Steiner-Hardness: A Query Hardness Measure for Graph-Based ANN Indexes
Summary: Steiner-hardness: a graph-native, connection-based measure of query difficulty for graph-based ANN, modeling minimal query effort on a representative graph. Reducible to Directed Steiner Tree so DST solvers compute it efficiently; outperforms LID in predicting actual query effort and yields unbiased index rankings. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Zeyu Wang
- 2. Qitong Wang
- 3. Xiaoxing Cheng
- 4. Peng Wang
- 5. Themis Palpanas
- 6. Wei Wang
Incoming Citations (Sorted by Pagerank)
Showing 7 of 7 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 5,129 | Navigating Labels and Vectors: A Unified Approach to Filtered Approximate Nearest Neighbor Search | 2024 | SIGMOD | 5.6755204e-05 |
| 7,843 | Subspace Collision: An Efficient and Accurate Framework for High-dimensional Approximate Nearest Neighbor Search | 2025 | SIGMOD | 4.6367909e-05 |
| 9,291 | DARTH: Declarative Recall Through Early Termination for Approximate Nearest Neighbor Search | 2026 | SIGMOD | 4.3619549e-05 |
| 10,071 | Dynamically Detect and Fix Hardness for Efficient Approximate Nearest Neighbor Search | 2026 | SIGMOD | 4.1945683e-05 |
| 10,129 | WoW: A Window-to-Window Incremental Index for Range-Filtering Approximate Nearest Neighbor Search | 2026 | SIGMOD | 4.1945683e-05 |
| 10,154 | Distribution-Aware Exploration for Adaptive HNSW Search | 2026 | SIGMOD | 4.1945683e-05 |
| 10,761 | SIEVE: Effective Filtered Vector Search with Collection of Indexes | 2025 | VLDB | 4.1945683e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 28 of 28 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next