arXiv subjects

Boyu Ruan

Publications and source records attributed to Boyu Ruan.

4 recordsLinked to original sources

arXiv2026

Breaking the Static Graph: Context-Aware Traversal for Robust Retrieval-Augmented Generation

Recent advances in Retrieval-Augmented Generation (RAG) have shifted from simple vector similarity to structure-aware approaches like HippoRAG, which leverage Knowledge Graphs (KGs) and Personalized PageRank (PPR) to capture multi-hop dependencies. However, these methods suffer from a "Static Graph Fallacy": they rely on fixed transition probabilities determined during indexing. This rigidity ignores the query-dependent nature of edge relevance, causing semantic drift where random walks are diverted into high-degree "hub" nodes before reaching critical downstream evidence. Consequently, models often achieve high partial recall but fail to retrieve the complete evidence chain required for multi-hop queries. To address this, we propose CatRAG, Context-Aware Traversal for robust RAG, a framework that builds on the HippoRAG 2 architecture and transforms the static KG into a query-adaptive navigation structure. We introduce a multi-faceted framework to steer the random walk: (1) Symbolic Anchoring, which injects weak entity constraints to regularize the random walk; (2) Query-Aware Dynamic Edge Weighting, which dynamically modulates graph structure, to prune irrelevant paths while amplifying those aligned with the query's intent; and (3) Key-Fact Passage Weight Enhancement, a cost-efficient bias that structurally anchors the random walk to likely evidence. Experiments across four multi-hop benchmarks demonstrate that CatRAG consistently outperforms state of the art baselines. Our analysis reveals that while standard Recall metrics show modest gains, CatRAG achieves substantial improvements in reasoning completeness, the capacity to recover the entire evidence path without gaps. These results reveal that our approach effectively bridges the gap between retrieving partial context and enabling fully grounded reasoning. Resources are available at https://github.com/kwunhang/CatRAG.

cs.CL↗

arXiv2024

Dynamic Structural Clustering Unleashed: Flexible Similarities, Versatile Updates and for All Parameters

We study structural clustering on graphs in dynamic scenarios, where the graphs can be updated by arbitrary insertions or deletions of edges/vertices. The goal is to efficiently compute structural clustering results for any clustering parameters $\epsilon$ and $\mu$ given on the fly, for arbitrary graph update patterns, and for all typical similarity measurements. Specifically, we adopt the idea of update affordability and propose an a-lot-simpler yet more efficient (both theoretically and practically) algorithm (than state of the art), named VD-STAR to handle graph updates. First, with a theoretical clustering result quality guarantee, VD-STAR can output high-quality clustering results with up to 99.9% accuracy. Second, our VD-STAR is easy to implement as it just needs to maintain certain sorted linked lists and hash tables, and hence, effectively enhances its deployment in practice. Third and most importantly, by careful analysis, VD-STAR improves the per-update time bound of the state-of-the-art from $O(\log^2 n)$ expected with certain update pattern assumption to $O(\log n)$ amortized in expectation without any update pattern assumption. We further design two variants of VD-STAR to enhance its empirical performance. Experimental results show that our algorithms consistently outperform the state-of-the-art competitors by up to 9,315 times in update time across nine real datasets.

cs.DS↗

arXiv2022

Frequency-based Randomization for Guaranteeing Differential Privacy in Spatial Trajectories

With the popularity of GPS-enabled devices, a huge amount of trajectory data has been continuously collected and a variety of location-based services have been developed that greatly benefit our daily life. However, the released trajectories also bring severe concern about personal privacy, and several recent studies have demonstrated the existence of personally-identifying information in spatial trajectories. Trajectory anonymization is nontrivial due to the trade-off between privacy protection and utility preservation. Furthermore, recovery attack has not been well studied in the current literature. To tackle these issues, we propose a frequency-based randomization model with a rigorous differential privacy guarantee for trajectory data publishing. In particular, we introduce two randomized mechanisms to perturb the local/global frequency distributions of significantly important locations in trajectories by injecting Laplace noise. We design a hierarchical indexing along with a novel search algorithm to support efficient trajectory modification, ensuring the modified trajectories satisfy the perturbed distributions without compromising privacy guarantee or data utility. Extensive experiments on a real-world trajectory dataset verify the effectiveness of our approaches in resisting individual re-identification and recovery attacks and meanwhile preserving desirable data utility as well as the feasibility in practice.

cs.DB↗

arXiv2021

Dynamic Structural Clustering on Graphs

Structural Clustering ($DynClu$) is one of the most popular graph clustering paradigms. In this paper, we consider $StrClu$ under two commonly adapted similarities, namely Jaccard similarity and cosine similarity on a dynamic graph, $G = \langle V, E\rangle$, subject to edge insertions and deletions (updates). The goal is to maintain certain information under updates, so that the $StrClu$ clustering result on~$G$ can be retrieved in $O(|V| + |E|)$ time, upon request. The state-of-the-art worst-case cost is $O(|V|)$ per update; we improve this update-time bound significantly with the $ρ$-approximate notion. Specifically, for a specified failure probability, $δ^*$, and every sequence of $M$ updates (no need to know $M$'s value in advance), our algorithm, $DynELM$, achieves $O(\log^2 |V| + \log |V| \cdot \log \frac{M}{δ^*})$ amortized cost for each update, at all times in linear space. Moreover, $DynELM$ provides a provable "sandwich" guarantee on the clustering quality at all times after \emph{each update} with probability at least $1 - δ^*$. We further develop $DynELM$ into our ultimate algorithm, $DynStrClu$, which also supports cluster-group-by queries. Given $Q\subseteq V$, this puts the non-empty intersection of $Q$ and each $StrClu$ cluster into a distinct group. $DynStrClu$ not only achieves all the guarantees of $DynELM$, but also runs cluster-group-by queries in $O(|Q|\cdot \log |V|)$ time. We demonstrate the performance of our algorithms via extensive experiments, on 15 real datasets. Experimental results confirm that our algorithms are up to three orders of magnitude more efficient than state-of-the-art competitors, and still provide quality structural clustering results. Furthermore, we study the difference between the two similarities w.r.t. the quality of approximate clustering results.

cs.DS↗