AI Paper Atlas

Research map / Learning theory and algorithms / Clustering

Autoregressive Networks

Binyan Jiang, Jialiang Li, Qiwei Yao

JMLR 2023 · Learning theory and algorithms › Clustering · approach: Correlation clustering

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 spectral clustering on L-hat (alpha and beta information) instead of time-averaged adjacency X-barAR(1) SBM spectral clustering · AR(1) SBM simulation (q=2, p=100, n=5)NMI: 0.621 vs 0.148Improved
use spectral clustering on L-hat instead of X-barAR(1) SBM spectral clustering · AR(1) SBM simulation (q=3, p=100, n=5)NMI: .542 vs .078Improved
use spectral clustering on L-hat instead of X-barAR(1) SBM spectral clustering · AR(1) SBM simulation (q=2, p=200, n=100)NMI: .994 vs .790Improved
increase number of time points nAR(1) MLE · AR(1) parameter estimation (p=100)MSE of alpha-hat: .130 -> .002Improved
increase number of time points n from 5 to 50AR(1) MLE · AR(1) parameter estimation (p=100)95% CI coverage (%): 39.2 -> 92.3Improved
increase nodes p from 100 to 200AR(1) MLE · AR(1) parameter estimation (n=5)MSE of alpha-hat: .130 -> .131No clear effect
use communities from L-hat clustering for parameter estimation instead of X-bar clusteringAR(1) SBM · AR(1) SBM simulation (q=2, p=100, n=5)MSE of theta-hat: .0298 -> .0149Improved
aggregate to half-day networks (n=10) instead of daily (n=5)stationary AR(1) model · RFID sensors datapermutation test P-value: 0.45 -> 0.008Hurt
use BIC to choose q on French high school dataAR(1) SBM · French high school contact dataBIC: 43624 (q=2) -> 34943 (q=9)Improved

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