AI Paper Atlas

Research map / Graph learning / GNN architectures

Co-Embedding of Nodes and Edges With Graph Neural Networks

Xiaodong Jiang, Ronghang Zhu, Pengsheng Ji, Sheng Li

TPAMI 2020 · Graph learning › GNN architectures · approach: Graph structure learning · 124 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 edge-node switching convolution (CensNet instead of GCN)GCN · Tox21 test (90% train)AUC: 0.75 -> 0.79Improved
add edge-node switching convolution (CensNet instead of GCN)GCN · Lipophilicity test (90% train)RMSE: 0.97 -> 0.83Improved
add edge-node switching convolution (CensNet instead of GCN)GCN · Lipophilicity test (60% train)RMSE: 1.06 -> 0.97Improved
add edge-node switching convolution (CensNet instead of GCN)GCN · Cora node classification (3% labels)accuracy (%): 74.0 -> 79.4Improved
add edge-node switching convolution (CensNet instead of GCN)GCN · Citeseer node classification (0.3% labels)accuracy (%): 39.2 -> 49.4Improved
add edge-node switching convolution (CensNet instead of AdaLNet)AdaLNet · Cora node classification (0.5% labels)accuracy (%): 60.8 -> 57.7Hurt
add edge-node switching convolution (CensNet instead of LNet)LNet · PubMed node classification (0.1% labels)accuracy (%): 73.4 -> 69.9Hurt
add edge-node switching to the VAE encoder (CensNet-VAE instead of VGAE)VGAE · Pubmed link predictionAUC (%): 94.4 -> 95.5Improved
add edge-node switching to the VAE encoder (CensNet-VAE instead of VGAE)VGAE · Citeseer link predictionAUC (%): 90.8 -> 90.6No clear effect
add more edge layers to CensNet-VAE (ablation)CensNet-VAE · link prediction (Cora, Citeseer, Pubmed)AUCNo clear effect
add node-edge switching operationGCN · Cora node classificationtime per epoch: about 40% slowerHurt
use mini-batch training with proportional sampling from train/val/test (ablation)CensNet · node classificationaccuracyNo 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