Finding Frequent Subgraphs in Longitudinal Social Network Data Using a Weighted Graph Mining Approach

Coenen, Frans; Zito, Michele

doi:10.1007/978-3-642-17316-5_39

Cited by 15 publications

(10 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Inspired by the relevance of detecting and counting graph substructures in applications, we propose to understand the power of GNN architectures via the substructures that they can and cannot count. Also referred to by various names including graphlets, motifs, subgraphs and graph fragments, graph substructures are well-studied and relevant for graph-related tasks in computational chemistry (Deshpande et al, 2002;Murray and Rees, 2009;Duvenaud et al, 2015;Jin et al, 2018Jin et al, , 2019Jin et al, , 2020, computational biology (Koyutrk et al, 2004) and social network studies (Jiang et al, 2010). In organic chemistry, for example, certain patterns of atoms called functional groups are usually considered indicative of the molecules' properties (Lemke, 2003;Pope et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

Can Graph Neural Networks Count Substructures?

Chen,

Villar

et al. 2020

Preprint

View full text Add to dashboard Cite

The ability to detect and count certain substructures in graphs is important for solving many tasks on graph-structured data, especially in the contexts of computational chemistry and biology as well as social network analysis. Inspired by this, we propose to study the expressive power of graph neural networks (GNNs) via their ability to count attributed graph substructures, extending recent works that examine their power in graph isomorphism testing and function approximation. We distinguish between two types of substructure counting: matching-count and containment-count, and establish both positive and negative answers for popular GNN architectures. Specifically, we prove that Message Passing Neural Networks (MPNNs), 2-Weisfeiler-Lehman (2-WL) and 2-Invariant Graph Networks (2-IGNs) cannot perform matching-count of substructures consisting of 3 or more nodes, while they can perform containment-count of star-shaped substructures. We also prove positive results for k-WL and k-IGNs as well as negative results for k-WL with limited number of iterations. We then conduct experiments that support the theoretical results for MPNNs and 2-IGNs, and demonstrate that local relational pooling strategies inspired by Murphy et al. (2019) are more effective for substructure counting. In addition, as an intermediary step, we prove that 2-WL and 2-IGNs are equivalent in distinguishing non-isomorphic graphs, partly answering an open problem raised in Maron et al. (2019a).

show abstract

Section: Introductionmentioning

confidence: 99%

Can Graph Neural Networks Count Substructures?

Chen,

Villar

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…gSpan uses less memory than algorithms based on embedding lists. Experiments show that gSpan outperforms related works by an order of magnitude [19].…”

Section: Frequent Subgraph Mining (Fsm)mentioning

confidence: 91%

Accurate and Robust Malware Analysis through Similarity of External Calls Dependency Graphs (ECDG)

Puodzius

Zendra

Heuser

et al. 2021

Proceedings of the 16th International Conference on Availability, Reliability and Security

View full text Add to dashboard Cite

Malware is a primary concern in cybersecurity, being one of the attacker's favorite cyberweapons. Over time, malware evolves not only in complexity but also in diversity and quantity. Malware analysis automation is thus crucial. In this paper we present ECDGs, a shorter call graph representation, and a new similarity function that is accurate and robust. Toward this goal, we revisit some principles of malware analysis research to define basic primitives and an evaluation paradigm addressed for the setup of more reliable experiments. Our benchmark shows that our similarity function is very efficient in practice, achieving speedup rates of 3.30x and 354, 11x wrt. radiff2 for the standard and the cache-enhanced implementations, respectively. Our evaluations generate clusters that produce almost unerring results -homogeneity score of 0.983 for the accuracy phase -and marginal information loss for a highly polluted dataset -NMI score of 0.974 between initial and final clusters of the robustness phase. Overall, ECDGs and our similarity function enable autonomous frameworks for malware search and clustering that can assist human-based analysis or improve classification models for malware analysis. CCS CONCEPTS• Security and privacy → Malware and its mitigation.

show abstract

“…e 1 = (a, b), e 2 = (i, j), e 1 = (a, i), e 2 = (b, j), (11) there are four types of relations between them.…”

Section: B the Lpi Problem And Subgraphsmentioning

confidence: 99%

Two-level Graph Neural Network

Ai¹,

Sun²,

Hancock³

2022

Preprint

View full text Add to dashboard Cite

Graph Neural Networks (GNNs) are recently proposed neural network structures for the processing of graphstructured data. Due to their employed neighbor aggregation strategy, existing GNNs focus on capturing node-level information and neglect high-level information. Existing GNNs therefore suffer from representational limitations caused by the Local Permutation Invariance (LPI) problem. To overcome these limitations and enrich the features captured by GNNs, we propose a novel GNN framework, referred to as the Two-level GNN (TL-GNN). This merges subgraph-level information with nodelevel information. Moreover, we provide a mathematical analysis of the LPI problem which demonstrates that subgraph-level information is beneficial to overcoming the problems associated with LPI. A subgraph counting method based on the dynamic programming algorithm is also proposed, and this has time complexity is O(n 3 ), n is the number of nodes of a graph. Experiments show that TL-GNN outperforms existing GNNs and achieves state-of-the-art performance.

show abstract

Finding Frequent Subgraphs in Longitudinal Social Network Data Using a Weighted Graph Mining Approach

Cited by 15 publications

References 8 publications

Can Graph Neural Networks Count Substructures?

Can Graph Neural Networks Count Substructures?

Accurate and Robust Malware Analysis through Similarity of External Calls Dependency Graphs (ECDG)

Two-level Graph Neural Network

Contact Info

Product

Resources

About