Embedding Temporal Network via Neighborhood Formation

By Y. Zuo, Guannan Liu, Hao Lin, Jia Guo, X. Hu, Junjie Wu. Knowledge Discovery and Data Mining, 2018

322 citations recorded by the source corpus.

Given the rich real-life applications of network mining as well as the surge of representation learning in recent years, network embedding has become the focal point of increasing research interests in both academic and industrial domains. Nevertheless, the complete temporal formation process of networks characterized by sequential interactive events between nodes has yet seldom been modeled in the existing studies, which calls for further research on the so-called temporal network embedding problem. In light of this, in this paper, we introduce the concept of neighborhood formation sequence to describe the evolution of a node, where temporal excitation effects exist between neighbors in the sequence, and thus we propose a Hawkes process based Temporal Network Embedding (HTNE) method. HTNE well integrates the Hawkes process into network embedding so as to capture the influence of historical neighbors on the current neighbors. In particular, the interactions of low-dimensional vectors are fed into the Hawkes process as base rate and temporal influence, respectively. In addition, attention mechanism is also integrated into HTNE to better determine the influence of historical neighbors on current neighbors of a node. Experiments on three large-scale real-life networks demonstrate that the embeddings learned from the proposed HTNE model achieve better performance than state-of-the-art methods in various tasks including node classification, link prediction, and embedding visualization. In particular, temporal recommendation based on arrival rate inferred from node embeddings shows excellent predictive power of the proposed model.

Subfields: Artificial Intelligence, Computational Theory and Mathematics

View Paper: https://www.semanticscholar.org/paper/3fbe522c63b973a83f88c6aac68bc1385e90ed5b

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 Computational Theory and Mathematics

Citations in the corpus

Relational Representation Learning for Dynamic (Knowledge) Graphs: A Survey (2019, methodology): “Recently there has been growing interest towards time predicting decoders [217, 216, 261].”
Representation Learning for Dynamic Graphs: A Survey (2019, background): “(2019, 2017); Zuo et al. (2018)). Trivedi et al. (2017) consider an encoder that provides an embedding function such that given a dynamic graph until time t gives EMB(v) = (zv) and EMB(r) = (Pr).”
A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multi-Modal (2022, methodology): “Instead of modeling the time in a discrete space, like a timestamp, leveraging some temporal processing mechanism, such as Hawkes processing [302], [303], may be a direction for it.”
Graph Learning: A Survey (2021, methodology): “[119] proposed the HTNE model which is a temporal NRL approach based on the Hawkes process.”
DySAT: Deep Neural Representation Learning on Dynamic Graphs via Self-Attention Networks (2020, unknown): “In the scenario of timestamped graphs, representative methods include temporal random walks [20], and neural extensions of temporal point-processes [31, 32, 42].”
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].”