Text reranking models are a crucial component in modern systems like Retrieval-Augmented Generation, tasked with selecting the most relevant documents prior to generation. However, current Large Language Models (LLMs) powered rerankers often face a fundamental trade-off. On one hand, Supervised Fine-Tuning based pointwise methods that frame relevance as a binary classification task lack the necessary scoring discrimination, particularly for those built on reasoning LLMs. On the other hand, approaches designed for complex reasoning often employ powerful yet inefficient listwise formulations, rendering them impractical for low latency applications. To resolve this dilemma, we introduce ERank, a highly Effective and Efficient pointwise reranker built from a reasoning LLM that excels across diverse relevance scenarios. We propose a novel two-stage training pipeline that begins with Supervised Fine-Tuning (SFT). In this stage, we move beyond binary labels and train the model generatively to output fine grained integer scores, which significantly enhances relevance discrimination. The model is then further refined using Reinforcement Learning (RL) with a novel, listwise derived reward. This technique instills global ranking awareness into the efficient pointwise architecture. We evaluate the ERank reranker on the BRIGHT, FollowIR, TREC DL, and BEIR benchmarks, demonstrating superior effectiveness and robustness compared to existing approaches. On the reasoning-intensive BRIGHT benchmark, our ERank-4B achieves an nDCG@10 of 38.7, while a larger 32B variant reaches a state of the art nDCG@10 of 40.2.

Approximate nearest neighbor search (ANNS) is widely used to retrieve similar vectors from high-dimensional data.However, many real-world applications require additional interval filtering based on numerical constraints, such as stock price ranges.In this paper, we introduce interval-filtering ANNS (IF-ANNS), a novel yet general retrieval task where both base and query vectors are associated with numerical intervals.The goal is to retrieve nearest neighbors whose intervals are fully contained within the query interval.To efficiently address this problem, we propose Hierarchical Interval Partitioning Navigating Graph (Hi-PNG), a framework that hierarchically partitions the interval space to efficiently locate the search space, eliminating unnecessary computations and achieving significant speedups.We provide a theoretical analysis of the search space, demonstrating the superiority of our approach.Extensive experiments on eight datasets, including commonly used benchmarks and real-world stock price data, show that Hi-PNG outperforms four state-of-the-art graph-based ANNS baselines, achieving up to 15× acceleration while maintaining high precision.These results highlight Hi-PNG's effectiveness in solving the IF-ANNS problem.All codes and data generation are available at https://github.com/PUITAR/Hi-PNG.git.

The 2023 Big ANN Challenge, held at NeurIPS 2023, focused on advancing the state-of-the-art in indexing data structures and search algorithms for practical variants of Approximate Nearest Neighbor (ANN) search that reflect its the growing complexity and diversity of workloads. Unlike prior challenges that emphasized scaling up classical ANN search (Simhadri et al., NeurIPS 2021), this competition addressed sparse, filtered, out-of-distribution, and streaming variants of ANNS. Participants developed and submitted innovative solutions that were evaluated on new standard datasets with constrained computational resources. The results showcased significant improvements in search accuracy and efficiency, with notable contributions from both academic and industrial teams. This paper summarizes the competition tracks, datasets, evaluation metrics, and the innovative approaches of the top-performing submissions, providing insights into the current advancements and future directions in the field of approximate nearest neighbor search.

In this paper, we study two different problems that investigate relations between given vertices$s$and$t$. The first problem is to generate the$k$-hop-constrained$s$-$t$path graph, i.e., the subgraph consisting of all paths from$s$to$t$, where each path is not longer than$k$s.t.$s$and$t$appear only once. To solve the first problem, we propose theA-BiBFS$^{++}$t++method enhanced with the reduced neighbor index and an approximate vertex grouping strategy. The second problem is to generate the$k$-hop-constrained$s$-$t$simple path graph, i.e., the subgraph consisting of all$k$-hop-constrained simple paths from$s$to$t$, which is proved to be NP-hard on directed graphs. Based onA-BiBFS$^{++}$t++, we propose theEVEmethod to tackle the second problem, which exploits the paradigm of edge-wise examination rather than exhaustively enumerating all simple paths. Extensive experiments show that bothA-BiBFS$^{++}$s++andEVEsignificantly outperform all baselines. Moreover, by takingEVEas a built-in block, state-of-the-art for hop-constrained simple path enumeration can be accelerated by up to an order of magnitude.

