AI Paper Atlas

Research map / Benchmarks / COX2

COX2 leaderboard

18 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on COX2. Best accuracy: 92.76 (RTPool, ICML 2025).

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.

COX2 · accuracy

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

#accuracy ↑MethodPaperTopic
192.76RTPoolRhomboid Tiling for Geometric Graph Deep Learning
ICML 2025 · Table: Performance of differen
GNN architectures
288.2MIGNN-N3
IGNN
Implicit Graph Neural Networks: A Monotone Operator Viewpoint
ICML 2023 · Table 3
GNN architectures
387.24Wit-TopoPoolTopological Pooling on Graphs
AAAI 2023 · Table: molecular and chemical
GNN architectures
486.9IGNNImplicit Graph Neural Networks
NeurIPS 2020 · Table 1
GNN architectures
586.52AutoTransfer (30 trials)AutoTransfer: AutoML with Knowledge Transfer - An Application to Graph Neural Networks
ICLR 2023 · Table 1
Graph algorithms and clustering
683.9UPG A_{5,0.5}
IGNN
On Training Implicit Models
NeurIPS 2021 · Table 3
Optimizers
783.39FDGNNFast and Deep Graph Neural Networks
AAAI 2020 · Table 1
GNN architectures
882.1AttentionGNTKGraphQNTK: Quantum Neural Tangent Kernel for Graph Data
NeurIPS 2022 · Table 2
GNN architectures
982.01TopERTopER: Topological Embeddings in Graph Representation Learning
NeurIPS 2025 · Graph Classification Results t
Graph self-supervised learning
1081.8KONGKONG: Kernels for ordered-neighborhood graphs
NeurIPS 2018 · Table 1
Graph algorithms and clustering
8 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.