Research map / Graph learning / Graph algorithms and clustering
Proximity Preserving Binary Code Using Signed Graph-Cut
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 PPC instead of SDH | CIFAR-10 out-of-sample hashing · CIFAR-10, 12 bits | AUC: 0.249316 -> 0.28365 | Helped |
| Use bit update rather than vector update (ablation) | PPC signed graph-cut optimization · Six small datasets | binary-code loss | Helped |
| Initialize with a random guess rather than a spectral solution (ablation) | PPC signed graph-cut optimization · Six small datasets | binary-code loss | No clear effect |
| Apply bit update to the initial code guess (ablation) | PPC signed graph-cut optimization · Six small datasets | binary-code loss | Helped |
| Use signed graph weights to model both attractive and repulsive proximity | PPC · CIFAR-10 out-of-sample retrieval | AUC | Helped |
| Optimize binary code first, then fit hashing functions | PPC out-of-sample hashing · Out-of-sample retrieval | code accuracy | Helped |
Closest papers by meaning
- K-Nearest Neighbors Hashing (CVPR 2019 · similarity 0.88)
- Asymmetric Discrete Graph Hashing (AAAI 2017 · similarity 0.84)
- Binary Embedding with Additive Homogeneous Kernels (AAAI 2017 · similarity 0.84)
- Faster Binary Embeddings for Preserving Euclidean Distances (ICLR 2021 · similarity 0.83)
- Random Cycle Coding: Lossless Compression of Cluster Assignments via Bits-Back Coding (NeurIPS 2024 · similarity 0.83)
- Differentially Private Gomory-Hu Trees (NeurIPS 2025 · similarity 0.82)
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.