Continuous-Time Dynamic Network Embeddings

Nguyen, Giang; Lee, John Boaz; Rossi, Ryan A.; Ahmed, Nesreen K.; Koh, Eunyee; Kim, Sung‐Chul

doi:10.1145/3184558.3191526

Cited by 409 publications

(233 citation statements)

References 40 publications

Supporting

Mentioning

232

Contrasting

Order By: Relevance

“…For the methods that are not able to deal with time dependencies, i.e. node2vec, there are following two typical treatments: 1) only using G t−1 to infer G t [18]; or 2) aggregating previous 10 snapshots into a single network and then do link prediction [31], [45]. We choose the former one when implementing node2vec, because the relatively long sequence of historical snapshots here may carry some disturbing information that node2vec cannot handle, leading to even poor performance.…”

Section: Resultsmentioning

confidence: 99%

E-LSTM-D: A Deep Learning Framework for Dynamic Network Link Prediction

Chen

Zhang

et al. 2021

IEEE Trans. Syst. Man Cybern, Syst.

127

View full text Add to dashboard Cite

Predicting the potential relations between nodes in networks, known as link prediction, has long been a challenge in network science. However, most studies just focused on link prediction of static network, while real-world networks always evolve over time with the occurrence and vanishing of nodes and links. Dynamic network link prediction thus has been attracting more and more attention since it can better capture the evolution nature of networks, but still most algorithms fail to achieve satisfied prediction accuracy. Motivated by the excellent performance of Long Short-Term Memory (LSTM) in processing time series, in this paper, we propose a novel Encoder-LSTM-Decoder (E-LSTM-D) deep learning model to predict dynamic links end to end. It could handle long term prediction problems, and suits the networks of different scales with finetuned structure. To the best of our knowledge, it is the first time that LSTM, together with an encoder-decoder architecture, is applied to link prediction in dynamic networks. This new model is able to automatically learn structural and temporal features in a unified framework, which can predict the links that never appear in the network before. The extensive experiments show that our E-LSTM-D model significantly outperforms newly proposed dynamic network link prediction methods and obtain the state-of-the-art results.

show abstract

Section: Resultsmentioning

confidence: 99%

E-LSTM-D: A Deep Learning Framework for Dynamic Network Link Prediction

Chen

Zhang

et al. 2021

IEEE Trans. Syst. Man Cybern, Syst.

127

View full text Add to dashboard Cite

show abstract

“…An extensive overview of temporal graphs, their static representations, and temporal walks can be found in [12,21]. In [25] temporal random walks are used to obtain node embeddings for link prediction in evolving networks. In [9], the Katz centrality is extended to temporal graphs using temporal walks.…”

Section: Related Workmentioning

confidence: 99%

“…Recently, methods for dynamic graphs were proposed where edges may be added to the graph as time progresses. All of these approaches focus on link prediction in single graphs, see, e.g., [25,32]. Graph neural networks [8] emerged as an alternative for graph classification.…”

Section: Related Workmentioning

confidence: 99%

Temporal Graph Kernels for Classifying Dissemination Processes

Oettershagen¹,

Kriege²,

Morris³

et al. 2020

Proceedings of the 2020 SIAM International Conference on Data Mining

View full text Add to dashboard Cite

Many real-world graphs or networks are temporal, e.g., in a social network persons only interact at specific points in time. This information directs dissemination processes on the network, such as the spread of rumors, fake news, or diseases. However, the current state-of-the-art methods for supervised graph classification are designed mainly for static graphs and may not be able to capture temporal information. Hence, they are not powerful enough to distinguish between graphs modeling different dissemination processes. To address this, we introduce a framework to lift standard graph kernels to the temporal domain. Specifically, we explore three different approaches and investigate the trade-offs between loss of temporal information and efficiency. Moreover, to handle large-scale graphs, we propose stochastic variants of our kernels with provable approximation guarantees. We evaluate our methods on a wide range of real-world social networks. Our methods beat static kernels by a large margin in terms of accuracy while still being scalable to large graphs and data sets. Hence, we confirm that taking temporal information into account is crucial for the successful classification of dissemination processes.

show abstract

“…Nguyen et al [16], propose a model to incorporate temporal information when creating graph embeddings via random walks by capturing individual temporal changes within a graph. The authors propose a temporal random walk to create the input data, with the approach producing more complex and rich temporal walks via a biasing process.…”

Section: B Temporal Graph Embeddingsmentioning

confidence: 99%

Temporal Neighbourhood Aggregation: Predicting Future Links in Temporal Graphs via Recurrent Variational Graph Convolutions

Bonner

Atapour-Abarghouei

Jackson

et al. 2019

2019 IEEE International Conference on Big Data (Big Data)

View full text Add to dashboard Cite

Graphs have become a crucial way to represent large, complex and often temporal datasets across a wide range of scientific disciplines. However, when graphs are used as input to machine learning models, this rich temporal information is frequently disregarded during the learning process, resulting in suboptimal performance on certain temporal infernce tasks. To combat this, we introduce Temporal Neighbourhood Aggregation (TNA), a novel vertex representation model architecture designed to capture both topological and temporal information to directly predict future graph states. Our model exploits hierarchical recurrence at different depths within the graph to enable exploration of changes in temporal neighbourhoods, whilst requiring no additional features or labels to be present. The final vertex representations are created using variational sampling and are optimised to directly predict the next graph in the sequence. Our claims are reinforced by extensive experimental evaluation on both real and synthetic benchmark datasets, where our approach demonstrates superior performance compared to competing methods, out-performing them at predicting new temporal edges by as much as 23% on real-world datasets, whilst also requiring fewer overall model parameters.

show abstract

Continuous-Time Dynamic Network Embeddings

Cited by 409 publications

References 40 publications

E-LSTM-D: A Deep Learning Framework for Dynamic Network Link Prediction

E-LSTM-D: A Deep Learning Framework for Dynamic Network Link Prediction

Temporal Graph Kernels for Classifying Dissemination Processes

Temporal Neighbourhood Aggregation: Predicting Future Links in Temporal Graphs via Recurrent Variational Graph Convolutions

Contact Info

Product

Resources

About