Towards efficient solutions of bitruss decomposition for large-scale bipartite graphs

Wang, Kai; Lin, Xuemin; Qin, Lu; Zhang, Wenjie; Zhang, Ying

doi:10.1007/s00778-021-00658-5

Cited by 26 publications

(7 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ABACUS chooses to explore vertices on the side of the incoming edge's endpoint that has the smallest cumulative degree. This is a common heuristic [28], [20], and allows for choosing the cheapest side to conduct the Algorithm 2 RANDOM PAIRING [32] 1: procedure InsertToSample({u, v}, k)…”

Section: B Counting Butterflies Per Edgementioning

confidence: 99%

“…Wang et al [20] extend [1] for dynamic graphs. Similarly, adapting the vertex-ordering approach to the streaming setting is infeasible as the priorities continuously change after each incoming edge and sorting becomes a huge overhead -besides [20] must store the whole graph in main memory, which is prohibitive for streaming algorithms that maintain only a sample of the graph in main memory. Sanei-Mehri et al [29] propose FLEET, which utilizes adaptive sampling for counting butterflies in bipartite streams using a fixed memory.…”

Section: Butterflies In Insert-only Graph Streamsmentioning

confidence: 99%

“…This metric is important in many real-world applications, such as: in online recommendation systems to identify similar items [10], [11], [12], [13], cluster users, and enhance collaborativefiltering [14]); in real-time anomaly detection [15], [16], [17]; in fraud detection [2]. Also, counting butterflies for each edge is required for the computation of k-bitrusses [18], [19], [20], which is used in a varienty of applications, such as community and spam detection [21], [22], [23], [24], [25], [26].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Space-efficient random walks on streaming graphs

et al. 2022

View full text Add to dashboard Cite

Graphs in many applications, such as social networks and IoT, are inherently streaming, involving continuous additions and deletions of vertices and edges at high rates. Constructing random walks in a graph, i.e., sequences of vertices selected with a specific probability distribution, is a prominent task in many of these graph applications as well as machine learning (ML) on graph-structured data. In a streaming scenario, random walks need to constantly keep up with the graph updates to avoid stale walks and thus, performance degradation in the downstream tasks. We present Wharf, a system that efficiently stores and updates random walks on streaming graphs. It avoids a potential size explosion by maintaining a compressed, high-throughput, and low-latency data structure. It achieves (i) the succinct representation by coupling compressed purely functional binary trees and pairing functions for storing the walks, and (ii) efficient walk updates by effectively pruning the walk search space. We evaluate Wharf, with real and synthetic graphs, in terms of throughput and latency when updating random walks. The results show the high superiority of Wharf over inverted index- and tree-based baselines.

show abstract

Section: B Counting Butterflies Per Edgementioning

confidence: 99%

Section: Butterflies In Insert-only Graph Streamsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Space-efficient random walks on streaming graphs

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Very recently, Wang et al [68] also proposed parallel versions of BE-Index based wing decomposition algorithms.…”

Section: Related Workmentioning

confidence: 99%

Parallel Peeling of Bipartite Networks for Hierarchical Dense Subgraph Discovery

Lakhotia¹,

Kannan²,

Prasanna³

2021

Preprint

View full text Add to dashboard Cite

Motif-based graph decomposition is widely used to mine hierarchical dense structures in graphs. In bipartite graphs, wing and tip decomposition construct a hierarchy of butterfly (2,2-biclique) dense edge and vertex induced subgraphs, respectively. They have applications in several domains including e-commerce, recommendation systems and document analysis.Existing decomposition algorithms use a bottom-up approach that constructs the hierarchy in an increasing order of subgraph density. They iteratively select the entities (edges or vertices) with minimum support (butterfly count) and peel them i.e. remove them from them graph and update the support of other entities. The amount of butterflies in real-world bipartite graphs makes bottom-up peeling computationally demanding. Furthermore, the strict order of peeling entities results in a large number of iterations with sequential dependencies on preceding support updates. Consequently, parallel algorithms based on bottom up peeling can only utilize intra-iteration parallelism and require heavy synchronization, leading to poor scalability.In this paper, we propose a novel Parallel Bipartite Network peelinG (PBNG) framework which adopts a two-phased peeling approach to relax the order of peeling, and in turn, dramatically reduce synchronization. The first phase divides the decomposition hierarchy into few partitions, and requires little synchronization to compute such partitioning. The second phase concurrently processes all of these partitions to generate individual levels in the final decomposition hierarchy, and requires no global synchronization.Effectively, both phases of PBNG parallelize computation across multiple levels of decomposition hierarchy, which is not possible with bottom-up peeling. The two-phased peeling further enables batching optimizations that dramatically improve the computational efficiency of PBNG. The proposed approach represents a non-trivial generalization of our prior work on a two-phased vertex peeling algorithm [30], and its adoption for both tip and wing decomposition.We empirically evaluate PBNG using several real-world bipartite graphs and demonstrate radical improvements over the existing approaches. On a shared-memory 36 core server, PBNG achieves up to 19.7× self-relative parallel speedup. Compared to the state-of-theart parallel framework ParButterfly, PBNG reduces synchronization by up to 15260× and execution time by up to 295×. Furthermore, it achieves up to 38.5× speedup over state-of-the-art algorithms specifically tuned for wing decomposition. We also present the first decomposition results of some of the largest public real-world datasets, which PBNG can peel in few minutes/hours, but algorithms in current practice fail to process even in several days. Our source code is made available at https://github.com/kartiklakhotia/RECEIPT.

show abstract

“…Bipartite graph serves as a useful data model when modeling relationships between two different types of entities and has been adopted in a large spectrum of applications including disease control on people-location networks [21,38], fraud detection on userpage networks [36,55] and recommendation on customer-product networks [26,53,56,57,66]. In the past decades, bipartite graphs are enriched with node attributes, edge importance and edge timestamps, yielding attributed bipartite graphs [65], weighted bipartite * Kai Wang is the corresponding author This work is licensed under the Creative Commons BY-NC-ND 4.0 International License.…”

Section: Introductionmentioning

confidence: 99%

Efficiently answering reachability and path queries on temporal bipartite graphs

et al. 2021

Self Cite

View full text Add to dashboard Cite

Bipartite graphs are naturally used to model relationships between two different types of entities, such as people-location, author-paper, and customer-product. When modeling real-world applications like disease outbreaks, edges are often enriched with temporal information, leading to temporal bipartite graphs. While reachability has been extensively studied on (temporal) unipartite graphs, it remains largely unexplored on temporal bipartite graphs. To fill this research gap, in this paper, we study the reachability problem on temporal bipartite graphs. Specifically, a vertex u reaches a vertex w in a temporal bipartite graph G if u and w axe connected through a series of consecutive wedges with time constraints. Towards efficiently answering if a vertex can reach the other vertex, we propose an index-based method by adapting the idea of 2-hop labeling. Effective optimization strategies and parallelization techniques are devised to accelerate the index construction process. To better support real-life scenarios, we further show how the index is leveraged to efficiently answer other types of queries, e.g., single-source reachability query and earliest-arrival path query. Extensive experiments on 16 real-world graphs demonstrate the effectiveness and efficiency of our proposed techniques.

show abstract

Towards efficient solutions of bitruss decomposition for large-scale bipartite graphs

Cited by 26 publications

References 64 publications

Space-efficient random walks on streaming graphs

Space-efficient random walks on streaming graphs

Parallel Peeling of Bipartite Networks for Hierarchical Dense Subgraph Discovery

Efficiently answering reachability and path queries on temporal bipartite graphs

Contact Info

Product

Resources

About