Research map / Architectures and efficiency / RNNs and normalization
Distributed Composite Quantization
Weixiang Hong, Jingjing Meng, Junsong Yuan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| distributed training (DCQ) instead of centralized CQ | Composite Quantization · Holidays Fisher 64-bit | mAP: 0.560 -> 0.554 | No clear effect |
| distributed training (DCQ) instead of centralized CQ | Composite Quantization · SIFT1M 128-bit | recall@1 (%): 54.43 -> 53.27 (4-node tree) | Hurt |
| line topology instead of binary tree topology (ablation) | DCQ · SIFT1M 128-bit | iterations to converge: 22 -> 26 (4 nodes) | Hurt |
| line topology instead of binary tree topology (ablation) | DCQ · SIFT1M 128-bit | recall@1 (%): 53.27 -> 52.78 (4 nodes); 52.19 -> 52.55 (16 nodes) | No clear effect |
| increase number of nodes from 1 to 16 (tree) (ablation) | DCQ · SIFT1M 128-bit | recall@1 (%): 54.43 -> 52.19 | No clear effect |
| distributed (16-node tree) versus single-machine training | CQ · SIFT1M 128-bit | training time (min): 328 -> about 63 | Improved |
| addition-based (CQ/DCQ) instead of partition-based quantization (PQ) | quantizer · UKBench Fisher 64-bit | score: 1.637 -> 2.315 | Improved |
Closest papers by meaning
- Composite Quantization (TPAMI 2018 · similarity 0.89)
- Asymmetric Mapping Quantization for Nearest Neighbor Search (TPAMI 2019 · similarity 0.88)
- Norm-Explicit Quantization: Improving Vector Quantization for Maximum Inner Product Search (AAAI 2020 · similarity 0.87)
- JointSQ: Joint Sparsification-Quantization for Distributed Learning (CVPR 2024 · similarity 0.87)
- Approximate Search with Quantized Sparse Representations (ECCV 2016 · similarity 0.86)
- QBB: Quantization with Binary Bases for LLMs (NeurIPS 2024 · 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.
