Continuous-Time Relationship Prediction in Dynamic Heterogeneous Information Networks

Sajadmanesh, Sina; Bazargani, Sogol; Zhang, Jiawei; Rabiee, Hamid R.

doi:10.1145/3333028

Cited by 17 publications

(9 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other recent algorithms such as DDNE [30], DANE [29], DynGem [18], Zhu et al [52], and Rahman et al [40] learn embeddings from a sequence of graph snapshots, which is not applicable to our setting of continuous interaction data. Recent models such as NP-GLM model [41], DGNN [33], and DyRep [44] learn embeddings from persistent links between nodes, which do not exist in interaction networks as the edges represent instantaneous interactions. Our proposed model, JODIE overcomes these shortcomings by generating dynamic user and item embeddings.…”

Section: Related Workmentioning

confidence: 99%

Learning Dynamic Embeddings from Temporal Interactions

Kumar,

Zhang,

Leskovec

2018

Preprint

View full text Add to dashboard Cite

Modeling a sequence of interactions between users and items (e.g., products, posts, or courses) is crucial in domains such as e-commerce, social networking, and education to predict future interactions. Representation learning presents an attractive solution to model the dynamic evolution of user and item properties, where each user/item can be embedded in a euclidean space and its evolution can be modeled by dynamic changes in its embedding. However, existing embedding methods either generate static embeddings, treat users and items independently, or are not scalable.Here we propose JODIE, a coupled recurrent model to jointly learn the dynamic embeddings of users and items from a sequence of user-item interactions. JODIE has three components. First, the update component updates the user and item embedding from each interaction using their previous embeddings with the two mutuallyrecursive Recurrent Neural Networks. Second, a novel projection component is trained to forecast the embedding of users at any future time. Finally, the prediction component directly predicts the embedding of the item in a future interaction. For models that learn from a sequence of interactions, traditional batching of training data can not be done due to complex user-user dependencies. Therefore, we present a novel batching algorithm called t-Batch that generates time-consistent batches that can be run in parallel, leading to massive speed-up.We conduct six experiments to validate JODIE on two prediction tasks-future interaction prediction and state change predictionusing four real-world datasets. We show that JODIE outperforms six state-of-the-art algorithms in these tasks by up to 22.4%. Moreover, we show that JODIE is highly scalable and up to 9.2× faster than comparable models. As an additional experiment, we illustrate that JODIE can predict student drop-out from courses up to five interactions in advance.

show abstract

Section: Related Workmentioning

confidence: 99%

Learning Dynamic Embeddings from Temporal Interactions

Kumar,

Zhang,

Leskovec

2018

Preprint

View full text Add to dashboard Cite

show abstract

“…Embedding (DHENE) HA-LSTM [17] multiple single Yes change2vec [1] multiple multiple Yes NP-GLM [26] multiple multiple Yes DHNE [38] multiple multiple Yes…”

Section: Dynamic Heterogeneous Networkmentioning

confidence: 99%

“…There exists four dynamic heterogeneous network embedding methods, Meta-DynaMix [21], change2vec [1], DHNE [38] and NP-GLM [26]. Here, we mainly focus on DHNE and NP-GLM method.…”

Section: Baselinesmentioning

confidence: 99%

“…The above two methods both focus on short-term evolutionary information between adjacent snapshots of dynamic networks and thus become insufficient to capture longterm evolutionary patterns. More recently, Sajadmanesh et al [26] uses a recurrent neural network model to learn long-term evolutionary patterns of dynamic networks on top of metapath-based models and proposes a non-parametric generalized linear model, NP-GLM, to predict continuous-time relationships. Yin et al [38] propose a DHNE method, which learns both the historical and current heterogeneous information and models evolutionary patterns by constructing comprehensive historical-current networks based on consecutive snapshots.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Modeling Dynamic Heterogeneous Network for Link Prediction using Hierarchical Attention with Temporal RNN

Xue

Yang

Wen

et al. 2020

Preprint

View full text Add to dashboard Cite

Network embedding aims to learn low-dimensional representations of nodes while capturing structure information of networks. It has achieved great success on many tasks of network analysis such as link prediction and node classification. Most of existing network embedding algorithms focus on how to learn static homogeneous networks effectively. However, networks in the real world are more complex, e.g., networks may consist of several types of nodes and edges (called heterogeneous information) and may vary over time in terms of dynamic nodes and edges (called evolutionary patterns). Limited work has been done for network embedding of dynamic heterogeneous networks as it is challenging to learn both evolutionary and heterogeneous information simultaneously. In this paper, we propose a novel dynamic heterogeneous network embedding method, termed as DyHATR, which uses hierarchical attention to learn heterogeneous information and incorporates recurrent neural networks with temporal attention to capture evolutionary patterns. We benchmark our method on four real-world datasets for the task of link prediction. Experimental results show that DyHATR significantly outperforms several state-of-the-art baselines.

show abstract

“…Networks of interest can be social, biological, informational, or technological. Link prediction is the task of identifying links missing from a network ( Lü & Zhou, 2011 ; Martínez, Berzal & Cubero, 2017 ; Guimerà & Sales-Pardo, 2009 ; Al Hasan et al, 2006 ; Guimerà & Sales-Pardo, 2009 ; Clauset, Moore & Newman, 2008 ; Lü & Zhou, 2011 ; Cannistraci, Alanis-Lobato & Ravasi, 2013 ; Daminelli et al, 2015 ; Al Hasan et al, 2006 ; Wang, Satuluri & Parthasarathy, 2007 ; Zhang et al, 2020 ; Beigi, Tang & Liu, 2020 ; Sajadmanesh et al, 2019 ; Makarov et al, 2019 ), a problem with important applications, such as the reconstruction of networks from partial observations ( Guimerà & Sales-Pardo, 2009 ), recommendation of items in online shops and friends in social networks ( Al Hasan et al, 2006 ), and the prediction of interactions in biological networks ( Clauset, Moore & Newman, 2008 ).…”

Section: Introductionmentioning

confidence: 99%

LinkPred: a high performance library for link prediction in complex networks

Kerrache

2021

PeerJ Computer Science

View full text Add to dashboard Cite

The problem of determining the likelihood of the existence of a link between two nodes in a network is called link prediction. This is made possible thanks to the existence of a topological structure in most real-life networks. In other words, the topologies of networked systems such as the World Wide Web, the Internet, metabolic networks, and human society are far from random, which implies that partial observations of these networks can be used to infer information about undiscovered interactions. Significant research efforts have been invested into the development of link prediction algorithms, and some researchers have made the implementation of their methods available to the research community. These implementations, however, are often written in different languages and use different modalities of interaction with the user, which hinders their effective use. This paper introduces LinkPred, a high-performance parallel and distributed link prediction library that includes the implementation of the major link prediction algorithms available in the literature. The library can handle networks with up to millions of nodes and edges and offers a unified interface that facilitates the use and comparison of link prediction algorithms by researchers as well as practitioners.

show abstract

Continuous-Time Relationship Prediction in Dynamic Heterogeneous Information Networks

Cited by 17 publications

References 41 publications

Learning Dynamic Embeddings from Temporal Interactions

Learning Dynamic Embeddings from Temporal Interactions

Modeling Dynamic Heterogeneous Network for Link Prediction using Hierarchical Attention with Temporal RNN

LinkPred: a high performance library for link prediction in complex networks

Contact Info

Product

Resources

About