AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

ASIL : Augmented Structural Information Learning for Deep Graph Clustering in Hyperbolic Space

Li Sun, Zhenhao Huang, Yujie Wang, Hongbo Lv, Chunyang Liu, Hao Peng, Philip S. Yu

TPAMI 2026 · Graph learning › Graph algorithms and clustering · approach: Neural and local graph clustering · 4 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
add neural Lorentz boost and augmented structural entropy to LSEnetLSEnet · CoraNMI: 63.97 -> 65.78Improved
add neural Lorentz boost and augmented structural entropy to LSEnetLSEnet · CiteseerNMI: 52.26 -> 55.01Improved
add neural Lorentz boost and augmented structural entropy to LSEnetLSEnet · AMAPNMI: 71.72 -> 75.81Improved
add neural Lorentz boost and augmented structural entropy to LSEnetLSEnet · ComputerNMI: 55.03 -> 56.31Improved
add neural Lorentz boost and augmented structural entropy to LSEnetLSEnet · PubmedNMI: 34.25 -> 38.13Improved
replace heuristic classic structural entropy tree with deep hyperbolic partitioning treeCSE · CoraNMI: 60.82 -> 65.78Improved
replace heuristic classic structural entropy tree with deep hyperbolic partitioning treeCSE · CiteseerNMI: 47.12 -> 55.01Improved
use differentiable level-wise structural entropy with kNN virtual graph (linear complexity)ASIL vs CSE · Corarunning time: 30x time cost of CSEImproved
use ASIL instead of DGCluster, the fastest baselineASIL · Citeseerrunning time (s): 79.3 -> 22.1Improved
use ASIL instead of S3GCASIL · Citeseerrunning time (s): 1247.2 -> 22.1Improved
use ASIL instead of Congregate-type best baselines on AMAP NMIASIL · AMAPNMI: 77.12 -> 75.81Hurt
use ASIL instead of MAGI on Computer ARIASIL · ComputerARI: 46.27 -> 45.77Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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