Learning Community Embedding with Community Detection and Node Embedding on Graphs

Cavallari, Sandro; Zheng, Vincent W.; Cai, Hongyun; Chang, Kevin Chen-Chuan; Wang, Zhaoxia

doi:10.1145/3132847.3132925

Cited by 301 publications

(186 citation statements)

References 25 publications

Supporting

Mentioning

169

Contrasting

Unclassified

Order By: Relevance

“…In the current literature, the graph embedding problem has also been investigated to specifically preserve community structures in a graph [9], [10]. These hybrid techniques combine the objectives of both node embedding learning and community detection.…”

Section: Related Work a Graph Embeddingmentioning

confidence: 99%

“…The latter is another community detection method [27], which is applied jointly with spectral optimization of modularity to learn node embeddings [10]. The Gausian mixture model (GMM) is a statistical inference-based community detection method [28], which can be used jointly with a conventional node representation learning (e.g., Deepwalk [2] and SDNE [29]) to perform graph embedding [9]. It is worth noting that GMM by itself explicitly learns the "random mixtures over latent communities variables" [28] (i.e., node embeddings) but suffers from a large number of parameters and does not take into account the low-order proximity of the nodes when generating the graph embeddings.…”

Section: B Community Detection For Graph Embeddingmentioning

confidence: 99%

“…In the current literature, the graph embedding problem has also been investigated to specifically preserve community structures in a graph by applying hybrid approaches [9], [10].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Bridging the Gap between Community and Node Representations: Graph Embedding via Community Detection

Lutov

Yang

Cudré-Mauroux

2019

2019 IEEE International Conference on Big Data (Big Data)

View full text Add to dashboard Cite

Graph embedding has become a key component of many data mining and analysis systems. Current graph embedding approaches either sample a large number of node pairs from a graph to learn node embeddings via stochastic optimization or factorize a high-order node proximity/adjacency matrix via computationally intensive matrix factorization techniques. These approaches typically require significant resources for the learning process and rely on multiple parameters, which limits their applicability in practice. Moreover, most of the existing graph embedding techniques operate effectively in one specific metric space only (e.g., the one produced with cosine similarity), do not preserve higher-order structural features of the input graph and cannot automatically determine a meaningful number of dimensions for the embedding space. Typically, the produced embeddings are not easily interpretable, which complicates further analyses and limits their applicability. To address these issues, we propose DAOR, a highly efficient and parameter-free graph embedding technique producing metric space-robust, compact and interpretable embeddings without any manual tuning. Compared to a dozen state-of-the-art graph embedding algorithms, DAOR yields competitive results on both node classification (which benefits form high-order proximity) and link prediction (which relies on low-order proximity mostly). Unlike existing techniques, however, DAOR does not require any parameter tuning and improves the embeddings generation speed by several orders of magnitude. Our approach has hence the ambition to greatly simplify and speed up data analysis tasks involving graph representation learning.Index Terms-parameter-free graph embedding, unsupervised learning of network representation, automatic feature extraction, interpretable embeddings, scalable graph embedding.

show abstract

Section: Related Work a Graph Embeddingmentioning

confidence: 99%

Section: B Community Detection For Graph Embeddingmentioning

confidence: 99%

See 1 more Smart Citation

Bridging the Gap between Community and Node Representations: Graph Embedding via Community Detection

Lutov

Yang

Cudré-Mauroux

2019

2019 IEEE International Conference on Big Data (Big Data)

View full text Add to dashboard Cite

show abstract

“…The proposed latent group discovery is related to community detection [1] that identifies groups of densely connected nodes in a graph. However, those methods [13] explicitly require proximity information among the nodes for discovering latent communities, and they are inapplicable in the case when the link information is not available.…”

Section: Community Detectionmentioning

confidence: 99%

DBRec

Wen

Zhong

et al. 2019

Proceedings of the 28th ACM International Conference on Information and Knowledge Management

View full text Add to dashboard Cite

In recommender systems, the user-item interaction data is usually sparse and not sufficient for learning comprehensive user/item representations for recommendation. To address this problem, we propose a novel dual-bridging recommendation model (DBRec). DBRec performs latent user/item group discovery simultaneously with collaborative filtering, and interacts group information with users/items for bridging similar users/items. Therefore, a user's preference over an unobserved item, in DBRec, can be bridged by the users within the same group who have rated the item, or the user-rated items that share the same group with the unobserved item. In addition, we propose to jointly learn user-user group (itemitem group) hierarchies, so that we can effectively discover latent groups and learn compact user/item representations. We jointly integrate collaborative filtering, latent group discovering and hierarchical modelling into a unified framework, so that all the model parameters can be learned toward the optimization of the objective function. We validate the effectiveness of the proposed model with two real datasets, and demonstrate its advantage over the state-ofthe-art recommendation models with extensive experiments.

show abstract

“…However, adding these potentially high-degree nodes to the network can substantially change the topological structure of the network, leading to an inaccurate estimation of the embedding space. Other methods aim at embedding densely connected subnetworks: ComE performs community embedding and community detection simultaneously using a community-aware high-order proximity [29] . PathEmb models pathways as documents and then applies document embedding models to calculate pathway similarity [30] .…”

Section: Introductionmentioning

confidence: 99%

GRep: Gene Set Representation via Gaussian Embedding

Wang

Flynn

Altman

2019

Preprint

View full text Add to dashboard Cite

Molecular interaction networks are our basis for understanding functional interdependencies among genes. Network embedding approaches analyze these complicated networks by representing genes as low-dimensional vectors based on the network topology. These low-dimensional vectors have recently become the building blocks for a larger number of systems biology applications. Despite the success of embedding genes in this way, it remains unclear how to effectively represent gene sets, such as protein complexes and signaling pathways. The direct adaptation of existing gene embedding approaches to gene sets cannot model the diverse functions of genes in a set. Here, we propose GRep, a novel gene set embedding approach, which represents each gene set as a multivariate Gaussian distribution rather than a single point in the low-dimensional space. The diversity of genes in a set, or the uncertainty of their contribution to a particular function, is modeled by the covariance matrix of the multivariate Gaussian distribution. By doing so, GRep produces a highly informative and compact gene set representation. Using our representation, we analyze two major pharmacogenomics studies and observe substantial improvement in drug target identification from expression-derived gene sets. Overall, the GRep framework provides a novel representation of gene sets that can be used as input features to off-the-shelf machine learning classifiers for gene set analysis.

show abstract

Learning Community Embedding with Community Detection and Node Embedding on Graphs

Cited by 301 publications

References 25 publications

Bridging the Gap between Community and Node Representations: Graph Embedding via Community Detection

Bridging the Gap between Community and Node Representations: Graph Embedding via Community Detection

DBRec

GRep: Gene Set Representation via Gaussian Embedding

Contact Info

Product

Resources

About