Back to papers
CAFE: Towards Compact, Adaptive, and Fast Embedding for Large-scale Recommendation Models
Summary: CAFE enables compact, adaptive embedding for large-scale DLRMs; HotSketch identifies hot features and assigns them dedicated embeddings, while non-hot features share via multi-level hash. Theoretical accuracy/convergence analysis; 3.92% and 3.68% AUC gains on Criteo Kaggle and CriteoTB at 10k× compression.
(summarized by gpt-5-nano on Feb 09 2026)
- Paper ID
- 6861
- Venue
- SIGMOD
- Year
- 2024
- Pagerank
- 4.3399748e-05
- Overall Rank
- 9,408 | 34.62%
- DOI
-
10.1145/3639306
Incoming Non-self Citations Over Time
Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
Outgoing Citations (Sorted by Pagerank)
Showing 18 of 18 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank |
Cited Paper |
Year |
Venue |
Pagerank |
| 740 |
Distributed Representations of Tuples for Entity Resolution |
2018 |
VLDB |
0.00017358024 |
| 973 |
Natural language to SQL: Where are we today? |
2020 |
VLDB |
0.0001488435 |
| 1,586 |
Augmented Sketch: Faster and More Accurate Stream Processing |
2016 |
SIGMOD |
0.00011245213 |
| 2,678 |
HET: Scaling out Huge Embedding Model Training via Cache-enabled Distributed Framework |
2022 |
VLDB |
8.3224016e-05 |
| 3,167 |
QueryFormer: A Tree Transformer Model for Query Plan Representation |
2022 |
VLDB |
7.4561078e-05 |
| 3,273 |
Data Sketches for Disaggregated Subset Sum and Frequent Item Estimation |
2018 |
SIGMOD |
7.2899198e-05 |
| 3,492 |
Fauce: Fast and Accurate Deep Ensembles with Uncertainty for Cardinality Estimation |
2021 |
VLDB |
7.0435484e-05 |
| 3,805 |
Scaling Attributed Network Embedding to Massive Graphs |
2021 |
VLDB |
6.7485579e-05 |
| 4,464 |
LOGER: A Learned Optimizer towards Generating Efficient and Robust Query Execution Plans |
2023 |
VLDB |
6.1552798e-05 |
| 5,169 |
HET-GMP: A Graph-based System Approach to Scaling Large Embedding Model Training |
2022 |
SIGMOD |
5.642415e-05 |
| 5,383 |
Parallel Training of Knowledge Graph Embedding Models: A Comparison of Techniques |
2022 |
VLDB |
5.5357645e-05 |
| 5,910 |
At-the-time and Back-in-time Persistent Sketches |
2021 |
SIGMOD |
5.2718714e-05 |
| 6,754 |
Agile and Accurate CTR Prediction Model Training for Massive-Scale Online Advertising Systems |
2021 |
SIGMOD |
4.9344367e-05 |
| 7,163 |
SKT: A One-Pass Multi-Sketch Data Analytics Accelerator |
2021 |
VLDB |
4.808534e-05 |
| 7,253 |
Effective and Efficient Retrieval of Structured Entities |
2020 |
VLDB |
4.7825469e-05 |
| 7,473 |
Cardinality Estimation of Approximate Substring Queries using Deep Learning |
2022 |
VLDB |
4.7149077e-05 |
| 9,041 |
TreeSensing: Linearly Compressing Sketches with Flexibility |
2023 |
SIGMOD |
4.3997447e-05 |
| 9,414 |
Experimental Analysis of Large-scale Learnable Vector Storage Compression |
2024 |
VLDB |
4.3399748e-05 |
Semantically Similar Papers
| Overall Rank |
Paper |
Year |
Venue |
Pagerank |
| 11,267 |
EmbedX: A Versatile, Efficient and Scalable Platform to Embed Both Graphs and High-Dimensional Sparse Data |
2023 |
VLDB |
4.1905499e-05 |
| 2,678 |
HET: Scaling out Huge Embedding Model Training via Cache-enabled Distributed Framework |
2022 |
VLDB |
8.3224016e-05 |
| 1,970 |
Compressed Linear Algebra for Large-Scale Machine Learning |
2016 |
VLDB |
9.9024431e-05 |
| 10,482 |
CARINA: An Efficient CXL-Oriented Embedding Serving System for Recommendation Models |
2025 |
SIGMOD |
4.1905499e-05 |
| 5,146 |
Efficient Tree-SVD for Subset Node Embedding over Large Dynamic Graphs |
2023 |
SIGMOD |
5.6589364e-05 |
| 5,997 |
DLRover-RM: Resource Optimization for Deep Recommendation Models Training in the Cloud |
2024 |
VLDB |
5.2365238e-05 |
| 9,091 |
FEC: Efficient Deep Recommendation Model Training with Flexible Embedding Communication |
2023 |
SIGMOD |
4.393856e-05 |
| 11,551 |
CAFE: Constraint-Aware Feature Extraction from Large Databases |
2020 |
CIDR |
4.1905499e-05 |
| 2,690 |
Accelerating Recommendation System Training by Leveraging Popular Choices |
2022 |
VLDB |
8.2911466e-05 |
| 9,414 |
Experimental Analysis of Large-scale Learnable Vector Storage Compression |
2024 |
VLDB |
4.3399748e-05 |