Research map / Graph learning / Graph algorithms and clustering
Large Graph Hashing with Spectral Rotation
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 |
|---|---|---|---|
| add spectral rotation to the real-valued solution (ablation) | AGH · CIFAR-10 48 bits, m=500 | MAP: 18.67 -> 21.07 | Helped |
| add spectral rotation to the real-valued solution (ablation) | AGH · CIFAR-10 96 bits, m=500 | MAP: 16.46 -> 20.88 | Helped |
| add spectral rotation to the real-valued solution (ablation) | AGH · CIFAR-10 48 bits, m=100 | MAP: 17.89 -> 18.12 | Helped |
| replace AGH rounding with spectral rotation plus balanced ranking assignment (LGHSR) | AGH · CIFAR-10 Hamming ranking 96 bits | MAP: 0.1766 -> 0.1987 | Helped |
| replace DGH with LGHSR | DGH · YouTube Faces Hamming ranking 128 bits | mean precision (top 2000): 0.7805 -> 0.8428 | Helped |
| use LGHSR at long code length (MNIST) | LGHSR · MNIST | MAP / F-measure | Mixed |
| replace AGH rounding with spectral rotation (LGHSR) in training cost | AGH · CIFAR-10 96 bits | training time (s): 18.3 -> 29.8 | Hurt |
Closest papers by meaning
- Asymmetric Discrete Graph Hashing (AAAI 2017 · similarity 0.87)
- An ensemble diversity approach to supervised binary hashing (NeurIPS 2016 · similarity 0.84)
- SEGA: Shaping Semantic Geometry for Robust Hashing under Noisy Supervision (NeurIPS 2025 · similarity 0.84)
- Pass-Efficient Algorithms for Graph Spectral Clustering (Student Abstract) (AAAI 2024 · similarity 0.83)
- Distributed Manifold Hashing for Image Set Classification and Retrieval (AAAI 2024 · similarity 0.83)
- Structure-Aware Spectral Sparsification via Uniform Edge Sampling (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.
