High-order Proximity Preserved Embedding For Dynamic Networks

Zhu, Dingyuan; Cui, Peng; Zhang, Ziwei; Pei, Jian; Zhu, Wenwu

doi:10.1109/tkde.2018.2822283

Cited by 103 publications

(68 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dynamic triad algorithm [56] considered the addition of a third edge among three nodes in the graph (dynamic triad closure) to capture network dynamics over time and learn from one time point to the next. Other temporal representations include the application of generalized singular value decomposition to consecutive time steps [57] and the use of node attribute Node Embedding over Temporal Graphs , , similarity to optimize representation over time [26]. Recent surveys provide good summaries and additional details [7,12,15].…”

Section: Related Workmentioning

confidence: 99%

Node Embedding over Temporal Graphs

Singer

Guy

Radinsky

2019

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence

117

View full text Add to dashboard Cite

In this work, we present a method for node embedding in temporal graphs. We propose an algorithm that learns the evolution of a temporal graph's nodes and edges over time and incorporates this dynamics in a temporal node embedding framework for different graph prediction tasks. We present a joint loss function that creates a temporal embedding of a node by learning to combine its historical temporal embeddings, such that it optimizes per given task (e.g., link prediction). The algorithm is initialized using static node embeddings, which are then aligned over the representations of a node at different time points, and eventually adapted for the given task in a joint optimization. We evaluate the effectiveness of our approach over a variety of temporal graphs for the two fundamental tasks of temporal link prediction and multi-label node classification, comparing to competitive baselines and algorithmic alternatives. Our algorithm shows performance improvements across many of the datasets and baselines and is found particularly effective for graphs that are less cohesive, with a lower clustering coefficient.

show abstract

Section: Related Workmentioning

confidence: 99%

Node Embedding over Temporal Graphs

Singer

Guy

Radinsky

2019

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence

117

View full text Add to dashboard Cite

show abstract

“…However, all the aforementioned methods only focus on static network embedding. There are some attempts in temporal network embedding, which can be broadly classified into two categories: embedding snapshot networks [6,8,14,34,35] and modeling temporal evolution [19,26,37]. The basic idea of the former is to learn node embedding for each network snapshot.…”

Section: Related Workmentioning

confidence: 99%

“…The basic idea of the former is to learn node embedding for each network snapshot. Specifically, DANE [14] and DHPE [35] present efficient algorithms based on perturbation theory. Song et al extend skip-gram based models and propose a dynamic network embedding framework [6].…”

Section: Related Workmentioning

confidence: 99%

Temporal Network Embedding with Micro- and Macro-dynamics

Wang

Shi

et al. 2019

Proceedings of the 28th ACM International Conference on Information and Knowledge Management

View full text Add to dashboard Cite

Network embedding aims to embed nodes into a low-dimensional space, while capturing the network structures and properties. Although quite a few promising network embedding methods have been proposed, most of them focus on static networks. In fact, temporal networks, which usually evolve over time in terms of microscopic and macroscopic dynamics, are ubiquitous. The microdynamics describe the formation process of network structures in a detailed manner, while the macro-dynamics refer to the evolution pattern of the network scale. Both micro-and macro-dynamics are the key factors to network evolution; however, how to elegantly capture both of them for temporal network embedding, especially macro-dynamics, has not yet been well studied. In this paper, we propose a novel temporal network embedding method with micro-and macro-dynamics, named M 2 DNE. Specifically, for micro-dynamics, we regard the establishments of edges as the occurrences of chronological events and propose a temporal attention point process to capture the formation process of network structures in a fine-grained manner. For macro-dynamics, we define a general dynamics equation parameterized with network embeddings to capture the inherent evolution pattern and impose constraints in a higher structural level on network embeddings. Mutual evolutions of micro-and macro-dynamics in a temporal network alternately affect the process of learning node embeddings. Extensive experiments on three real-world temporal networks demonstrate that M 2 DNE significantly outperforms the state-of-the-arts not only in traditional tasks, e.g., network reconstruction, but also in temporal tendency-related tasks, e.g., scale prediction. Definition 3.3. Macro-dynamics. Given a temporal network G = (V, E, T ), macro-dynamics refer to the evolution process of the network scale, denoted as A = {e(t)} | T | t =t 1 , where e(t) is the cumulative number of edges by time t.

show abstract

“…All of them are publicly available and have been widely used in previous research of both static and dynamic graph representation learning. For instance, Blog dataset have been used in [2,8,16,[18][19][20]28], Flickr dataset in [6,8,[18][19][20]28], Cora dataset in [2,6,8]. • Blog was collected from the BlogCatalog website, which manages bloggers and their posted blogs.…”

Section: Data Setsmentioning

confidence: 99%

Real-Time Streaming Graph Embedding Through Local Actions

Liu¹,

Hsieh²,

Duffield³

et al. 2019

Companion Proceedings of the 2019 World Wide Web Conference

View full text Add to dashboard Cite

Recently, considerable research attention has been paid to network embedding, a popular approach to construct feature vectors of vertices in latent space. Due to the curse of dimensionality and sparsity in graphical datasets, this approach has become indispensable for machine learning tasks over large networks. The majority of existing literature has considered this technique under the assumption that the network is static. However, networks in many applications, including social networks, collaboration networks, and recommender systems, nodes and edges accrue to a growing network as a streaming. Moreover, high-throughput production machine learning systems require to promptly generate representations for new vertices. A small number of very recent results have address the problem of embedding for dynamic networks. However, they either rely on knowledge of vertex attributes, suffer high-time complexity, or need to be re-trained without closed-form expression. Thus the approach of adapting of the existing methods designed for static networks or dynamic networks to the streaming environment faces non-trivial technical challenges.These challenges motivate developing new approaches to the problems of streaming network embedding. In this paper We propose a new framework that is able to generate latent features for new vertices with high efficiency and low complexity under specified iteration rounds. We formulate a constrained optimization problem for the modification of the representation resulting from a stream arrival. We show this problem has no closed-form solution and instead develop an online approximation solution. Our solution follows three steps: (1) identify vertices affected by newly arrived ones, (2) generating latent features for new vertices, and (3) updating the latent features of the most affected vertices. The generated representations are provably feasible and not far from the optimal ones in terms of expectation. Multi-class classification and clustering on five real-world networks demonstrate that our model can efficiently update vertex representations and simultaneously achieve comparable or even better performance compared with model retraining.

show abstract

High-order Proximity Preserved Embedding For Dynamic Networks

Cited by 103 publications

References 21 publications

Node Embedding over Temporal Graphs

Node Embedding over Temporal Graphs

Temporal Network Embedding with Micro- and Macro-dynamics

Real-Time Streaming Graph Embedding Through Local Actions

Contact Info

Product

Resources

About