Incremental Frequent Subgraph Mining on Large Evolving Graphs

Abdelhamid, Ehab; Canim, Mustafa; Sadoghi, Mohammad; Bhattacharjee, Bishwaranjan; Chang, Yuan-Chi; Kalnis, Panos

doi:10.1109/icde.2018.00241

Cited by 15 publications

(24 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We define the support set σ (G S ) of any k-vertex subgraph G S ∈ C k as the number of k-vertex subgraphs of G that are isomorphic to G S , i.e., σ (G S ) = |C k i |, where G S ∈ C k i . We then define the 1 Notice that the value of T k is simply determined by k, |L |, and |Q |.…”

Section: Problem Definitionmentioning

confidence: 99%

“…The closest to our setting is the work by Ray et al [29] which consider a single graph with continuous updates, however their approach is a simple heuristic applicable only to incremental streams and without provable guarantees. Likewise, Abdelhamid et al [1] consider an analogous setting, and propose an exact algorithm which borrows from the literature on incremental pattern mining. The algorithm keeps track of "fringe" subgraph patterns, which are around the frequency threshold, and all their possible expansions/contractions (by adding/removing one edge).…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Mining Frequent Patterns in Evolving Graphs

Aslay

Nasir²,

Morales

et al. 2018

Proceedings of the 27th ACM International Conference on Information and Knowledge Management

View full text Add to dashboard Cite

Given a labeled graph, the frequent-subgraph mining (FSM) problem asks to find all the k-vertex subgraphs that appear with frequency greater than a given threshold. FSM has numerous applications ranging from biology to network science, as it provides a compact summary of the characteristics of the graph. However, the task is challenging, even more so for evolving graphs due to the streaming nature of the input and the exponential time complexity of the problem.In this paper, we initiate the study of the approximate FSM problem in both incremental and fully-dynamic streaming settings, where arbitrary edges can be added or removed from the graph. For each streaming setting, we propose algorithms that can extract a high-quality approximation of the frequent k-vertex subgraphs for a given threshold, at any given time instance, with high probability.In contrast to the existing state-of-the-art solutions that require iterating over the entire set of subgraphs for any update, our algorithms operate by maintaining a uniform sample of k-vertex subgraphs with optimized neighborhood-exploration procedures local to the updates. We provide theoretical analysis of the proposed algorithms and empirically demonstrate that the proposed algorithms generate high-quality results compared to baselines.

show abstract

Section: Problem Definitionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Mining Frequent Patterns in Evolving Graphs

Aslay

Nasir²,

Morales

et al. 2018

Proceedings of the 27th ACM International Conference on Information and Knowledge Management

View full text Add to dashboard Cite

show abstract

“…Many matching problem for large-scale and time-evolving graphs have been proposed. Previous work proposed in [1], [4], [5], [6] updates the results partially by the update of input data graph structures and attributes. However, the efficiency of the incremental process depends on the types of the input data graphs and query pattern graphs.…”

Section: Research Challenges and Contributionsmentioning

confidence: 99%

“…That means each vertex in the subgraph corresponds to a vertex in the query graph, and the connectivity is maintained even when the exact pattern does not exist in the input data graph. Additionally, the computation cost of the G-Ray is linear concerning the size Paper Method ISO Attr Time Approx IncGM+ [4] Compute only fringe subgraphs D-ISI [5] Distributed graph pruning Bounded Simulation [1] Query preserving graph compression Turbo ISO [6] Region exploration and COMB/PERM Our Method Adaptive and approximate IGPM and PEM We adopt G-Ray as a baseline of our method since it has following properties, which satisfy part of the requirements we defined.…”

Section: A Approximate Graph Pattern Matchingmentioning

confidence: 99%

Adaptive Pattern Matching with Reinforcement Learning for Dynamic Graphs

Kanezashi

Suzumura

Garcia-Gasulla

et al. 2018

2018 IEEE 25th International Conference on High Performance Computing (HiPC)

View full text Add to dashboard Cite

Graph pattern matching algorithms to handle million-scale dynamic graphs are widely used in many applications such as social network analytics and suspicious transaction detections from financial networks. On the other hand, the computation complexity of many graph pattern matching algorithms is expensive, and it is not affordable to extract patterns from million-scale graphs. Moreover, most real-world networks are time-evolving, updating their structures continuously, which makes it harder to update and output newly matched patterns in real time. Many incremental graph pattern matching algorithms which reduce the number of updates have been proposed to handle such dynamic graphs. However, it is still challenging to recompute vertices in the incremental graph pattern matching algorithms in a single process, and that prevents the real-time analysis. We propose an incremental graph pattern matching algorithm to deal with time-evolving graph data and also propose an adaptive optimization system based on reinforcement learning to recompute vertices in the incremental process more efficiently. Then we discuss the qualitative efficiency of our system with several types of data graphs and pattern graphs. We evaluate the performance using million-scale attributed and time-evolving social graphs. Our incremental algorithm is up to 10.1 times faster than an existing graph pattern matching and 1.95 times faster with the adaptive systems in a computation node than naive incremental processing.

show abstract

“…This algorithm takes memory overhead to maintain maximal frequent subgraphs (MFS) and Minimal infrequent subgraphs (MIFS). [21] MuGraM by Vijay et al takes FSM to a level where multigraphs can be processed for subgraph mining and it tested many datasets like amazon, citeseer etc. this backtracking based algorithm keeps support computation as least as possible and subgraph pruning reduces search space complexity making it better than few other approaches.…”

Section: Existing Fsm Algorithmsmentioning

confidence: 99%

A Survey of Frequent Subgraph Mining Algorithms

Dixit¹,

Khare²

2018

IJET

View full text Add to dashboard Cite

Graphs are broadly used data structure. Graphs are very useful in representing/analyzing and processing real world data. Evolving graphs are graphs which are frequently changing in nature. There is either increase or decrease in their size i.e. change in number of edges or/and vertices. Mining is the process done for knowledge discovery in graphs. Detecting specific patterns with their number of repetition more than a predefined threshold in graph is known as frequent subgraph mining or FSM. Real Timed data representing graphs are high volumetric or of very large in size, handling such graphs require processing them with special mechanisms and algorithms. Our review paper discovers present FSM techniques and tries to give their comparative study.

show abstract

Incremental Frequent Subgraph Mining on Large Evolving Graphs

Cited by 15 publications

References 6 publications

Mining Frequent Patterns in Evolving Graphs

Mining Frequent Patterns in Evolving Graphs

Adaptive Pattern Matching with Reinforcement Learning for Dynamic Graphs

A Survey of Frequent Subgraph Mining Algorithms

Contact Info

Product

Resources

About