AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Intensity Profile Projection: A Framework for Continuous-Time Representation Learning for Dynamic Networks

Alexander Modell, Ian Gallagher, Emma Ceccherini, Nick Whiteley, Patrick Rubin-Delanchy

NeurIPS 2023 · Probabilistic and scientific modeling › Dynamical systems · approach: Latent dynamics models · 1 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
use IPP with kernel smoother instead of histogram intensity estimator (ablation)Intensity Profile Projection · Bifurcating block model (simulated)qualitative trajectory fidelityNo clear effect
alignment of per-snapshot spectral embeddings (Procrustes + interpolation) instead of IPPadjacency spectral embedding · Bifurcating block model (simulated)temporal coherenceHurt
averaging network over time before embedding instead of IPPadjacency spectral embedding · Bifurcating block model (simulated)structural coherenceHurt
use CLPM instead of IPPdynamic network embedding · Bifurcating block model (simulated)structural coherence (community merging)Hurt
use Omnibus instead of IPPdynamic network embedding · Bifurcating block model (simulated)structural coherence (community merging)Hurt
use PisCES instead of IPPdynamic network embedding · Bifurcating block model (simulated)temporal coherence when communities indistinguishableHurt
use MultiNeSS instead of IPPdynamic network embedding · Bifurcating block model (simulated)temporal coherence when communities indistinguishableHurt
compare IPP trajectories at lunch hour versus lesson timesIPP (kernel smoother, bandwidth 5 min, d=30) · Lyon primary school contact datacluster fragmentation of representations (t-SNE)Mixed
IPP reveals joint lessons not in the study report (classes 5A/5B, 3A/3B merge)IPP (kernel smoother) · Lyon primary school contact dataqualitative discovery of structureImproved

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