AI Paper Atlas

Research map / Benchmarks / amazon-ratings

amazon-ratings leaderboard

25 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on amazon-ratings. Best accuracy: 66.79 (PKD Llama #LN 5, NeurIPS 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.

amazon-ratings · accuracy

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

#accuracy ↑MethodPaperTopic
166.79PKD Llama #LN 5
Llama-3.1-8B-Instruct
Preference-driven Knowledge Distillation for Few-shot Node Classification
NeurIPS 2025 · Table 1
GNN architectures
255.54GAT*
GAT
Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification
NeurIPS 2024 · Heterophilous results table
GNN architectures
355.09FAF (best val)Fixed Aggregation Features Can Rival GNNs
ICML 2026 · Table 1
GNN architectures
455.05Polynormer + Wideformer
Polynormer
Relieving the Over-Aggregating Effect in Graph Transformers
NeurIPS 2025 · Table: Comparison Results on H
GNN architectures
554.58NeuralWalker
Polynormer
Learning Long Range Dependencies on Graphs via Random Walks
ICLR 2025 · Node classification table
GNN architectures
654.46PolynormerPolynormer: Polynomial-Expressive Graph Transformer in Linear Time
ICLR 2024 · Table 2
GNN architectures
754.17Co-GNN(μ,μ)Cooperative Graph Neural Networks
ICML 2024 · Table: Results on node classif
GNN architectures
853.78PRAT (ours)Learning Pseudo-Riemannian Manifolds for Heterophilic Graphs via Graph Signature
NeurIPS 2026 · Table 4
Graph self-supervised learning
953.74BuNNBundle Neural Network for message diffusion on graphs
ICLR 2025 · Table: heterophilic tasks
GNN architectures
1053.39L2G-NetL2G-NET: Local to Global Spectral Graph Neural Networks via Cauchy Factorizations
ICML 2026 · Table 2
GNN architectures
15 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.