AI Paper Atlas

Research map / Benchmarks / ML-1M

ML-1M leaderboard

15 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on ML-1M. Best NDCG@10: 0.8392 (FedEM, AAAI 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.

ML-1M · NDCG@10

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

#NDCG@10 ↑MethodPaperTopic
10.8392FedEMBreaking the Aggregation Bottleneck in Federated Recommendation: A Personalized Model Merging Approach
AAAI 2026 · Table 1
Personalized and heterogeneous FL
20.5577TTT4RecPreliminary Evaluation of the Test-Time Training Layers in Recommendation System (Student Abstract)
AAAI 2025 · Table 1
RNNs and normalization
30.4567CCLRecCCLRec: Consensus-driven Contrastive Learning for LLM-enhanced Graph Recommendation
ICML 2026 · Table 1
Graph self-supervised learning
40.446RaCT
DAE
RaCT: Toward Amortized Ranking-Critical Training For Collaborative Filtering
ICLR 2020 · Appendix Table: Comparison bet
Policy gradient and actor-critic
50.4416CFNetDeepCF: A Unified Framework of Representation Learning and Matching Function Learning in Recommender System
AAAI 2019 · Table: Comparison results
Recognition and long-tail
60.2822PRPFrom Pairwise to Ranking: Climbing the Ladder to Ideal Collaborative Filtering with Pseudo-Ranking
AAAI 2025 · Table 1
Recognition and long-tail
70.2558NLCFLLM Collaborative Filtering: User-Item Graph as New Language
AAAI 2026 · Table 1
Retrieval and knowledge
80.2048IOCLRecIntent Oriented Contrastive Learning for Sequential Recommendation
AAAI 2025 · Table 2
Recognition and long-tail
90.1995LLM4RSR + BirDRec
BirDRec
LLM4RSR: Large Language Models as Data Correctors for Robust Sequential Recommendation
AAAI 2025 · Table 2
Language, safety and interpretability
100.1915BirDRec
SASRec
Theoretically Guaranteed Bidirectional Data Rectification for Robust Sequential Recommendation
NeurIPS 2023 · Table 3
Recognition and long-tail
2 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

ML-1M · HR@10

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

#HR@10 ↑MethodPaperTopic
10.9507FedEMBreaking the Aggregation Bottleneck in Federated Recommendation: A Personalized Model Merging Approach
AAAI 2026 · Table 1
Personalized and heterogeneous FL
20.8191CoT4Rec
flan-t5-base
CoT4Rec: Revealing User Preferences Through Chain of Thought for Recommender Systems
AAAI 2025 · Table 2
Reasoning and chain of thought
30.7877TTT4RecPreliminary Evaluation of the Test-Time Training Layers in Recommendation System (Student Abstract)
AAAI 2025 · Table 1
RNNs and normalization
40.7796PRPFrom Pairwise to Ranking: Climbing the Ladder to Ideal Collaborative Filtering with Pseudo-Ranking
AAAI 2025 · Table 1
Recognition and long-tail
50.7253CFNetDeepCF: A Unified Framework of Representation Learning and Matching Function Learning in Recommender System
AAAI 2019 · Table: Comparison results
Recognition and long-tail
60.3457IOCLRecIntent Oriented Contrastive Learning for Sequential Recommendation
AAAI 2025 · Table 2
Recognition and long-tail
70.3392MIMAR-SRecMulti-granularity Intent Modeling with Adversarial Robustness for Sequential Recommendation
AAAI 2026 · Table 1
Recognition and long-tail
80.3308SIGMASIGMA: Selective Gated Mamba for Sequential Recommendation
AAAI 2025 · Overall performance table
Attention and transformers
90.3259BirDRec
SASRec
Theoretically Guaranteed Bidirectional Data Rectification for Robust Sequential Recommendation
NeurIPS 2023 · Table 3
Recognition and long-tail
100.2952WEARecWavelet Enhanced Adaptive Frequency Filter for Sequential Recommendation
AAAI 2026 · Table 1
Recognition and long-tail
1 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.