The state-of-the-art approximate nearest neighbor search (ANNS) algorithm builds a large proximity graph on the dataset and performs a greedy beam search, which may bring many unnecessary explorations. We develop a novel framework, namely *corssing sparse proximity graph (CSPG)*, based on random partitioning of the dataset. It produces a smaller sparse proximity graph for each partition and routing vectors that bind all the partitions. An efficient two-staged approach is designed for exploring *CSPG*, with fast approaching and cross-partition expansion. We theoretically prove that *CSPG* can accelerate the existing graph-based ANNS algorithms by reducing unnecessary explorations. In addition, we conduct extensive experiments on benchmark datasets. The experimental results confirm that the existing graph-based methods can be significantly outperformed by incorporating *CSPG*, achieving 1.5x to 2x speedups of *QPS* in almost all recalls.

Given a query vector, approximate nearest neighbor search (ANNS) aims to retrieve similar vectors from a set of high-dimensional base vectors. However, many real-world applications jointly query both vector data and structured data, imposing label constraints such as attributes and keywords on the search, known as filtered ANNS. Effectively incorporating filtering conditions with vector similarity presents significant challenges, including index for dynamically filtered search space, agnostic query labels, computational overhead for label-irrelevant vectors, and potential inadequacy in returning results. To tackle these challenges, we introduce a novel approach called the Label Navigating Graph, which encodes the containment relationships of label sets for all vectors. Built upon graph-based ANNS methods, we develop a general framework termed Unified Navigating Graph (UNG) to bridge the gap between label set containment and vector proximity relations. UNG offers several advantages, including versatility in supporting any query label size and specificity, fidelity in exclusively searching filtered vectors, completeness in providing sufficient answers, and adaptability in integration with most graph-based ANNS algorithms. Extensive experiments on real datasets demonstrate that the proposed framework outperforms all baselines, achieving 10x speedups at the same accuracy.

As one of the most primitive operators in graph algorithms, such as the triangle counting, maximal clique enumeration, and subgraph listing, a set intersection operator returns common vertices between any two given sets of vertices in data graphs. It is therefore very important to accelerate the set intersection, which will benefit a bunch of tasks that take it as a built-in block. Existing works on the set intersection usually followed the merge intersection or galloping-search framework, and most optimization research focused on how to leverage the SIMD hardware instructions. In this paper, we propose a novel multi-level set intersection framework, namely hierarchical set partitioning and join (HERO), by using our well-designed set intersection bitmap tree (SIB-tree) index, which is independent of SIMD instructions and completely orthogonal to the merge intersection framework. We recursively decompose the set intersection task into small-sized subtasks and solve each subtask using bitmap and boolean AND operations. To sufficiently achieve the acceleration brought by our proposed intersection approach, we formulate a graph reordering problem, prove its NP-hardness, and then develop a heuristic algorithm to tackle this problem. Extensive experiments on real-world graphs have been conducted to confirm the efficiency and effectiveness of our HERO approach. The speedup over classic merge intersection achieves up to 188x and 176x for triangle counting and maximal clique enumeration, respectively.

Graphs have been widely used in real-world applications, in which investigating relations between vertices is an important task. In this paper, we study the problem of generating the k-hop-constrained s-t simple path graph, i.e., the subgraph consisting of all simple paths from vertex s to vertex t of length no larger than k. To our best knowledge, we are the first to formalize this problem and prove its NP-hardness on directed graphs. To tackle this challenging problem, we propose an efficient algorithm namedEVE, which exploits the paradigm of edge-wise examination rather than exhaustively enumerating all paths. Powered by essential vertices appearing in all simple paths between vertex pairs,EVE distinguishes the edges that are definitely (or not) contained in the desired simple path graph, producing a tight upper-bound graph in the time cost O(k2|E|). Each remaining undetermined edge is further verified to deliver the exact answer. Extensive experiments are conducted on 15 real networks. The results show thatEVE significantly outperforms all baselines by several orders of magnitude. Moreover, by takingEVE as a built-in block, state-of-the-art for hop-constrained simple path enumeration can be accelerated by up to an order of magnitude.

The vertices in many graphs are weighted unequally in real scenarios, but the previous studies on the maximum independent set (MIS) ignore the weights of vertices. Therefore, the weight of an MIS may not necessarily be the largest. In this paper, we study the problem of maximum weighted independent set (MWIS) that is defined as the set of independent vertices with the largest weight. Since it is intractable to deliver the exact solution for large graphs, we design a reducing and tie-breaking framework to compute a near-maximum weighted independent set. The reduction rules are critical to reduce the search space for both exact and greedy algorithms as they determine the vertices that are definitely (or not) in the MWIS while preserving the correctness of solutions. We devise a set of novel reductions including low-degree reductions and high-degree reductions for general weighted graphs. Extensive experimental studies over real graphs confirm that our proposed method outperforms the state-of-the-arts significantly in terms of both effectiveness and efficiency.