Back to papers
FEXIPRO: Fast and Exact Inner Product Retrieval in Recommender Systems
Summary: FEXIPRO enables fast, exact inner-product retrieval for MF-based recommenders via a sequential scan. It truncates P via SVD so few dims capture most q^T P, computes fast upper bounds with an integer-approx P to prune, and applies a lossless transform to P to ensure positivity and monotone growth; this yields order-of-magnitude speedups on real data.
(summarized by gpt-5-nano on Feb 09 2026)
- Paper ID
- 5385
- Venue
- SIGMOD
- Year
- 2017
- Pagerank
- 6.7761705e-05
- Overall Rank
- 3,772 | 73.77%
- DOI
-
10.1145/3035918.3064009
Incoming Non-self Citations Over Time
Incoming Citations (Sorted by Pagerank)
Showing 13 of 13 citing papers.
| Rank |
Citing Paper |
Year |
Venue |
Pagerank |
| 495 |
Milvus: A Purpose-Built Vector Data Management System |
2021 |
SIGMOD |
0.00021767688 |
| 1,940 |
SliceLine: Fast, Linear-Algebra-based Slice Finding for ML Model Debugging |
2021 |
SIGMOD |
0.00010020173 |
| 7,002 |
Marrying Top-k with Skyline Queries: Relaxing the Preference Input while Producing Output of Controllable Size |
2021 |
SIGMOD |
4.8670742e-05 |
| 7,239 |
Efficient Data-aware Distance Comparison Operations for High-Dimensional Approximate Nearest Neighbor Search |
2025 |
VLDB |
4.792836e-05 |
| 7,606 |
Tribase: A Vector Data Query Engine for Reliable and Lossless Pruning Compression using Triangle Inequalities |
2025 |
SIGMOD |
4.6967106e-05 |
| 8,424 |
DIGRA: A Dynamic Graph Indexing for Approximate Nearest Neighbor Search with Range Filter |
2025 |
SIGMOD |
4.5163161e-05 |
| 8,425 |
Efficient Dynamic Indexing for Range Filtered Approximate Nearest Neighbor Search |
2025 |
SIGMOD |
4.5163161e-05 |
| 8,485 |
Maximum Inner Product is Query-Scaled Nearest Neighbor |
2025 |
VLDB |
4.4999394e-05 |
| 9,283 |
Adaptive Indexing in High-Dimensional Metric Spaces |
2023 |
VLDB |
4.3631652e-05 |
| 9,879 |
HARMONY: A Scalable Distributed Vector Database for High-Throughput Approximate Nearest Neighbor Search |
2026 |
SIGMOD |
4.2643674e-05 |
| 10,090 |
Integrating Vector Databases across Embedding Models |
2026 |
SIGMOD |
4.1945683e-05 |
| 10,110 |
SAQ: Pushing the Limits of Vector Quantization through Code Adjustment and Dimension Segmentation |
2026 |
SIGMOD |
4.1945683e-05 |
| 10,711 |
Cracking Vector Search Indexes |
2025 |
VLDB |
4.1945683e-05 |
Outgoing Citations (Sorted by Pagerank)
Showing 5 of 5 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Semantically Similar Papers
| Overall Rank |
Paper |
Year |
Venue |
Pagerank |
| 11,846 |
Real-time Video Recommendation Exploration |
2016 |
SIGMOD |
4.1945683e-05 |
| 6,017 |
A Distributed Algorithm for Large-Scale Generalized Matching |
2013 |
VLDB |
5.2415551e-05 |
| 8,296 |
Modern Recommender Systems: from Computing Matrices to Thinking with Neurons |
2018 |
SIGMOD |
4.5435639e-05 |
| 2,979 |
FlexRecs: Expressing and Combining Flexible Recommendations |
2009 |
SIGMOD |
7.7844948e-05 |
| 9,094 |
FEC: Efficient Deep Recommendation Model Training with Flexible Embedding Communication |
2023 |
SIGMOD |
4.3980444e-05 |
| 8,485 |
Maximum Inner Product is Query-Scaled Nearest Neighbor |
2025 |
VLDB |
4.4999394e-05 |
| 2,688 |
Accelerating Recommendation System Training by Leveraging Popular Choices |
2022 |
VLDB |
8.2991144e-05 |
| 5,775 |
Federated Matrix Factorization with Privacy Guarantee |
2022 |
VLDB |
5.3310992e-05 |
| 5,147 |
Efficient Tree-SVD for Subset Node Embedding over Large Dynamic Graphs |
2023 |
SIGMOD |
5.6643767e-05 |
| 4,887 |
Supercharging Recommender Systems using Taxonomies for Learning User Purchase Behavior |
2012 |
VLDB |
5.8533058e-05 |