arXiv subjects

Pingpeng Yuan

Publications and source records attributed to Pingpeng Yuan.

7 recordsLinked to original sources

arXiv2025

Scalable Similarity Search over Large Attributed Bipartite Graphs

Bipartite graphs are widely used to model relationships between entities of different types, where nodes are divided into two disjoint sets. Similarity search, a fundamental operation that retrieves nodes similar to a given query node, plays a crucial role in various real-world applications, including machine learning and graph clustering. However, existing state-of-the-art methods often struggle to accurately capture the unique structural properties of bipartite graphs or fail to incorporate the informative node attributes, leading to suboptimal performance. Besides, their high computational complexity limits scalability, making them impractical for large graphs with millions of nodes and tens of thousands of attributes. To overcome these challenges, we first introduce Attribute-augmented Hidden Personalized PageRank (AHPP), a novel random walk model designed to blend seamlessly both the higher-order bipartite structure proximity and attribute similarity. We then formulate the similarity search over attributed bipartite graphs as an approximate AHPP problem and propose two efficient push-style local algorithms with provable approximation guarantees. Finally, extensive experiments on real-world and synthetic datasets validate the effectiveness of AHPP and the efficiency of our proposed algorithms when compared with fifteen competitors.

cs.DS↗

arXiv2025

Fast Answering Pattern-Constrained Reachability Queries with Two-Dimensional Reachability Index

Reachability queries ask whether there exists a path from the source vertex to the target vertex on a graph. Recently, several powerful reachability queries, such as Label-Constrained Reachability (LCR) queries and Regular Path Queries (RPQ), have been proposed for emerging complex edge-labeled digraphs. However, they cannot allow users to describe complex query requirements by composing query patterns. Here, we introduce composite patterns, a logical expression of patterns that can express complex constraints on the set of labels. Based on pattern, we propose pattern-constrained reachability queries (PCR queries). However, answering PCR queries is NP-hard. Thus, to improve the performance to answer PCR queries, we build a two-dimensional reachability (TDR for short) index which consists of a multi-way index (horizontal dimension) and a path index (vertical dimension). Because the number of combinations of both labels and vertices is exponential, it is very expensive to build full indices that contain all the reachability information. Thus, the reachable vertices of a vertex are decomposed into blocks, each of which is hashed into the horizontal dimension index and the vertical dimension index, respectively. The indices in the horizontal dimension and the vertical dimension serve as a global filter and a local filter, respectively, to prune the search space. Experimental results demonstrate that our index size and indexing time outperform the state-of-the-art label-constrained reachability indexing technique on 16 real datasets. TDR can efficiently answer pattern-constrained reachability queries, including label-constrained reachability queries.

cs.DB↗

arXiv2025

Effective and Efficient Conductance-based Community Search at Billion Scale

Community search is a widely studied semi-supervised graph clustering problem, retrieving a high-quality connected subgraph containing the user-specified query vertex. However, existing methods primarily focus on cohesiveness within the community but ignore the sparsity outside the community, obtaining sub-par results. Inspired by this, we adopt the well-known conductance metric to measure the quality of a community and introduce a novel problem of conductance-based community search (CCS). CCS aims at finding a subgraph with the smallest conductance among all connected subgraphs that contain the query vertex. We prove that the CCS problem is NP-hard. To efficiently query CCS, a four-stage subgraph-conductance-based community search algorithm, SCCS, is proposed. Specifically, we first greatly reduce the entire graph using local sampling techniques. Then, a three-stage local optimization strategy is employed to continuously refine the community quality. Namely, we first utilize a seeding strategy to obtain an initial community to enhance its internal cohesiveness. Then, we iteratively add qualified vertices in the expansion stage to guarantee the internal cohesiveness and external sparsity of the community. Finally, we gradually remove unqualified vertices during the verification stage. Extensive experiments on real-world datasets containing one billion-scale graph and synthetic datasets show the effectiveness, efficiency, and scalability of our solutions.

