Mell

Matsuno, Ryuta; Murata, Tsuyoshi

doi:10.1145/3184558.3191565

Cited by 37 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An important aspect of multiplex embeddings is that they can improve link prediction in the individual layers compared to the case where the layers are embedded independently, cf. [50]. Further, they could potentially lead to improved multidimensional community detection on a geometric basis and yield more realistic multilayer greedy routing success rates [14], as they are expected to better capture the relation between the layers.…”

Section: Discussionmentioning

confidence: 99%

Link persistence and conditional distances in multiplex networks

Papadopoulos

Kleineberg

2019

Phys. Rev. E

View full text Add to dashboard Cite

Recent progress towards unraveling the hidden geometric organization of real multiplexes revealed significant correlations across the hyperbolic node coordinates in different network layers, which facilitated applications like trans-layer link prediction and mutual navigation. But are geometric correlations alone sufficient to explain the topological relation between the layers of real systems? Here we provide the negative answer to this question. We show that connections in real systems tend to persist from one layer to another irrespectively of their hyperbolic distances. This suggests that in addition to purely geometric aspects the explicit link formation process in one layer impacts the topology of other layers. Based on this finding, we present a simple modification to the recently developed Geometric Multiplex Model to account for this effect, and show that the extended model can reproduce the behavior observed in real systems. We also find that link persistence is significant in all considered multiplexes and can explain their layers' high edge overlap, which cannot be explained by coordinate correlations alone. Furthermore, by taking both link persistence and hyperbolic distance correlations into account we can improve trans-layer link prediction. These findings guide the development of multiplex embedding methods, suggesting that such methods should be accounting for both coordinate correlations and link persistence across layers.A first step towards this direction is the finding that if the layers comprising real multiplexes are independently embedded into hyperbolic spaces, their coordinates exhibit significant correlations [14]. This finding motivated new applications, like multidimensional community de-1 2β r , gives the power law degree distribution, P (k) ≈ ρ(r(k))|r (k)| ∝ k −γ , γ = 1 + 1/β > 2. Without loss of generality, we assume here a hyperbolic plane of curvature K = −1. See [2] for further details.

show abstract

Section: Discussionmentioning

confidence: 99%

Link persistence and conditional distances in multiplex networks

Papadopoulos

Kleineberg

2019

Phys. Rev. E

View full text Add to dashboard Cite

show abstract

“…Since these methods optimize the embeddings on local patches, it becomes difficult to extract global information. Another line of work uses consensus embeddings to encode information of multiple dimensions [18], [19], [20].…”

Section: Context and Background Informationmentioning

confidence: 99%

“…This results in a consensus embedding for each node. MELL [20] follows a similar approach, but for directed multiplex graphs. It uses two embedding vectors for each node: one as a head vector and another as a tail vector.…”

Section: Sharing Information With Regularizationmentioning

confidence: 99%

Hierarchical Aggregations for High-Dimensional Multiplex Graph Embedding

Abdous

Mrabah

Bouguessa

2024

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

We investigate the problem of multiplex graph embedding, that is, graphs in which nodes interact through multiple types of relations (dimensions). In recent years, several methods have been developed to address this problem. However, the need for more effective and specialized approaches grows with the production of graph data with diverse characteristics. In particular, real-world multiplex graphs may exhibit a high number of dimensions, making it difficult to construct a single consensus representation. Furthermore, important information can be hidden in complex latent structures scattered in multiple dimensions. To address these issues, we propose HMGE, a novel embedding method based on hierarchical aggregation for high-dimensional multiplex graphs. Hierarchical aggregation consists in learning a hierarchical combination of the graph dimensions and refining the embeddings at each hierarchy level. Non-linear combinations are computed from previous ones, thus uncovering complex information and latent structures hidden in the multiplex graph dimensions. Moreover, we leverage mutual information maximization between local patches and global summaries to train the model without supervision. This allows to captures globally relevant information present in diverse locations of the graph. Detailed experiments on synthetic and real-world data illustrate the suitability of our approach on downstream supervised tasks, including link prediction and node classification.

show abstract

“…PMNE [9], MELL [24], MVE [8], and MNE [25] are the earlier works for multiplex graph representation learning. These methods are designed utilising different strategies to capture the intra-relation and inter-relation information.…”

Section: Multilayer Network Embeddingmentioning

confidence: 99%

CoLM²S: Contrastive self‐supervised learning on attributed multiplex graph network with multi‐scale information

Han

Wei

Wang

et al. 2023

CAAI Trans on Intel Tech

View full text Add to dashboard Cite

Contrastive self‐supervised representation learning on attributed graph networks with Graph Neural Networks has attracted considerable research interest recently. However, there are still two challenges. First, most of the real‐word system are multiple relations, where entities are linked by different types of relations, and each relation is a view of the graph network. Second, the rich multi‐scale information (structure‐level and feature‐level) of the graph network can be seen as self‐supervised signals, which are not fully exploited. A novel contrastive self‐supervised representation learning framework on attributed multiplex graph networks with multi‐scale (named CoLM2S) information is presented in this study. It mainly contains two components: intra‐relation contrast learning and inter‐relation contrastive learning. Specifically, the contrastive self‐supervised representation learning framework on attributed single‐layer graph networks with multi‐scale information (CoLMS) framework with the graph convolutional network as encoder to capture the intra‐relation information with multi‐scale structure‐level and feature‐level self‐supervised signals is introduced first. The structure‐level information includes the edge structure and sub‐graph structure, and the feature‐level information represents the output of different graph convolutional layer. Second, according to the consensus assumption among inter‐relations, the CoLM2S framework is proposed to jointly learn various graph relations in attributed multiplex graph network to achieve global consensus node embedding. The proposed method can fully distil the graph information. Extensive experiments on unsupervised node clustering and graph visualisation tasks demonstrate the effectiveness of our methods, and it outperforms existing competitive baselines.

show abstract

Mell

Cited by 37 publications

References 13 publications

Link persistence and conditional distances in multiplex networks

Link persistence and conditional distances in multiplex networks

Hierarchical Aggregations for High-Dimensional Multiplex Graph Embedding

CoLM²S: Contrastive self‐supervised learning on attributed multiplex graph network with multi‐scale information

Contact Info

Product

Resources

About

Mell

Cited by 37 publications

References 13 publications

Link persistence and conditional distances in multiplex networks

Link persistence and conditional distances in multiplex networks

Hierarchical Aggregations for High-Dimensional Multiplex Graph Embedding

CoLM2S: Contrastive self‐supervised learning on attributed multiplex graph network with multi‐scale information

Contact Info

Product

Resources

About

CoLM²S: Contrastive self‐supervised learning on attributed multiplex graph network with multi‐scale information