AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Stationary Diffusion State Neural Estimation for Multiview Clustering

Chenghua Liu, Zhuolin Liao, Yixuan Ma, Kun Zhan

AAAI 2022 · Graph learning › Graph self-supervised learning · approach: Multi-view graph clustering · 54 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 SDSNE_sc instead of CGDSDSNE · BBC SportNMI: 0.910±0.003 -> 0.948±0.000Improved
use SDSNE_sc instead of CGDSDSNE · MSRC-v1NMI: 0.842±0.004 -> 0.872±0.000Improved
use SDSNE_sc instead of CGDSDSNE · 100 LeavesNMI: 0.943±0.007 -> 0.972±0.000Improved
use SDSNE_sc instead of O2MACSDSNE · Three SourcesNMI: 0.727±0.030 -> 0.848±0.000Improved
use SDSNE_sc instead of CGDSDSNE · Scene-15NMI: 0.419±0.006 -> 0.438±0.000Improved
use SDSNE_sc instead of O2MACSDSNE · ReutersNMI: 0.290±0.026 -> 0.393±0.000Improved
use cross-view diffusion rather than same-view diffusion (ablation)SDSNE_sc · MSRC-v1NMI: 0.872 -> 0.860Hurt
use cross-view diffusion rather than same-view diffusion (ablation)SDSNE_sc · MSRC-v1ACC: 0.933 -> 0.924Hurt
use cross-view diffusion rather than same-view diffusion (ablation)SDSNE_sc · MSRC-v1ARI: 0.845 -> 0.824Hurt
add multiple layers (1–15) (ablation)SDSNE_sc · MSRC-v1NMI: 0.872 -> 0.872No clear effect
add multiple layers (1–15) (ablation)SDSNE_sc · MSRC-v1ACC: 0.933 -> 0.933No clear effect
add multiple layers (1–15) (ablation)SDSNE_sc · MSRC-v1ARI: 0.845 -> 0.845No 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