AI Paper Atlas

Research map / Benchmarks / roman-empire

roman-empire leaderboard

29 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on roman-empire. Best accuracy: 93.87 (D-CDE, NeurIPS 2024).

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.

roman-empire · accuracy

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

#accuracy ↑MethodPaperTopic
193.87D-CDEDistributed-Order Fractional Graph Operating Network
NeurIPS 2024 · Heterophilic node classificati
GNN architectures
293.42Nvo-CDENeural Variable-Order Fractional Differential Equation Networks
AAAI 2025 · Table: Node classification res
Differential equations and PDEs
392.92NeuralWalker
Polynormer
Learning Long Range Dependencies on Graphs via Random Walks
ICLR 2025 · Node classification table
GNN architectures
492.87Commute GNNCommute Graph Neural Networks
ICML 2025 · Table 1
GNN architectures
592.63CSNNCooperative Sheaf Neural Networks
ICLR 2026 · Table 1
GNN architectures
692.16Polynormer + Wideformer
Polynormer
Relieving the Over-Aggregating Effect in Graph Transformers
NeurIPS 2025 · Table: Comparison Results on H
GNN architectures
792.13PolynormerPolynormer: Polynomial-Expressive Graph Transformer in Linear Time
ICLR 2024 · Table 2
GNN architectures
892.12L2G-NetL2G-NET: Local to Global Spectral Graph Neural Networks via Cauchy Factorizations
ICML 2026 · Table 2
GNN architectures
992.03Stable-ChebNetReturn of ChebNet: Understanding and Improving an Overlooked GNN on Long Range Tasks
NeurIPS 2025 · Table, Additional Experiments
GNN architectures
1091.75BuNNBundle Neural Network for message diffusion on graphs
ICLR 2025 · Table: heterophilic tasks
GNN architectures
19 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.