Temporally Factorized Network Modeling for Evolutionary Network Analysis

Yu, Wenchao; Aggarwal, Charų C.; Wang, Wei

doi:10.1145/3018661.3018669

Cited by 60 publications

(55 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As T and d are small and constant compared to |V |, in total, the time complexity of tNodeEmbed is O(|V | 2 ). The lowest time complexity among the other temporal state-of-the-art methods is of O(|V | 2 ) [10, 34,55], while the highest is of O(|V | 2 |E|) [56]. We conclude our method is at the lower bound of time complexity compared to the state-of-the-art methods.…”

Section: Time and Space Complexitymentioning

confidence: 88%

See 1 more Smart Citation

Node Embedding over Temporal Graphs

Singer

Guy

Radinsky

2019

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

120

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: Time and Space Complexitymentioning

confidence: 88%

“…Temporally Factorized Network Modeling (TFNM) [55]: this method applies factorization before collapsing, by generalizing the regular notion of matrix factorization for matrices with a third 'time' dimension. Given T adjacency matrices A 1 , .…”

Section: Baselinesmentioning

confidence: 99%

Node Embedding over Temporal Graphs

Singer

Guy

Radinsky

2019

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

120

View full text Add to dashboard Cite

show abstract

“…They take the correlation between the quasi-local similarity measures and temporal evolutions of link occurrences information into account by using NARX for multivariate time series forecasting. Yu et al developed a novel temporal matrix factorization model to explicitly represent the network as a function of time [44]. They provided results for link prediction as a specific example and showed that their model performs better than the state-of-the-art techniques.…”

Section: Related Workmentioning

confidence: 99%

Continuous-Time Relationship Prediction in Dynamic Heterogeneous Information Networks

Sajadmanesh

Bazargani

Zhang

et al. 2019

ACM Trans. Knowl. Discov. Data

View full text Add to dashboard Cite

Online social networks, World Wide Web, media and technological networks, and other types of so-called information networks are ubiquitous nowadays. These information networks are inherently heterogeneous and dynamic. They are heterogeneous as they consist of multi-typed objects and relations, and they are dynamic as they are constantly evolving over time. One of the challenging issues in such heterogeneous and dynamic environments is to forecast those relationships in the network that will appear in the future. In this paper, we try to solve the problem of continuous-time relationship prediction in dynamic and heterogeneous information networks. This implies predicting the time it takes for a relationship to appear in the future, given its features that have been extracted by considering both heterogeneity and temporal dynamics of the underlying network. To this end, we first introduce a feature extraction framework that combines the power of meta-path-based modeling and recurrent neural networks to effectively extract features suitable for relationship prediction regarding heterogeneity and dynamicity of the networks. Next, we propose a supervised non-parametric approach, called Non-Parametric Generalized Linear Model (Np-Glm), which infers the hidden underlying probability distribution of the relationship building time given its features. We then present a learning algorithm to train Np-Glm and an inference method to answer time-related queries. Extensive experiments conducted on synthetic data and three real-world datasets, namely Delicious, MovieLens, and DBLP, demonstrate the effectiveness of Np-Glm in solving continuous-time relationship prediction problem vis-à-vis competitive baselines. Sajadmanesh et al.The problem of link prediction has a long literature and is studied extensively in the last decade. Initial works on link prediction problem mostly concentrated on homogeneous networks, which are composed of single type of nodes connected by links of the same type [21,22,40]. However, many of today's networks, such as online social networks or bibliographic networks, are inherently heterogeneous, in which multiple types of nodes are interconnected using multiple types of links [31,37]. For example, a bibliographic network may contain author, paper, venue, etc. as different node types; and write, publish, cite, and so on as diverse link types that bind nodes with different types to each other. In these heterogeneous networks, the concept of a link can be generalized to a relationship, which can be constructed by combining different links with different types. For instance, the author-cite-paper relationship can be defined in a bibliographic network as a combination of author-write-paper and paper-cite-paper links. Analogously, one can generalize the link prediction to relationship prediction in heterogeneous networks which tries to predict complex relationships instead of links [34].While most of the studies on the link/relationship prediction in heterogeneous networks utilize a static snapshot of the und...

show abstract

“…He and Chen [14] propose an algorithm for dynamic community detection in temporal networks, which takes advantage of community information at previous time steps. Yu, Aggarwal, and Wang [42] present a model-based matrix factorization for link prediction and also for community prediction. However, their work uses only links for the prediction process.…”

Section: Introductionmentioning

confidence: 99%

Temporally Evolving Community Detection and Prediction in Content-Centric Networks

Appel

Cunha

Aggarwal

et al. 2019

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

In this work, we consider the problem of combining link, content and temporal analysis for community detection and prediction in evolving networks. Such temporal and content-rich networks occur in many real-life settings, such as bibliographic networks and question answering forums. Most of the work in the literature (that uses both content and structure) deals with static snapshots of networks, and they do not reflect the dynamic changes occurring over multiple snapshots. Incorporating dynamic changes in the communities into the analysis can also provide useful insights about the changes in the network such as the migration of authors across communities. In this work, we propose Chimera 1 , a shared factorization model that can simultaneously account for graph links, content, and temporal analysis. This approach works by extracting the latent semantic structure of the network in multidimensional form, but in a way that takes into account the temporal continuity of these embeddings. Such an approach simplifies temporal analysis of the underlying network by using the embedding as a surrogate. A consequence of this simplification is that it is also possible to use this temporal sequence of embeddings to predict future communities. We present experimental results illustrating the effectiveness of the approach.

show abstract

Temporally Factorized Network Modeling for Evolutionary Network Analysis

Cited by 60 publications

References 26 publications

Node Embedding over Temporal Graphs

Node Embedding over Temporal Graphs

Continuous-Time Relationship Prediction in Dynamic Heterogeneous Information Networks

Temporally Evolving Community Detection and Prediction in Content-Centric Networks

Contact Info

Product

Resources

About