Dynamic Network Embedding by Modeling Triadic Closure Process

By Le-kui Zhou, Yang Yang, Xiang Ren, Fei Wu, Yueting Zhuang. 2018

508 citations recorded by the source corpus.

Network embedding, which aims to learn the low-dimensional representations of vertices, is an important task and has attracted considerable research efforts recently. In real world, networks, like social network and biological networks, are dynamic and evolving over time. However, almost all the existing network embedding methods focus on static networks while ignore network dynamics. In this paper, we present a novel representation learning approach, DynamicTriad, to preserve both structural information and evolution patterns of a given network. The general idea of our approach is to impose triad, which is a group of three vertices and is one of the basic units of networks. In particular, we model how a closed triad, which consists of three vertices connected with each other, develops from an open triad that has two of three vertices not connected with each other. This triadic closure process is a fundamental mechanism in the formation and evolution of networks, thereby makes our model being able to capture the network dynamics and to learn representation vectors for each vertex at different time steps. Experimental results on three real-world networks demonstrate that, compared with several state-of-the-art techniques, DynamicTriad achieves substantial gains in several application scenarios. For example, our approach can effectively be applied and help to identify telephone frauds in a mobile network, and to predict whether a user will repay her loans or not in a loan network.

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Statistical and Nonlinear Physics

Citations in the corpus

Recurrent Event Network for Reasoning over Temporal Knowledge Graphs (2019, background): “e stamps. 1 INTRODUCTION Representation learning on dynamically-evolving, graph-structured data has emerged as an important problem in a wide range of applications, including social network analysis (Zhou et al., 2018; Trivedi et al., 2019), knowledge graph reasoning (Trivedi et al., 2017; Nguyen et”
Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks (2021, background): “Network-embedding approaches may also be applied to temporal networks (Zhou et al., 2018; Du et al., 2018; Mahdavi et al., 2018; Singer et al., 2019; Nguyen et al., 2018).”
DySAT: Deep Neural Representation Learning on Dynamic Graphs via Self-Attention Networks (2020, methodology): “To evaluate link prediction, we use a downstream logistic regression classifier with evaluation examples from the links in G t + 1 and an equal number of randomly sampled pairs of unconnected nodes (non-links) [8, 39].”
dyngraph2vec: Capturing Network Dynamics using Dynamic Graph Representation Learning (2018, methodology): “Figure 2 shows the results of the state-of-the-art dynamic graph embedding techniques ( DynGEM , optimalSVD , and DynamicTriad ) and the three variations of our model: dyngraph2vecAE , dyn-graph2vecRNN and dyngraph2vecAERNN (see Methodology Section for the description of the methods).”
Streaming Graph Neural Networks via Continual Learning (2020, methodology): “Some of them capture temporal information along with local structure so as to improve the expressive ability of themodel, with typical examples like DynamicTriad [34], HTNE [36], EPNE [27], EvolveGCN [18], DynamicGCN [4], DGNN [14] and ST-GCN [31].”
Dynamic Network Embedding : An Extended Approach for Skip-gram based Network Embedding (2018, background): “[Zhou et al., 2018] focuses on mining the pattern of network evolvement to predicts whether there will be a link between two vertices at the next time step.”
Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks (2020, background): “SeqCopyNet (Zhou et al. 2018b) improves the copy mechanism to not only copy single lexemes, but also copies subsequences from the input text.”
CGLB: Benchmark Tasks for Continual Graph Learning (2022, background): “Finally, the essential difference between CGL, dynamic graph learning [14, 48, 18, 60, 35, 66, 33, 13, 5], and few-shot graph learning [65, 16, 57, 43] is worth noting.”
EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs (2019, background): “Dynamic-Triad (Zhou et al. 2018) uses a point process to model a more complex phenomenon—triadic closure—where a triad with three nodes is developed from an open one (a pair of nodes are not connected) to a closed one (all three pairs are connected).”
Network Representation Learning: A Survey (2017, background): “, [106], [107], [108]) assume that the node”
AliGraph: A Comprehensive Graph Neural Network Platform (2019, background): “[57] focuses on capturing the triadic structure properties for learning network embedding.”
Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs (2019, methodology): “There are attempts on predicting future links on homogeneous graphs (Pareja et al., 2020; Goyal et al., 2018, 2019; Zhou et al., 2018; Singer et al., 2019).”
Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks (2019, methodology): “ ensures platform integrity [9, 25, 26]. Representation learning, or learning low-dimensional embeddings of entities, is a powerful approach to represent the evolution of users’ and items’ properties [8, 11, 13, 14, 48, 50]. However, the recent methods that generate dynamic embeddings suffer from fo”
Temporal Graph Networks for Deep Learning on Dynamic Graphs (2020, methodology): “In the latter case, the embeddings are either aggregated by taking a weighted sum [67, 74], ﬁt to time series models [30, 24, 11, 44], used as components in RNNs [55, 45, 41, 69, 8, 54, 48], or learned by imposing a smoothness constraint over time [33, 25, 67, 75, 73, 57, 22, 17, 50].”
Relational Representation Learning for Dynamic (Knowledge) Graphs: A Survey (2019, methodology): “A common approach to leverage the temporal aspect of DTDGs is to use time as a regularizer to impose a smoothness constraint over the embeddings of each node over consecutive snapshots [31, 43, 120, 86, 242, 259, 257].”
Representation Learning for Dynamic Graphs: A Survey (2019, methodology): “Other formulations for the transform function can be found in several recent surveys (see, e.g., Zhou et al. (2018a); Cai et al. (2018)).”