LouvainNE

Bhowmick, Ayan Kumar; Meneni, Koushik; Danisch, Maximilien; Guillaume, Jean‐Loup; Mitra, Bivas

doi:10.1145/3336191.3371800

Cited by 30 publications

(3 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The prominent GRL frameworks used in this study are: (i) DEEPWALK [7], (ii) NODE2VEC [4], (iii) LINE [8], (iv) NETMF [79]. In addition, we consider five scalable graph embedding approaches: (v) NETSMF [15], (vi) RANDNE [18], (vii) PRONE [14], (viii) LOUVAINNE [16], (ix) VERSE [69]. For more details see the supplementary material.…”

Section: Datasetsmentioning

confidence: 99%

“…Furthermore, neural network models [6], [13] have been proposed for graphstructured data, returning outstanding performance by combining node attributes and network structure when learning embeddings. Recent studies [14] aim to alleviate the computational burden of these algorithms through matrix sparsification tools [15], hierarchical representations [16], [17], or by fast hashing schemes [18].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Hierarchical Block Distance Model for Ultra Low-Dimensional Graph Representations

Nakis,

Çelikkanat,

Lehmann

et al. 2024

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

Graph Representation Learning (GRL) has become central for characterizing structures of complex networks and performing tasks such as link prediction, node classification, network reconstruction, and community detection. Whereas numerous generative GRL models have been proposed, many approaches have prohibitive computational requirements hampering large-scale network analysis, fewer are able to explicitly account for structure emerging at multiple scales, and only a few explicitly respect important network properties such as homophily and transitivity. This paper proposes a novel scalable graph representation learning method named the Hierarchical Block Distance Model (HBDM). The HBDM imposes a multiscale block structure akin to stochastic block modeling (SBM) and accounts for homophily and transitivity by accurately approximating the latent distance model (LDM) throughout the inferred hierarchy. The HBDM naturally accommodates unipartite, directed, and bipartite networks whereas the hierarchy is designed to ensure linearithmic time and space complexity enabling the analysis of very large-scale networks. We evaluate the performance of the HBDM on massive networks consisting of millions of nodes. Importantly, we find that the proposed HBDM framework significantly outperforms recent scalable approaches in all considered downstream tasks. Surprisingly, we observe superior performance even imposing ultra-low two-dimensional embeddings facilitating accurate direct and hierarchical-aware network visualization and interpretation.

show abstract

Section: Datasetsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Hierarchical Block Distance Model for Ultra Low-Dimensional Graph Representations

Nakis,

Çelikkanat,

Lehmann

et al. 2024

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

show abstract

“…The early works relied either on random walks (Perozzi, Al-Rfou, and Skiena 2014;Grover and Leskovec 2016;Tang et al 2015) or matrix factorization techniques (Qiu et al 2018(Qiu et al , 2019. In recent years, Graph Neural Network (GNN) architectures have become a prominent way to address network embedding problems (Wu et al 2021), and a plethora of methods have also been developed to address a variety of network types, such as signed networks (Li et al 2020;Nakis et al 2023) and knowledge graphs (Dai et al 2020), or to serve diverse purposes like encoding the hierarchical structure of networks in learning node embeddings (Bhowmick et al 2020;Nakis et al 2022).…”

Section: Introductionmentioning

confidence: 99%

Continuous-Time Graph Representation with Sequential Survival Process

Çelikkanat,

Nakis,

Mørup

2024

AAAI

View full text Add to dashboard Cite

Over the past two decades, there has been a tremendous increase in the growth of representation learning methods for graphs, with numerous applications across various fields, including bioinformatics, chemistry, and the social sciences. However, current dynamic network approaches focus on discrete-time networks or treat links in continuous-time networks as instantaneous events. Therefore, these approaches have limitations in capturing the persistence or absence of links that continuously emerge and disappear over time for particular durations. To address this, we propose a novel stochastic process relying on survival functions to model the durations of links and their absences over time. This forms a generic new likelihood specification explicitly accounting for intermittent edge-persistent networks, namely GraSSP: Graph Representation with Sequential Survival Process. We apply the developed framework to a recent continuous time dynamic latent distance model characterizing network dynamics in terms of a sequence of piecewise linear movements of nodes in latent space. We quantitatively assess the developed framework in various downstream tasks, such as link prediction and network completion, demonstrating that the developed modeling framework accounting for link persistence and absence well tracks the intrinsic trajectories of nodes in a latent space and captures the underlying characteristics of evolving network structure.

show abstract

SINr: Fast Computing of Sparse Interpretable Node Representations is not a Sin!

Prouteau

Connes

Dugué

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

While graph embedding aims at learning low-dimensional representations of nodes encompassing the graph topology, word embedding focus on learning word vectors that encode semantic properties of the vocabulary. The first finds applications on tasks such as link prediction and node classification while the latter is systematically considered in natural language processing. Most of the time, graph and word embeddings are considered on their own as distinct tasks. However, word co-occurrence matrices, widely used to extract word embeddings, can be seen as graphs. Furthermore, most network embedding techniques rely either on a word embedding methodology (Word2vec) or on matrix factorization, also widely used for word embedding. These methods are usually computationally expensive, parameter dependant and the dimensions of the embedding space are not interpretable. To circumvent these issues, we introduce the Lower Dimension Bipartite Graphs Framework (LDBGF) which takes advantage of the fact that all graphs can be described as bipartite graphs, even in the case of textual data. This underlying bipartite structure may be explicit, like in coauthor networks. However, with LDBGF, we focus on uncovering latent bipartite structures, lying for instance in social or word co-occurrence networks, and especially such structures providing conciser and interpretable representations of the graph at hand. We further propose SINr, an efficient implementation of the LDBGF approach that extracts Sparse Interpretable Node Representations using community structure to approximate the underlying bipartite structure. In the case of graph embedding, our near-linear time method is the fastest of our benchmark, parameter-free and provides state-ofthe-art results on the classical link prediction task. We also show that

show abstract

LouvainNE

Cited by 30 publications

References 37 publications

A Hierarchical Block Distance Model for Ultra Low-Dimensional Graph Representations

A Hierarchical Block Distance Model for Ultra Low-Dimensional Graph Representations

Continuous-Time Graph Representation with Sequential Survival Process

SINr: Fast Computing of Sparse Interpretable Node Representations is not a Sin!

Contact Info

Product

Resources

About