Research map / Architectures and efficiency / Quantization
Query-Aware Quantization for Maximum Inner Product Search
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use Query-aware Quantization instead of the compared baselines | MIPS quantization · LastFM | Recall 1@N | Helped |
| Use Query-aware Quantization instead of the compared baselines | MIPS quantization · Glove | Recall 1@N | Helped |
| Use Query-aware Quantization instead of the compared baselines | MIPS quantization · Music100 | Recall 1@N | Helped |
| Use QUIP instead of PQ | MIPS quantization · LastFM | Recall 1@N | No clear effect |
| Use ScaNN instead of PQ | MIPS quantization · LastFM | Recall 1@N | No clear effect |
| Use QUIP or ScaNN instead of PQ | MIPS quantization · Music100 | Recall 1@N | No clear effect |
| Use ScaNN instead of PQ | MIPS quantization · Glove | Recall 1@N | Helped |
| Use a smaller number of codebooks (ablation) | Query-aware Quantization · Music100 | top-1 relative inner-product error | Helped |
| Vary codebook size (ablation) | Query-aware Quantization · Music100 | top-1 relative inner-product error | Helped |
Closest papers by meaning
- Anisotropic Additive Quantization for Fast Inner Product Search (AAAI 2022 · similarity 0.92)
- Amortized Maximum Inner Product Search with Learned Support Functions (ICML 2026 · similarity 0.89)
- Norm-Explicit Quantization: Improving Vector Quantization for Maximum Inner Product Search (AAAI 2020 · similarity 0.88)
- A Greedy Approach for Budgeted Maximum Inner Product Search (NeurIPS 2017 · similarity 0.87)
- Faster Maximum Inner Product Search in High Dimensions (ICML 2024 · similarity 0.86)
- Optimistic Query Routing in Clustering-based Approximate Maximum Inner Product Search (NeurIPS 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.