beam width adaptation 1gpu/cpu evaluation 1graph-based ann search 1query hardness estimation 1self-profiling 1
From the 1 of 3 linked papers with an AI index.
3 papers
cs.IR2026
SHEAF: Self-profiled Hardness Estimation from Answer-set Flux for Predicting Query Hardness in Graph-based ANN Search
Dongfang Zhao
The paper introduces SHEAF, a method that estimates how hard each query is for graph‑based approximate nearest neighbor search by measuring how its top‑k results change between sha…
cs.DC2026
ETALE: Evolving Topology with Accelerated Lock-free Execution for Dynamic Graph ANN Search on GPUs
Dongfang Zhao
Graph-based approximate nearest neighbor (ANN) indexes on the GPU are originally built for static collections and must reconstruct the affected window to absorb any update, while t…
cs.IR2026
Slipstream: Locality-Aware Graph Index Construction for Streaming Approximate Nearest Neighbor Search
Shubing Yang, Dongfang Zhao
Graph indexes are widely used for high-recall approximate nearest neighbor search (ANNS), but many real-time applications require streaming ANNS. In these real-time applications, c…