A Deep Learning Approach to Link Prediction in Dynamic Networks

Li, X.; Du, Nan; Li, H.; Li, K.; Gao, Jing; Zhang, A.

doi:10.1137/1.9781611973440.33

Cited by 127 publications

(86 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, for both node and edge based prediction tasks, there is a body of recent work for supervised feature learning based on existing and novel graph-specific deep network architectures [15, 16, 17, 31, 39]. These architectures directly minimize the loss function for a downstream prediction task using several layers of non-linear transformations which results in high accuracy, but at the cost of scalability due to high training time requirements.…”

Section: Related Workmentioning

confidence: 99%

node2vec

Grover

Leskovec

2016

Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

7,696

977

View full text Add to dashboard Cite

Prediction tasks over nodes and edges in networks require careful effort in engineering features used by learning algorithms. Recent research in the broader field of representation learning has led to significant progress in automating prediction by learning the features themselves. However, present feature learning approaches are not expressive enough to capture the diversity of connectivity patterns observed in networks. Here we propose node2vec, an algorithmic framework for learning continuous feature representations for nodes in networks. In node2vec, we learn a mapping of nodes to a low-dimensional space of features that maximizes the likelihood of preserving network neighborhoods of nodes. We define a flexible notion of a node’s network neighborhood and design a biased random walk procedure, which efficiently explores diverse neighborhoods. Our algorithm generalizes prior work which is based on rigid notions of network neighborhoods, and we argue that the added flexibility in exploring neighborhoods is the key to learning richer representations. We demonstrate the efficacy of node2vec over existing state-of-the-art techniques on multi-label classification and link prediction in several real-world networks from diverse domains. Taken together, our work represents a new way for efficiently learning state-of-the-art task-independent representations in complex networks.

show abstract

Section: Related Workmentioning

confidence: 99%

node2vec

Grover

Leskovec

2016

Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

7,696

977

View full text Add to dashboard Cite

show abstract

“…• To test the correctness, we compare our optimal setting (i.e., τ =1, α=0.5) of the explicit social influence function with its different forms such as: 1) without temporal smoothing component i.e., η u t = 1 |F u t | m∈F u t p s t ≤ s t (u, m) , and 2) replacing our function by the social influence function in the ctRBM [12], this becomes the aforementioned SctRBM. Figure 6b shows that either the SRBM without temporal smoothing or the SctRBM have significant lower prediction accuracies compared with the SRBM with optimal setting.…”

Section: Methodsmentioning

confidence: 99%

“…However, it cannot capture the social influences on individual behaviors in the multiple agent scenario. Li et al [12] proposed a ctRBM model for link prediction in dynamic networks. The ctRBM simulates the social influences by adding the prediction expectations of local neighbors on an individual into a dynamic bias.…”

Section: The Rbms and Related Workmentioning

confidence: 99%

Social Restricted Boltzmann Machine

Phan

Dou

Piniewski³

et al. 2015

Proceedings of the 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining 2015

View full text Add to dashboard Cite

Modeling and predicting human behaviors, such as the activity level and intensity, is the key to prevent the cascades of obesity, and help spread wellness and healthy behavior in a social network. The user diversity, dynamic behaviors, and hidden social influences make the problem more challenging. In this work, we propose a deep learning model named Social Restricted Boltzmann Machine (SRBM) for human behavior modeling and prediction in health social networks. In the proposed SRBM model, we naturally incorporate self-motivation, implicit and explicit social influences, and environmental events together into three layers which are historical, visible, and hidden layers. The interactions among these behavior determinants are naturally simulated through parameters connecting these layers together. The contrastive divergence and back-propagation algorithms are employed for training the model. A comprehensive experiment on real and synthetic data has shown the great effectiveness of our deep learning model compared with conventional methods.

show abstract

“…The structural link prediction problem, which only considers a single network structure as the input, predicts the possible unobserved links within the same network [Liben-Nowell and Kleinberg, 2007;Lichtenwalter et al, 2010]. Temporal link prediction models, on the other hand, analyze the evolution pattern of a sequence of networks over time [Sarkar et al, 2012;Dunlavy et al, 2011;Li et al, 2014;Zhu et al, 2016;Rahman and Al Hasan, 2016]. The probabilistic nonparametric link prediction model can be used to predict the linkage possibility of two nodes only based on the similarity of their local neighborhoods [Sarkar et al, 2012].…”

Section: Related Workmentioning

confidence: 99%

Link Prediction with Spatial and Temporal Consistency in Dynamic Networks

Cheng

Aggarwal³

et al. 2017

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

View full text Add to dashboard Cite

Dynamic networks are ubiquitous. Link prediction in dynamic networks has attracted tremendous research interests. Many models have been developed to predict links that may emerge in the immediate future from the past evolution of the networks. There are two key factors: 1) a node is more likely to form a link in the near future with another node within its close proximity, rather than with a random node; 2) a dynamic network usually evolves smoothly. Existing approaches seldom unify these two factors to strive for the spatial and temporal consistency in a dynamic network. To address this limitation, in this paper, we propose a link prediction model with spatial and temporal consistency (LIST), to predict links in a sequence of networks over time. LIST characterizes the network dynamics as a function of time, which integrates the spatial topology of network at each timestamp and the temporal network evolution. Comparing to existing approaches, LIST has two advantages: 1) LIST uses a generic model to express the network structure as a function of time, which makes it also suitable for a wide variety of temporal network analysis problems beyond the focus of this paper; 2) by retaining the spatial and temporal consistency, LIST yields better prediction performance. Extensive experiments on four real datasets demonstrate the effectiveness of the LIST model.

show abstract

A Deep Learning Approach to Link Prediction in Dynamic Networks

Cited by 127 publications

References 13 publications

node2vec

node2vec

Social Restricted Boltzmann Machine

Link Prediction with Spatial and Temporal Consistency in Dynamic Networks

Contact Info

Product

Resources

About