Maximum Inner Product is Query-Scaled Nearest Neighbor
Summary: Equates MIPS to query-scaled NNS without space transformations, enabling direct use of graph-based indexes and edge-pruning to eliminate redundant computations. Adds PSP to avoid large-norm solution clustering and AET to curb over-exploration, yielding ~35% speedup and 3x smaller indexes (deployed in Shopee). (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Tingyang Chen
- 2. Cong Fu
- 3. Kun Wang
- 4. Xiangyu Ke
- 5. Yunjun Gao
- 6. Wenchao Zhou
- 7. Yabo Ni
- 8. Anxiang Zeng
Incoming Citations (Sorted by Pagerank)
Showing 3 of 3 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,158 | Efficient and Robust Out-Of-Distribution Vector Similarity Search with Cross-Distribution Monotonic Graph | 2026 | SIGMOD | 4.1945683e-05 |
| 10,166 | FGIM: a Fast Graph-based Indexes Merging Framework for Approximate Nearest Neighbor Search | 2026 | SIGMOD | 4.1945683e-05 |
| 10,204 | Reveal Hidden Pitfalls and Navigate Next Generation of Vector Similarity Search from Task-Centric Views: [Experiments & Analysis] | 2026 | SIGMOD | 4.1945683e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 14 of 14 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next