dynnode2vec: Scalable Dynamic Network Embedding

Mahdavi, Sedigheh; Khoshraftar, Shima; An, Aijun

doi:10.1109/bigdata.2018.8621910

Cited by 86 publications

(70 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To workaround this issue, we choose to look for optimal parameters one by one, by fixing the others. Also, there are few other dynamic approaches we do not consider in our comparison due to the unavailability of the code (Dynnode2vec [15]) or their proven inefficiency 3 (Temporal network embedding [26]).…”

Section: Baseline Methodsmentioning

confidence: 99%

“…However, time is crucial for inference purposes in many use cases. Some approaches use temporal information for the conception of more reliable global embeddings [17,27], while other methods aim to obtain a representation for the network at each time step, and through different scales [25,15].…”

Section: Introductionmentioning

confidence: 99%

“…Some approaches learn time steps embeddings separately and search for the optimal linear transformation of the output matrices minimizing the distance between consecutive embeddings [12]. Another approach is to learn current time step representation by initializing it with the previous embedding vectors [15]. Those different methods can be sensitive to data sparsity: for example a missing node in a time step would mislead its representation and place it far from its previous and next embeddings.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

TemporalNode2vec: Temporal Node Embedding in Temporal Networks

Haddad

Bothorel

Lenca

et al. 2019

Complex Networks and Their Applications VIII

View full text Add to dashboard Cite

The goal of graph embedding is to learn a representation of graphs vertices in a latent low-dimensional space in order to encode the structural information that lies in graphs. While real-world networks evolve over time, the majority of research focuses on static networks, ignoring local and global evolution patterns. A simplistic approach consists of learning nodes embeddings independently for each time step. This can cause unstable and inefficient representations over time. We present a novel dynamic graph embedding approach that learns continuous time-aware node representations. Overall, we demonstrate that our method improves node classification tasks comparing to previous static and dynamic approaches as it achieves up to 14% gain regarding to the F1 score metric. We also prove that our model is more data-efficient than several baseline methods, as it affords to achieve good performances with a limited number of vertex representation features.

show abstract

Section: Baseline Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

TemporalNode2vec: Temporal Node Embedding in Temporal Networks

Haddad

Bothorel

Lenca

et al. 2019

Complex Networks and Their Applications VIII

View full text Add to dashboard Cite

show abstract

“…Tempnode2vec [49] generates PPMI matrices from individual network snapshots, factorizes the PPMI matrices, and optimizes a joint loss function to align the node embeddings and captures temporal stability. Dynnode2vec [50] extends the skip-gram architecture of node2vec so as to work with dynamic network snapshots. DyRep [51] considers both topological evolution and temporal interactions, and aims to develop embeddings which encode both structural and temporal information.…”

Section: Related Workmentioning

confidence: 99%

Temporal network embedding using graph attention network

Mohan

Pramod

2021

Complex Intell. Syst.

View full text Add to dashboard Cite

Graph convolutional network (GCN) has made remarkable progress in learning good representations from graph-structured data. The layer-wise propagation rule of conventional GCN is designed in such a way that the feature aggregation at each node depends on the features of the one-hop neighbouring nodes. Adding an attention layer over the GCN can allow the network to provide different importance within various one-hop neighbours. These methods can capture the properties of static network, but is not well suited to capture the temporal patterns in time-varying networks. In this work, we propose a temporal graph attention network (TempGAN), where the aim is to learn representations from continuous-time temporal network by preserving the temporal proximity between nodes of the network. First, we perform a temporal walk over the network to generate a positive pointwise mutual information matrix (PPMI) which denote the temporal correlation between the nodes. Furthermore, we design a TempGAN architecture which uses both adjacency and PPMI information to generate node embeddings from temporal network. Finally, we conduct link prediction experiments by designing a TempGAN autoencoder to evaluate the quality of the embedding generated, and the results are compared with other state-of-the-art methods.

show abstract

“…It would be interesting to extend this approach to co-expression networks, which are probably a lot more variable. For cases where co-expression or interaction evolves over time, e.g., for developmental processes or stress responses, it might be helpful to look at dynamic network embedding algorithms, such as dynnode2vec [24] that can learn condition-specific node embeddings without prior knowledge and more efficiently than the approach of [23]. Advances in single-cell sequencing [25] and the generation of cell atlases [26,27] are expected to elucidate even more subtleties of protein function and thus provide a valuable resource for more fine-grained functional annotation.…”

Section: Protein Representationmentioning

confidence: 99%

Automatic Gene Function Prediction in the 2020’s

Makrodimitris

Ham

Reinders

2020

Genes

View full text Add to dashboard Cite

The current rate at which new DNA and protein sequences are being generated is too fast to experimentally discover the functions of those sequences, emphasizing the need for accurate Automatic Function Prediction (AFP) methods. AFP has been an active and growing research field for decades and has made considerable progress in that time. However, it is certainly not solved. In this paper, we describe challenges that the AFP field still has to overcome in the future to increase its applicability. The challenges we consider are how to: (1) include condition-specific functional annotation, (2) predict functions for non-model species, (3) include new informative data sources, (4) deal with the biases of Gene Ontology (GO) annotations, and (5) maximally exploit the GO to obtain performance gains. We also provide recommendations for addressing those challenges, by adapting (1) the way we represent proteins and genes, (2) the way we represent gene functions, and (3) the algorithms that perform the prediction from gene to function. Together, we show that AFP is still a vibrant research area that can benefit from continuing advances in machine learning with which AFP in the 2020s can again take a large step forward reinforcing the power of computational biology.

show abstract

dynnode2vec: Scalable Dynamic Network Embedding

Cited by 86 publications

References 20 publications

TemporalNode2vec: Temporal Node Embedding in Temporal Networks

TemporalNode2vec: Temporal Node Embedding in Temporal Networks

Temporal network embedding using graph attention network

Automatic Gene Function Prediction in the 2020’s

Contact Info

Product

Resources

About