthetic and real datasets · synthetic and real multilayer graphsAPRImproved
learned aggregation (BINOM) versus fixed aggregationsreal datasets, 1% labels · real-world multilayer datasets with one noisy layerAPR: 0.97 vs 0.94 for best fixed mean (ARIT)Improved
fixed min aggregationmultilayer SSL · synthetic all settingsaccuracyHurt
adding a noisy layer to real datasets with fixed max aggregationMAX aggregation · UCI 1% labelsaccuracy: 0.85 without noise vs 0.5 with one noise layerHurt
fixed arithmetic/harmonic/max aggregationmultilayer SSL · synthetic noisy caseaccuracy: MAX 0.68 vs learned 0.99 at std=2Hurt
AGML and SGMI baselinesmultilayer SSL · real datasets 10% labelsAPR: SGMI APR 0.85 vs BINOM 0.98Hurt
learned aggregation (BINOM/MULTI) versus single layersreal and synthetic datasets · real-world datasetsaccuracyImproved
additional layers of noise (one to two) added to real datasetsfixed ARIT aggregation · 3sources 1% labelsaccuracy: 0.79 clean vs 0.73 (+1 noise) vs 0.70 (+2 noise)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