A Survey on Dynamic Network Embedding

Xie, Yu; Li, Chunyi; Yu, Bin; Zhang, Chen; Tang, Zhouhua

doi:10.48550/arxiv.2006.08093

Cited by 13 publications

(12 citation statements)

References 52 publications

(54 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another study was of a temporal hyper-SBM with ω < 1 which thus exhibits both link-persistence and group-assignment-persistence [73], influencing performance of community detection algorithms and motivating the development of new ones. Another area of relevant work is the rapidly emerging area of dynamic graph embeddings [75,[142][143][144][145][146][147][148][149][150][151][152][153][154], related to the task of inference of hidden-variable trajectories [155].…”

Section: Related Workmentioning

confidence: 99%

Dynamic Hidden-Variable Network Models

Hartle,

Papadopoulos,

Krioukov

2021

Preprint

View full text Add to dashboard Cite

Models of complex networks often incorporate node-intrinsic properties abstracted as hidden variables. The probability of connections in the network is then a function of these variables. Realworld networks evolve over time, and many exhibit dynamics of node characteristics as well as of linking structure. Here we introduce and study natural temporal extensions of static hidden-variable network models with stochastic dynamics of hidden variables and links. The rates of the hidden variable dynamics and link dynamics are controlled by two parameters, and snapshots of networks in the dynamic models may or may not be equivalent to a static model, depending on the location in the parameter phase diagram. We quantify deviations from static-like behavior, and examine the level of structural persistence in the considered models. We explore temporal versions of popular static models with community structure, latent geometry, and degree-heterogeneity. We do not attempt to directly model real networks, but comment on interesting qualitative resemblances, discussing possible extensions, generalizations, and applications.

show abstract

Section: Related Workmentioning

confidence: 99%

Dynamic Hidden-Variable Network Models

Hartle,

Papadopoulos,

Krioukov

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Moreover, there are also a few works modeling the dynamic graphs as temporal point processes in conjunction with the attention mechanism, e.g., Dynam-icTriad [30], HTNE [31], DyRep [32]. More dynamic graph embedding literature can be found in the surveys [33], [34], [2], [35].…”

Section: Gnn-based Modelsmentioning

confidence: 99%

DynG2G: An Efficient Stochastic Graph Embedding Method for Temporal Graphs

Xu¹,

Singh²,

Karniadakis³

2021

Preprint

View full text Add to dashboard Cite

Dynamic graph embedding has gained great attention recently due to its capability of learning low-dimensional and meaningful graph representations for complex temporal graphs with high accuracy. However, recent advances mostly focus on learning node embeddings as deterministic "vectors" for static graphs, hence disregarding the key graph temporal dynamics and the evolving uncertainties associated with node embedding in the latent space. In this work, we propose an efficient stochastic dynamic graph embedding method (DynG2G) that applies an inductive feed-forward encoder trained with node triplet energy-based ranking loss. Every node per timestamp is encoded as a time-dependent probabilistic multivariate Gaussian distribution in the latent space, hence we are able to quantify the node embedding uncertainty on-the-fly. We have considered eight different benchmarks that represent diversity in size (from 96 nodes to 87,626 and from 13,398 edges to 4,870,863) as well as diversity in dynamics, from slowly changing temporal evolution to rapidly varying multi-rate dynamics. We demonstrate through extensive experiments based on these eight dynamic graph benchmarks that DynG2G achieves new state-of-the-art performance in capturing the underlying temporal node embeddings. We also demonstrate that DynG2G can simultaneously predict the evolving node embedding uncertainty, which plays a crucial role in quantifying the intrinsic dimensionality of the dynamical system over time. In particular, we obtain a "universal" relation of the optimal embedding dimension, Lo, versus the effective dimensionality of uncertainty, Du, and we infer that Lo = Du for all cases; see Table III. This, in turn, implies that the uncertainty quantification approach we employ in the DynG2G algorithm correctly captures the intrinsic dimensionality of the dynamics of such evolving graphs despite the diverse nature and composition of the graphs at each timestamp. In addition, this L0 − Du correlation provides a clear path to selecting adaptively the optimum embedding size at each timestamp by setting L ≥ Do.

show abstract

“…In this paper, we survey the state-of-the-art dynamic network embedding approaches. To the best knowledge we have, there is one published survey [10] and a preprint on arxiv.org [11] in this field. In contrast to them, our survey aims to 1) inspect the related works from more perspectives like data models, 2) build the taxonomy of existing techniques from higher abstract level based on underlying data models, and 3) have more discussion of common and principal issues involved in the related work like out-of-sample node embedding and prediction of future embedding.…”

Section: Introductionmentioning

confidence: 99%

Dynamic Network Embedding Survey

Xue¹,

Zhong²,

Li³

et al. 2021

Preprint

View full text Add to dashboard Cite

Since many real world networks are evolving over time, such as social networks and user-item networks, there are increasing research efforts on dynamic network embedding in recent years. They learn node representations from a sequence of evolving graphs but not only the latest network, for preserving both structural and temporal information from the dynamic networks. Due to the lack of comprehensive investigation of them, we give a survey of dynamic network embedding in this paper. Our survey inspects the data model, representation learning technique, evaluation and application of current related works and derives common patterns from them. Specifically, we present two basic data models, namely, discrete model and continuous model for dynamic networks. Correspondingly, we summarize two major categories of dynamic network embedding techniques, namely, structural-first and temporal-first that are adopted by most related works. Then we build a taxonomy that refines the category hierarchy by typical learning models. The popular experimental data sets and applications are also summarized. Lastly, we have a discussion of several distinct research topics in dynamic network embedding.

show abstract

A Survey on Dynamic Network Embedding

Cited by 13 publications

References 52 publications

Dynamic Hidden-Variable Network Models

Dynamic Hidden-Variable Network Models

DynG2G: An Efficient Stochastic Graph Embedding Method for Temporal Graphs

Dynamic Network Embedding Survey

Contact Info

Product

Resources

About