Scalable Optimization for Embedding Highly-Dynamic and Recency-Sensitive Data

Chen, Xumin; Cui, Peng; Yi, Lingling

doi:10.1145/3219819.3219898

Cited by 7 publications

(8 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One possible reason is that this solution does not suffer the aforementioned issue of global topology preservation. However, it is time-consuming [12], [14], and thus may not satisfy the requirement of promptly updating embeddings for some downstream tasks [16], [22].…”

Section: Static Network Embeddingmentioning

confidence: 99%

“…For instance, in a wireless sensor network, devices will regularly connect to or accidentally disconnect from routers; in a social network, new friendships will establish between new users and/or existing users. Due to the time-evolving nature of many real-world networks, Dynamic Network Embedding (DNE) is now attracting much attention [9], [10], [11], [12], [13], [14], [15], [16], [17], [18], [19]. The main and common objective of DNE is to efficiently update node embeddings while preserving network topology at each time step.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

GloDyNE: Global Topology Preserving Dynamic Network Embedding

Hou

Zhang

et al. 2022

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

Learning low-dimensional topological representation of a network in dynamic environments is attracting much attention due to the time-evolving nature of many real-world networks. The main and common objective of Dynamic Network Embedding (DNE) is to efficiently update node embeddings while preserving network topology at each time step. The idea of most existing DNE methods is to capture the topological changes at or around the most affected nodes (instead of all nodes) and accordingly update node embeddings. Unfortunately, this kind of approximation, although can improve efficiency, cannot effectively preserve the global topology of a dynamic network at each time step, due to not considering the inactive sub-networks that receive accumulated topological changes propagated via the high-order proximity. To tackle this challenge, we propose a novel node selecting strategy to diversely select the representative nodes over a network, which is coordinated with a new incremental learning paradigm of Skip-Gram based embedding approach. The extensive experiments show GloDyNE, with a small fraction of nodes being selected, can already achieve the superior or comparable performance w.r.t. the state-of-the-art DNE methods in three typical downstream tasks. Particularly, GloDyNE significantly outperforms other methods in the graph reconstruction task, which demonstrates its ability of global topology preservation.

show abstract

Section: Static Network Embeddingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

GloDyNE: Global Topology Preserving Dynamic Network Embedding

Hou

Zhang

et al. 2022

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

show abstract

“…Besides, if the degree of changes would greatly affect the effectiveness of a DNE method, it is then needed to carefully choose a suitable degree of changes while construing a dynamic network. But the choice of degree of changes, in turn, might result in an efficiency issue if some scenarios have a requirement in efficiency [11], [13], [17], [23], since DNE methods need to be executed more times if the choice produces more snapshots on the same dataset (e.g., compare G1 and G3 in Figure 1). Therefore, it is desirable to have a robust DNE method to reduce the complicated trade-off in industrial applications.…”

Section: Evaluation Embeddingsmentioning

confidence: 99%

Towards Robust Dynamic Network Embedding

Hou

Tang

2021

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

Dynamic Network Embedding (DNE) has recently drawn much attention due to the dynamic nature of many real-world networks. Comparing to a static network, a dynamic network has a unique character called the degree of changes, which can be defined as the average number of the changed edges between consecutive snapshots spanning a dynamic network. The degree of changes could be quite different even for the dynamic networks generated from the same dataset. It is natural to ask whether existing DNE methods are effective and robust w.r.t. the degree of changes. Towards robust DNE, we suggest two important scenarios. One is to investigate the robustness w.r.t. different slicing settings that are used to generate different dynamic networks with different degree of changes, while another focuses more on the robustness w.r.t. different number of changed edges over timesteps.

show abstract

“…After that, Chen et al [6] proposed a novel optimization method on neural networks, which assigns different sensitive weights for samples and selects the samples via their weights when computes gradients. The related samples are updated in a diffusion strategy, as the embedding of the selected sample is reconstructed.…”

Section: Embedding Based On Neural Networkmentioning

confidence: 99%

A Survey on Dynamic Network Embedding

Xie¹,

Li²,

Yu³

et al. 2020

Preprint

View full text Add to dashboard Cite

Real-world networks are composed of diverse interacting and evolving entities, while most of existing researches simply characterize them as particular static networks, without consideration of the evolution trend in dynamic networks. Recently, significant progresses in tracking the properties of dynamic networks have been made, which exploit changes of entities and links in the network to devise network embedding techniques. Compared to widely proposed static network embedding methods, dynamic network embedding endeavors to encode nodes as lowdimensional dense representations that effectively preserve the network structures and the temporal dynamics, which is beneficial to multifarious downstream machine learning tasks. In this paper, we conduct a systematical survey on dynamic network embedding. In specific, basic concepts of dynamic network embedding are described, notably, we propose a novel taxonomy of existing dynamic network embedding techniques for the first time, including matrix factorization based, Skip-Gram based, autoencoder based, neural networks based and other embedding methods. Additionally, we carefully summarize the commonly used datasets and a wide variety of subsequent tasks that dynamic network embedding can benefit. Afterwards and primarily, we suggest several challenges that the existing algorithms faced and outline possible directions to facilitate the future research, such as dynamic embedding models, large-scale dynamic networks, heterogeneous dynamic networks, dynamic attributed networks, task-oriented dynamic network embedding and more embedding spaces.

show abstract

Scalable Optimization for Embedding Highly-Dynamic and Recency-Sensitive Data

Cited by 7 publications

References 8 publications

GloDyNE: Global Topology Preserving Dynamic Network Embedding

GloDyNE: Global Topology Preserving Dynamic Network Embedding

Towards Robust Dynamic Network Embedding

A Survey on Dynamic Network Embedding

Contact Info

Product

Resources

About