Triangle Completion Time Prediction Using Time-Conserving Embedding

Dave, Vachik S.; Hasan, Mohammad Al

doi:10.1007/978-3-030-46150-8_32

Cited by 4 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As presented by Cai et al [3] for static graphs, a few methods handle elementary substructures that are decomposed from a whole graph structure. They incorporate topological attributes built in the network processing step, including graphlet transitions count [58], graphlet frequencies over time [59] and adjacency matrix summation [118], to learn representations capable of reconstructing such elaborate attributes using a shallow approach of an autoencoder. Hence, since these substructures are used as a topological building block of a static network, dynamic graph embedding takes into account the transitions between different elementary structures.…”

Section: Methods Based On Graph Kernelmentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Embedding Dynamic Graphs

Barros¹,

Mendonça²,

Vieira³

et al. 2021

Preprint

View full text Add to dashboard Cite

Embedding static graphs in low-dimensional vector spaces plays a key role in network analytics and inference, supporting applications like node classification, link prediction, and graph visualization.However, many real-world networks present dynamic behavior, including topological evolution, feature evolution, and diffusion. Therefore, several methods for embedding dynamic graphs have been proposed to learn network representations over time, facing novel challenges, such as time-domain modeling, temporal features to be captured, and the temporal granularity to be embedded. In this survey, we overview dynamic graph embedding, discussing its fundamentals and the recent advances developed so far. We introduce the formal definition of dynamic graph embedding, focusing on the problem setting and introducing a novel taxonomy for dynamic graph embedding input and output.We further explore different dynamic behaviors that may be encompassed by embeddings, classifying by topological evolution, feature evolution, and processes on networks. Afterward, we describe existing techniques and propose a taxonomy for dynamic graph embedding techniques based on algorithmic approaches, from matrix and tensor factorization to deep learning, random walks, and temporal point processes. We also elucidate main applications, including dynamic link prediction, anomaly detection, and diffusion prediction, and we further state some promising research directions in the area.

show abstract

Section: Methods Based On Graph Kernelmentioning

confidence: 99%

“…Several dynamic graph embedding methods generalize traditional node or link prediction tasks to consider joint prediction over larger k-node induced subgraphs [57] and graphlets [58,59].…”

Section: Topological Embeddingmentioning

confidence: 99%