AI Paper Atlas

Research map / Benchmarks / ogbg-molhiv

ogbg-molhiv leaderboard

26 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on ogbg-molhiv. Best ROC-AUC: 87.4 (GT+GTE, ICLR 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.

ogbg-molhiv · ROC-AUC

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

#ROC-AUC ↑MethodPaperTopic
187.4GT+GTE
GTE
Graph Tokenization for Bridging Graphs and Transformers
ICLR 2026 · Table 1
Graph self-supervised learning
282.72Neural FingerPrints + GMoE
Neural FingerPrints
Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling
NeurIPS 2023 · text
GNN architectures
380.86HOD-GNNOn The Expressive Power of GNN Derivatives
ICLR 2026 · Table 1
GNN architectures
480.58RFP - QR - L,A,S_learn - DSS
GINE
Graph Positional Encoding via Random Feature Propagation
ICML 2023 · Table 1
GNN architectures
580.03SUN (EGO+)
GIN
Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries
NeurIPS 2022 · Table 2
GNN architectures
679.86Nested GIN* (ens)
GIN
Nested Graph Neural Networks
NeurIPS 2021 · OGB results table
GNN architectures
779.44PINWeisfeiler and Lehman Go Paths: Learning Topological Features via Path Complexes
AAAI 2024 · ZINC and OGBG-MOLHIV table
GNN architectures
879.17PathNN-SP+ (K=2)Path Neural Networks: Expressive and Accurate Graph Neural Networks
ICML 2023 · ogbg-molhiv results table
GNN architectures
979.13ER (node) embeddings + HT (random rotations)Affinity-Aware Graph Networks
NeurIPS 2023 · Table 2
GNN architectures
1079.12pi-GNNPermute Me Softly: Learning Soft Permutations for Graph Representations
TPAMI 2022 · Table 2
GNN architectures
16 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

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