AI Paper Atlas

Research map / Benchmarks / WikiCS node classification

WikiCS node classification leaderboard

10 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on WikiCS node classification. Best accuracy: 85.52 (BES, ICML 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

WikiCS node classification · accuracy

10 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
185.52BESBoundary Embedding Shaping with Adaptive Contrastive Learning for Graph Structural Disentanglement
ICML 2026 · Table 1
Graph self-supervised learning
282.4SHiFT
RoBERTa-Large + GCN
Uncovering Semantic Hierarchies in Text-Attributed Graphs via Variational EM-based LLM–GNN Synergy
NeurIPS 2026 · Table 1
Graph self-supervised learning
381.31TEDMAETeacher-guided Edge Discriminator for Personalized Graph Masked Autoencoder
AAAI 2025 · Table 1
Graph self-supervised learning
481.23GALOPAGALOPA: Graph Transport Learning with Optimal Plan Alignment
NeurIPS 2023 · Table 1
Graph self-supervised learning
580.45ControlG
GCN/GAT encoder
Feedback Control for Multi-Objective Graph Self-Supervision
ICML 2026 · Table 1
Self-supervised and contrastive
680.06CoCoCompactness and Consistency: A Conjoint Framework for Deep Graph Clustering
ICLR 2026 · Node classification table
GNN architectures
780.02pathGCNpathGCN: Learning General Graph Spatial Operators from Paths
ICML 2022 · Table, Node classification on
GNN architectures
879.59C2-GMAE
GAT encoder
Reconstruction Outcomes Look Similar but Processes Differ: Improving Context Consistency and Coverage in Graph Masked Auto-Encoder
ICML 2026 · Table 1
Graph self-supervised learning
979.42Sp2GCLGraph Contrastive Learning with Stable and Scalable Spectral Encoding
NeurIPS 2023 · Table 2
Graph self-supervised learning
1077.2SAGCLStage-Aware Graph Contrastive Learning with Node-oriented Mixture of Experts
AAAI 2026 · Table 1
Graph self-supervised learning

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.