Research map / Graph learning / Graph algorithms and clustering
Möbius Transformation for Fast Inner Product Search on Graph
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 |
|---|---|---|---|
| build graph on Möbius-transformed (l2) data instead of inner-product-based construction (Möbius-Graph vs ip-NSW) | graph-based MIPS index · Netflix | graph construction time (s): 2.19 -> 1.89 | Helped |
| build graph on Möbius-transformed (l2) data instead of inner-product-based construction (Möbius-Graph vs ip-NSW) | graph-based MIPS index · Music-100 | graph construction time (s): 396.82 -> 162.24 | Helped |
| build graph on Möbius-transformed (l2) data instead of inner-product-based construction (Möbius-Graph vs ip-NSW) | graph-based MIPS index · Yelp | graph construction time (s): 6.78 -> 2.34 | Helped |
| remove hierarchical structure from ip-NSW (ablation) | ip-NSW · recall vs QPS, four datasets | QPS at given recall | No clear effect |
| remove edge selection from ip-NSW (ablation) | ip-NSW · recall vs QPS, four datasets | QPS at given recall | Mixed |
| use SONG instead of HNSW as graph implementation | Möbius-Graph and ip-NSW · top-10 recall vs QPS | QPS at given recall | Helped |
Closest papers by meaning
- Optimistic Query Routing in Clustering-based Approximate Maximum Inner Product Search (NeurIPS 2025 · similarity 0.84)
- Sort Before You Prune: Improved Worst-Case Guarantees of the DiskANN Family of Graphs (ICML 2025 · similarity 0.83)
- Faster Maximum Inner Product Search in High Dimensions (ICML 2024 · similarity 0.83)
- Distance Adaptive Beam Search for Provably Accurate Graph-Based Nearest Neighbor Search (NeurIPS 2025 · similarity 0.82)
- Sign Rank Limitations for Inner Product Graph Decoders (ICML 2024 · similarity 0.82)
- Bipartite Matching in Massive Graphs: A Tight Analysis of EDCS (ICML 2024 · 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.