AI Paper Atlas

Research map / Graph learning / GNN architectures

Adaptive Initial Residual Connections for GNNs with Theoretical Guarantees

Mohammad Shirzadi, Ali Safarpoor Dehkordi, Ahad N. Zehmakan

AAAI 2026 · Graph learning › GNN architectures · approach: Graph rewiring and scalable message passing · 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
replace static initial residual (GCNII) with PageRank-based adaptive residual strengthsGNN · Texas, Wisconsin, Cornell, Chameleon, Squirrel (heterophilic)test accuracy: 59.5 -> 77.0 (Texas); 60.4 -> 79.0 (Wisconsin); 36.2 -> 65.0 (Chameleon); 28.8 -> 49.0 (Squirrel)Improved
adaptive IRC (PageRank) vs GCNIIGNN · Actortest accuracy: 35.2 -> 33.8Hurt
use fixed PageRank-based residual strengths instead of learned ones (ablation)adaptive IRC · Cora, CiteSeer, Pubmed, Texas, Cornell, Chameleon, Squirreltest accuracy: 80.1 -> 80.7 (Cora); 69.3 -> 70.2 (CiteSeer); 47.7 -> 49.0 (Squirrel)Improved
use fixed PageRank-based residual strengths instead of learned ones (ablation)adaptive IRC · Wisconsin, Actortest accuracy: 82.4 -> 79.0 (Wisconsin); 34.2 -> 33.8 (Actor)Hurt
adaptive IRC vs DirGNNGNN · Texastest accuracy: 84.6 -> 77.0Hurt
increase depth beyond four layers with adaptive IRC (ablation)adaptive IRC · node classification, all datasetstest accuracyImproved
adaptive IRC vs GCN/GAT/GraphSAGE on oversmoothingadaptive IRC · synthetic SBM, 200 nodesDirichlet energyImproved

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