Title: Learning embeddings for multiplex networks using triplet loss
Learning low-dimensional representations of graphs has facilitated the use of traditional machine learning techniques to solving classic network analysis tasks such as link prediction, node classification, community detection, etc. However, to date, the vast majority of these learning tasks are focused on traditional single-layer/unimodal networks and largely ignore the case of multiplex networks. A multiplex network is a suitable structure to model multi-dimensional real-world complex systems. It consists of multiple layers where each layer represents a different relationship among the network nodes. In this work, we propose MUNEM, a novel approach for learning a low-dimensional representation of a multiplex network using a triplet loss objective function. In our approach, we preserve the global structure of each layer, while at the same time fusing knowledge among different layers during the learning process. We evaluate the effectiveness of our proposed method by testing and comparing on real-world multiplex networks from different domains, such as collaboration network, protein-protein interaction network, online social network. Finally, in order to deliberately examine the effect of our model’s parameters we conduct extensive experiments on synthetic multiplex networks.  more » « less
Award ID(s):
1739413
PAR ID:
10205844
Author(s) / Creator(s):
Date Published:
Journal Name:
Applied network science
ISSN:
2364-8228
Subject(s) / Keyword(s):
Sponsoring Org:
National Science Foundation
More Like this
  1. null (Ed.)
    Multiplex networks are complex graph structures in which a set of entities are connected to each other via multiple types of relations, each relation representing a distinct layer. Such graphs are used to investigate many complex biological, social, and technological systems. In this work, we present a novel semi-supervised approach for structure-aware representation learning on multiplex networks. Our approach relies on maximizing the mutual information between local node-wise patch representations and label correlated structure-aware global graph representations to model the nodes and cluster structures jointly. Specifically, it leverages a novel cluster-aware, node-contextualized global graph summary generation strategy for effective joint-modeling of node and cluster representations across the layers of a multiplex network. Empirically, we demonstrate that the proposed architecture outperforms state-of-the-art methods in a range of tasks: classification, clustering, visualization, and similarity search on seven real-world multiplex networks for various experiment settings. 
    more » « less
  2. Many real-world networks are multilayer, with nontrivial correlations across layers. Here, we show that these correlations amplify geometry in networks. We focus on mutual clustering—a measure of the number of triangles that are present in all layers among the same triplets of nodes—and find that this clustering is abnormally high in many real-world networks, even when clustering in each individual layer is weak. We explain this unexpected phenomenon using a simple multiplex network model with latent geometry: Links that are most congruent with this geometry are the ones that persist across layers, amplifying the cross-layer triangle overlap. This result reveals a different dimension in which multilayer networks are radically distinct from their constituent layers. 
    more » « less
  3. The complex relationships in an urban environment can be captured through multiple interrelated sources of data. These relationships form multilayer networks, that are also spatially embedded in an area, could be used to identify latent patterns. In this work, we propose a low-dimensional representation learning approach that considers multiple layers of a multiplex network simultaneously and is able to encode similarities between nodes across different layers. In particular, we introduce a novel neural network architecture to jointly learn low-dimensional representations of each network node from multiple layers of a network. This process simultaneously fuses knowledge of various data sources to better capture the characteristics of the nodes. To showcase the proposed method we focus on the problem of identifying the functionality of an urban region. Using a variety of public data sources for New York City, we design a multilayer network and evaluate our approach. Our results indicate that our proposed approach can improve the accuracy of traditional approaches in an unsupervised task. 
    more » « less
  4. Abstract We introduce multi-location networks to model the real-world phenomena of nodes existing in multiple places simultaneously. A multi-location network contains a set of locations. Each location can have a different set of nodes, but nodes can be present in multiple locations at once. In contrast, a multiplex network contains a set of layers, where each layer shares the same set of nodes. By combining these two structures, a multi-location multiplex network (MLMN) enables nodes to appear in various locations and connect through multiple edge types. For example, in a species interaction MLMN, locations could correspond to continents, while layers represent different types of interactions, such as predation and competition. Some species may inhabit multiple continents, with interactions varying by location. Analyzing the evolution of MLMNs poses substantial challenges due to the complexity of integrating location and edge type. Traditional dynamic network logistic regression models often aggregate data across these structures, leading to information loss. In this paper, we extend dynamic network logistic regression to accommodate MLMNs, improving the estimation of factors driving changes in such networks. Our approach predicts node presence in each location and the formation of edges across different layers at each location. We provide theoretical guarantees for the model, including global optimality, consistency, asymptotic normality, and asymptotic efficiency of the estimated parameters. The model’s finite sample performance is evaluated through simulations. Additionally, a case study is conducted using a dataset from Equinix, a 2024 Fortune 500 company and one of the world’s largest data center operators. Our findings highlight the strong impact of location on node presence and link formation, showcasing the practical relevance of understanding multi-location structures to capture complex network dynamics. 
    more » « less
  5. null (Ed.)
    Networks have been widely used to represent the relations between objects such as academic networks and social networks, and learning embedding for networks has thus garnered plenty of research attention. Self-supervised network representation learning aims at extracting node embedding without external supervision. Recently, maximizing the mutual information between the local node embedding and the global summary (e.g. Deep Graph Infomax, or DGI for short) has shown promising results on many downstream tasks such as node classification. However, there are two major limitations of DGI. Firstly, DGI merely considers the extrinsic supervision signal (i.e., the mutual information between node embedding and global summary) while ignores the intrinsic signal (i.e., the mutual dependence between node embedding and node attributes). Secondly, nodes in a real-world network are usually connected by multiple edges with different relations, while DGI does not fully explore the various relations among nodes. To address the above-mentioned problems, we propose a novel framework, called High-order Deep Multiplex Infomax (HDMI), for learning node embedding on multiplex networks in a self-supervised way. To be more specific, we first design a joint supervision signal containing both extrinsic and intrinsic mutual information by high-order mutual information, and we propose a High- order Deep Infomax (HDI) to optimize the proposed supervision signal. Then we propose an attention based fusion module to combine node embedding from different layers of the multiplex network. Finally, we evaluate the proposed HDMI on various downstream tasks such as unsupervised clustering and supervised classification. The experimental results show that HDMI achieves state-of-the-art performance on these tasks. 
    more » « less