AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

A tensor factorization model of multilayer network interdependence

Izabel Aguiar, Dane Taylor, Johan Ugander

JMLR 2024 · Architectures and efficiency › RNNs and normalization · approach: Symmetry and equivariance in loss landscapes · 3 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
allow layer dependence (core tensor C<L) instead of layer-independent NTD (ablation)NTD · Krackhardt independent link predictiontest AUCImproved
allow layer dependence instead of layer-independent NTD (ablation)NTD · Krackhardt tubular link predictiontest AUCNo clear effect
allow layer dependence or redundance instead of layer-independent NTD (ablation)NTD · Malaria link predictiontest AUCHurt
allow layer redundance or dependence instead of layer-independent NTD (ablation)NTD · Village 0 link predictiontest AUCNo clear effect
use layer redundant NTD instead of layer independent NTD (ablation)NTD · 113 village networks, K=4 and K=10test AUCNo clear effect
increase K beyond the main range (ablation)NTD · Village 0 tubular cross-validationtest AUCNo clear effect

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