cs.SI↗

arXiv2024

Towards Truss-Based Temporal Community Search

Identifying communities from temporal networks facilitates the understanding of potential dynamic relationships among entities, which has already received extensive applications. However, existing methods primarily rely on lower-order connectivity (e.g., temporal edges) to capture the structural and temporal cohesiveness of the community, often neglecting higher-order temporal connectivity, which leads to sub-optimal results. To overcome this dilemma, we propose a novel temporal community model named maximal-truss (MDT). This model emphasizes maximal temporal support, ensuring all edges are connected by a sequence of triangles with elegant temporal properties. To search the MDT containing the user-initiated query node q (q-MDT), we first design a powerful local search framework with some effective pruning strategies. This approach aims to identify the solution from the small temporal subgraph which is expanded from q. To further improve the performance on large graphs, we build the temporal trussness index (TT-index) for all edges. Leveraging the TT-index allows us to efficiently search high-probability target subgraphs instead of performing a full search across the entire input graph. Empirical results on nine real-world networks and seven competitors demonstrate the superiority of our solutions in terms of efficiency, effectiveness, and scalability

cs.SI↗

arXiv2024

XMiner: Efficient Directed Subgraph Matching with Pattern Reduction

Graph pattern matching, one of the fundamental graph mining problems, aims to extract structural patterns of interest from an input graph. The state-of-the-art graph matching algorithms and systems are mainly designed for undirected graphs. Directed graph matching is more complex than undirected graph matching because the edge direction must be taken into account before the exploration of each directed edge. Thus, the technologies (e.g. storage, exploiting symmetry for graph matching) for undirected graph matching may not be fully applicable to directed graphs. For example, the redundancy implied in directed graph pattern can not be detected using the symmetry breaking for undirected pattern graph. Here, we present XMiner for efficient directed graph pattern matching whose core idea is 'pattern reduction'. It first analyzes the relationship between constraints implied in a pattern digraph. Then it reduces the pattern graph into a simplified form by finding a minimum constraint cover. Finally, XMiner generates an execution plan and follows it to extract matchings of the pattern graph. So, XMiner works on simplified pattern graph and avoids much data access and redundant computation throughout the matching process. Our experimental results show that XMiner outperforms state-of the-art stand-alone graph matching systems, and scales to complex graph pattern matching tasks on larger graph.

cs.DB↗

arXiv2023

Query-Centered Temporal Community Search via Time-Constrained Personalized PageRank

Existing temporal community search suffers from two defects: (i) they ignore the temporal proximity between the query vertex $q$ and other vertices but simply require the result to include $q$. Thus, they find many temporal irrelevant vertices (these vertices are called \emph{query-drifted vertices}) to $q$ for satisfying their cohesiveness, resulting in $q$ being marginalized; (ii) their methods are NP-hard, incurring high costs for exact solutions or compromised qualities for approximate/heuristic algorithms. Inspired by these, we propose a novel problem named \emph{query-centered} temporal community search to circumvent \emph{query-drifted vertices}. Specifically, we first present a novel concept of Time-Constrained Personalized PageRank to characterize the temporal proximity between $q$ and other vertices. Then, we introduce a model called $β$-temporal proximity core, which can combine temporal proximity and structural cohesiveness. Subsequently, our problem is formulated as an optimization task that finds a $β$-temporal proximity core with the largest $β$. To solve our problem, we first devise an exact and near-linear time greedy removing algorithm that iteratively removes unpromising vertices. To improve efficiency, we then design an approximate two-stage local search algorithm with bound-based pruning techniques. Finally, extensive experiments on eight real-life datasets and nine competitors show the superiority of the proposed solutions.

cs.DS↗

arXiv2022

Significant Engagement Community Search on Temporal Networks: Concepts and Algorithms

Community search, retrieving the cohesive subgraph which contains the query vertex, has been widely touched over the past decades. The existing studies on community search mainly focus on static networks. However, real-world networks usually are temporal networks where each edge is associated with timestamps. The previous methods do not work when handling temporal networks. We study the problem of identifying the significant engagement community to which the user-specified query belongs. Specifically, given an integer k and a query vertex u, then we search for the subgraph H which satisfies (i) u $\in$ H; (ii) the de-temporal graph of H is a connected k-core; (iii) In H that u has the maximum engagement level. To address our problem, we first develop a top-down greedy peeling algorithm named TDGP, which iteratively removes the vertices with the maximum temporal degree. To boost the efficiency, we then design a bottom-up local search algorithm named BULS and its enhanced versions BULS+ and BULS*. Lastly, we empirically show the superiority of our proposed solutions on six real-world temporal graphs.

cs.SI↗