AI Paper Atlas

Research map / Graph learning / GNN architectures

Contrastive Graph Poisson Networks: Semi-Supervised Learning with Extremely Limited Labels

Sheng Wan, Yibing Zhan, Liu Liu, Baosheng Yu, Shirui Pan, Chen Gong

NeurIPS 2021 · Graph learning › GNN architectures · approach: Graph structure learning · 26 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 fixed-graph Poisson learning with attention-based GPN (ablation)Poisson learning · Cora 1 label/classaccuracy: 46.23 -> 49.26Improved
replace Poisson learning with GPN (ablation)Poisson learning · CiteSeer 2 labels/classaccuracy: 40.69 -> 48.24Improved
add GCN branch plus contrastive loss to GPN (CGPN-GCN) (ablation)GPN · Cora 1 label/classaccuracy: 49.26 -> 60.64Improved
add GCN branch plus contrastive loss to GPN (CGPN-GCN) (ablation)GPN · CiteSeer 2 labels/classaccuracy: 48.24 -> 58.45Improved
CGPN vs best baseline at 1 label per classGNN baselines · Coraaccuracy: 56.02 -> 61.17Improved
CGPN vs best baseline at 1 label per classGNN baselines · CiteSeeraccuracy: 47.94 -> 52.68Improved
CGPN vs best baseline at 1 label per classGNN baselines · PubMedaccuracy: 58.36 -> 61.85Improved
instantiate CGPN with GAT vs GCNCGPN · Coraaccuracy: 60.64 -> 61.17No clear effect
vary lambda1 and lambda2 from 0.1 to 1.5CGPN · Cora, CiteSeeraccuracyNo 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