This is the first study that systematically formulates and evaluates privacy-preserving RFANNS over outsourced encrypted vector databases, and improves the QPS-Recall trade-off over representative secure adaptations of existing RFANNS approaches, scaling effectively to large datasets.
Haoyu Wang, Yandi Zhang, Jia-Dong Xie et al.· 0 citations
FROG is a GPU-oriented RFANNS index that replaces multiple locally optimal substructure building with a globally aware, vertex-centric design and organizes diverse expansion neighbor candidates for each vertex in a GPU-friendly structure and rapidly identifies the expansion neighbors used for computation at query time.
Xiao-Kun Cui, Peng Liu, Jia-Dong Xie et al.· 0 citations
BoxDPpS performs box-level search with safe region pruning, eliminates redundant representations of the same iRM-set, improves early pruning through bounded warm-up, and compresses each fixed-M auxiliary network for exact parametric pseudoflow solving.
Jia-Dong Xie, Jiaming Yang, Kangfei Zhao et al.· 0 citations
This work studies a new query-efficient cycle basis (QCB) problem and devise efficient algorithms to find QCB with enhanced efficiency to enumerate cycles, and demonstrates the efficiency and scalability of the cycle enumeration algorithm based on QCB.
Experiments show that KNNG-CS achieves accuracy comparable to representative gradient-approximation coreset methods, while reducing selection time by $2.3\times$-$41.2\times$ and peak memory to $0.3\%$-$7.5\%$ of the baselines.
Yingfan Liu, Lei-Yu Zhang, Jia-Dong Xie et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
