AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Causal Structure Learning for Sparse Matrix Fill-in Reduction

Ziwei Li, Shuzi Niu, Tao Yuan, Huiyuan Li

ICML 2026 · Probabilistic and scientific modeling › Causal discovery · approach: Constraint-based structure learning with latents

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 causal triplet loss lCTS instead of PFM loss (ablation)MgKGAT · CPS+CFD ablationfill-in ratio: 119.02 -> 107.51Improved
add multigrid architecture to KGAT (ablation)KGAT · CPS ablationfill-in ratio: 167.41 -> 160.43Improved
add multigrid architecture to KGAT (ablation)KGAT · CFD ablationfill-in ratio: 52.83 -> 54.59Hurt
add multigrid architecture to GUnet-style network (ablation)GUnet vs MgKGAT · CPS+CFD ablationfill-in ratio: 164.19 -> 107.51Improved
add vertex embedding network on top of spectral embedding (ablation)SE · CPS+CFD ablationfill-in ratio: 118.74 -> 107.51Improved
use KAN-based KGAT instead of GAT in multigrid (ablation)MgGAT · CPS+CFD ablationfill-in ratio: 109.37 -> 107.51Improved
use KGAT instead of SAGE in multigrid (ablation)MgSAGE · CPS+CFD ablationfill-in ratio: 111.28 -> 107.51Improved
CTS versus PFM on LU timeCTS · CFDLU factorization time (s): 7.52 -> 5.02Improved
CTS versus UDNO on SPCTS · SPfill-in ratio: 52.17 vs 48.64Hurt

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