This paper proposes a novel "Certify-then-Rectify" framework that bridges the gap between the speed of heuristic search and the rigor of exact retrieval, and reinterprets the HNSW graph as a geometric spanner and utilizes Extreme Value Theory to stochastically estimate its maximum empirical stretch factor.
Abstract
Hierarchical Navigable Small World (HNSW) graphs serve as the industry standard due to their logarithmic complexity and strong empirical performance. However, HNSW relies on greedy graph traversal, a heuristic that provides no theoretical guarantees of correctness. In this paper, we propose a novel"Certify-then-Rectify"framework that bridges the gap between the speed of heuristic search and the rigor of exact retrieval. Rather than discarding HNSW, our approach first employs a distribution-free statistical certifier to dynamically evaluate the quality of a standard HNSW search with minimal overhead. If certification indicates that the retrieved neighbors are of low quality, the framework safely escalates to a rigorous exact recovery algorithm. To make this exact recovery computationally feasible, we reinterpret the HNSW graph as a geometric spanner and utilize Extreme Value Theory to stochastically estimate its maximum empirical stretch factor. This allows us to mathematically bound the maximum distance of true nearest neighbors. Extensive evaluations on benchmark datasets demonstrate that our tiered framework delivers the average-case speed of HNSW while ensuring the worst-case correctness of exact search and outperforming other applicable approaches.
It is proved that any dataset admits a $\gamma$-almost navigable graph with just $O\left(\frac{n}{1-\gamma}\right)$ edges, linear in the dataset size, and a randomized algorithm for constructing such a graph in near-linear time is presented.
P-SAPST Lite replaces peeling with a degree order and provides a lower latency order choice within the same framework and complements edge oblivious streaming APST by addressing an offline regime in which structural plans can be reused.
Rong Fu, Yongtai Liu, Xiaowen Ma et al.· 0 citations
The findings indicate that the Eppstein-Wang algorithm provides a practical and scalable solution for average distance estimation, with higher reliability on unipartite graphs compared to bipartite graphs.
The two-dimensional bandwidth minimization problem (2DBMP) seeks an injective embedding of a guest graph into a square grid that minimizes the maximum Manhattan distance over its edges. Heuristic methods can provide strong upper bounds, but these bounds do not by themselves certify optimality. We present an efficient exact SAT-based approach for 2DBMP that incrementally searches for the minimum feasible bandwidth and certifies optimality through satisfiability and unsatisfiability results. On the standard $\lceil\sqrt n\rceil \times \lceil\sqrt n\rceil$ host grid, under a 3600 s time limit, the proposed SAT approach certifies optimal bandwidths for 41 of 43 Regular instances and 42 of 93 Harwell--Boeing instances, achieving substantially broader optimality certification within the 3600 s time limit than a previous exact approach evaluated with a 72-hour time limit. In addition, it certifies three bandwidth values that improve all previously published comparison values considered in this study and establishes all three as optimal. We further evaluate the approach on alternative host geometries, namely $2\times\lceil n/2\rceil$ and $n\times n$ grids, to assess its effectiveness beyond the standard host. Overall, the results demonstrate that the proposed SAT approach provides an effective exact method for the small- and medium-sized benchmark instances considered in this study, with fewer than 400 vertices, while heuristic methods remain important for larger and more challenging instances.
Pham Quang Minh, Dao Xuan Nghia, To Van Khanh· 0 citations
Given a graph $G$ labeled with positive distances on each edge, what is the fewest number of edge distances that must be modified for $G$ to become a metric? It is known that this metric repair problem is $\mathrm{NP}$-hard on general graphs, with prior work focusing on approximations and fixed-parameter tractability with respect to properties of the input distance function. In this paper, we ask what structural properties of the graph itself make metric repair tractable. On the positive side, we give pseudo-polynomial time algorithms for series-parallel graphs, and by generalization, graphs of bounded treewidth. An immediate consequence of this result is a new algorithm for the length-bounded multicut problem, with a parameterized runtime bound in terms of the treewidth of a modestly augmented graph. Surprisingly, pseudo-polynomial time turns out to be the best one can hope for: We complement our algorithm with a proof that metric repair is weakly $\mathrm{NP}$-hard even on graphs of pathwidth at most six. We also prove that planarity does not help either, as the problem remains strongly $\mathrm{NP}$-hard even on grid graphs.
Asaf Etgar, Anna C.Gilbert, Jamie Tucker-Foltz· 0 citations
Worst-case-optimal (wco) join algorithms have demonstrated their power -- in both theory and practice -- to efficiently solve complex Basic Graph Patterns (BGPs). Modern graph query languages, such as SPARQL and GQL, have BGPs at their core, but also have a wide range of other features, including filters (aka.\ selections). Such conditions are typically handled via pre- or post-filtering, before or after processing the BGPs. In this paper we show how to uplift wco join algorithms so as to incorporate such filtering natively, improving efficiency. We demonstrate the superiority of this approach by extending the \textit{Ring} -- a compact index that provides wco resolution of BGPs within almost no extra space on top of the graph -- so as to handle property graphs using our new techniques while retaining compactness. We implement this extension and experimentally show that it outperforms various baseline systems.
