Edge Role Discovery via Higher-Order Structures

Ahmed, Nesreen K.; Rossi, Ryan A.; Willke, Theodore L.; Zhou, Rong

doi:10.1007/978-3-319-57454-7_23

Cited by 16 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the field of graph representation, it is crucial to comprehend the nature of the embedding generation functions as they tend to differ based on the type of behavior that is being captured from the graph [2] [5] [15] [9]. The most commonly used features for the computation of representations are structural and proximity behaviors, which play a vital role in differentiating between various embedding generation techniques [3][16] [17]. Choosing the appropriate embedding generation technique can significantly enhance the quality of the embeddings and lead to improved classification performance.…”

Section: Literature Reviewmentioning

confidence: 99%

WITHDRAWN: IEER: Inferring Embedded Email Roles

Ejaz,

Cheema,

Khan

2024

Preprint

View full text Add to dashboard Cite

In this study, we investigate the use of representation learning techniques for solving complex problems represented as graphs. To this end, we propose a novel method for learning graph representations called Inferring Embedded Email Roles (IEER). Our method generates low-dimensional vectorized features by acquiring local structural information for each vertex in the graph. Unlike existing approaches that have focused on incorporating various graph attributes, our method takes a unique approach to improving the performance of the base framework, EMBedding Email-based Roles (EMBER). This research aims to understand the effectiveness of an embedding technique for generating graph representations and its suitability for replacing the base framework technique. We identify an embedding technique that significantly improves the performance of EMBER, resulting in a 94\% accuracy improvement using the Permutation Invariant technique, which has been shown to outperform matrix factorization techniques in capturing structural behaviors. This technique has been shown to outperform matrix factorization techniques in dealing with structural behaviors. Additionally, our method is scalable and linear concerning the number of vertices in the graph.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

WITHDRAWN: IEER: Inferring Embedded Email Roles

Ejaz,

Cheema,

Khan

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Specifically, the concept is mainly related to role discovery in networks [30], which focuses on mining graph nodes with similar connectivity patterns, e.g., star-center/edge, peripheral, near-clique nodes, and motif/graphlet [27]. Besides, [2] tries to discover edge role via motifs. Overall, these works mainly focus on topology structures of graphs, where the role is a structure concept.…”

Section: A Role In Other Research Domainsmentioning

confidence: 99%

Role-Aware Modeling for N-ary Relational Knowledge Bases

Yao

2021

Preprint

View full text Add to dashboard Cite

N-ary relational knowledge bases (KBs) represent knowledge with binary and beyond-binary relational facts. Especially, in an n-ary relational fact, the involved entities play different roles, e.g., the ternary relation PlayCharacterIn consists of three roles, Actor, Character and Movie. However, existing approaches are often directly extended from binary relational KBs, i.e., knowledge graphs, while missing the important semantic property of role. Therefore, we start from the role level, and propose a Role-Aware Modeling, RAM for short, for facts in n-ary relational KBs. RAM explores a latent space that contains basis vectors, and represents roles by linear combinations of these vectors. This way encourages semantically related roles to have close representations. RAM further introduces a pattern matrix that captures the compatibility between the role and all involved entities. To this end, it presents a multilinear scoring function to measure the plausibility of a fact composed by certain roles and entities. We show that RAM achieves both theoretical full expressiveness and computation efficiency, which also provides an elegant generalization for approaches in binary relational KBs. Experiments demonstrate that RAM outperforms representative baselines on both n-ary and binary relational datasets.

show abstract

Predictive Representation Learning in Motif-Based Graph Networks

Zhang

Wan

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Edge Role Discovery via Higher-Order Structures

Cited by 16 publications

References 23 publications

WITHDRAWN: IEER: Inferring Embedded Email Roles

WITHDRAWN: IEER: Inferring Embedded Email Roles

Role-Aware Modeling for N-ary Relational Knowledge Bases

Predictive Representation Learning in Motif-Based Graph Networks

Contact Info

Product

Resources

About