AI Paper Atlas

Research map / Benchmarks / Amazon-670K

Amazon-670K leaderboard

16 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Amazon-670K. Best P@1: 53.02 (ELIAS++, NeurIPS 2022).

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-670K · P@1

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

#P@1 ↑MethodPaperTopic
153.02ELIAS++ELIAS: End-to-End Learning to Index and Search in Large Output Spaces
NeurIPS 2022 · Table 1
Recognition and long-tail
252.15CascadeXML* (DNN+tf-idf)CascadeXML: Rethinking Transformers for End-to-end Multi-resolution Training in Extreme Multi-label Classification
NeurIPS 2022 · Table 2
Recognition and long-tail
350.7ELMO (BF16)
BERT-Base
ELMO : Efficiency via Low-precision and Peak Memory Optimization in Large Output Spaces
ICML 2025 · Table: Comparison of ELMO and
RNNs and normalization
450.11XR-Transformer
BERT (3-ensemble)
Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification
NeurIPS 2021 · Table 2
Recognition and long-tail
549.1LightXMLLightXML: Transformer with Dynamic Negative Sampling for High-Performance Extreme Multi-label Text Classification
AAAI 2021 · Table: Comparisons with differ
Recognition and long-tail
648.1HASTEHASTE: Hardware-Aware Dynamic Sparse Training for Large Output Spaces
ICML 2026 · Table 1
RNNs and normalization
747.58AttentionXMLAttentionXML: Label Tree-based Attention-Aware Deep Model for High-Performance Extreme Multi-Label Text Classification
NeurIPS 2019 · Performance comparison table
Recognition and long-tail
847.1SpartexNavigating Extremes: Dynamic Sparsity in Large Output Spaces
NeurIPS 2024 · Table: Comparison with differe
Pruning and efficient tuning
946.38GLaS (Ours)Breaking the Glass Ceiling for Embedding-Based Classifiers for Large Output Spaces
NeurIPS 2019 · Table 3
Recognition and long-tail
1043.46APLC-XLNet
XLNet-Base
Pretrained Generalized Autoregressive Model with Adaptive Probabilistic Label Clusters for Extreme Multi-label Text Classification
ICML 2020 · Table 4
Recognition and long-tail
6 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.