AI Paper Atlas

Research map / Graph learning / GNN architectures

Reservoir-Based Graph Convolutional Networks

Mayssa Soussia, Gita Ayu Salsabila, Mohamed Ali Mahjoub, Islem Rekik

TPAMI 2026 · Graph learning › GNN architectures · approach: Deep graph convolution and simplification · 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
make reservoir weights trainable (TRGC-Net) (ablation)RGC-Net · MUTAG (k=1, avg)accuracy: 0.8611 -> 0.8207Hurt
make reservoir weights trainable (TRGC-Net) (ablation)RGC-Net · EMCI-AD (avg)accuracy: 0.4464 -> 0.4606 (k=1); 0.5120 -> 0.4456 (k=4)Mixed
make reservoir weights trainable (TRGC-Net) (ablation)RGC-Net · PROTEINStraining time (s): 1.83 -> 10.54Hurt
make reservoir weights trainable (TRGC-Net) (ablation)RGC-Net · DDtraining time (s): 7.73 -> 38.92Hurt
replace GCN layer with reservoir graph convolution layerGCN classifier · MUTAG (1 layer)accuracy: 0.7500 -> 0.8726Improved
increase number of layers from 1 to 5 (ablation)RGC-Net · MUTAGaccuracy: 0.8726 -> 0.8032Hurt
increase reservoir iterations from 1 to 5 (ablation)RGC-Net · MUTAG (avg)accuracy: 0.8611 -> 0.8063Hurt
increase reservoir iterations from 1 to 4 (ablation)RGC-Net · EMCI-AD (avg)accuracy: 0.4464 -> 0.5120Improved
lower leaky rate from 1 to 0.8 (k=1) (ablation)RGC-Net · MUTAGaccuracy: 0.8442 -> 0.8726Improved
lower leaky rate from 1 to 0.8 (k=1) (ablation)RGC-Net · EMCI-ADaccuracy: 0.4476 -> 0.4573No clear effect
use RGC-Net layers instead of GCN layers in graph transformerGraph transformer · EMCI-ADMAE: 0.6847 -> 0.1860Improved
use RGC-Net layers instead of GCN layers in graph transformerGraph transformer · SimulatedMAE: 0.0353 -> 0.0305Improved

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