Multi-Net: A Scalable Multiplex Network Embedding Framework

@inproceedings{Bagavathi2018MultiNetAS,
  title={Multi-Net: A Scalable Multiplex Network Embedding Framework},
  author={Arunkumar Bagavathi and Siddhartha Krishnan},
  booktitle={COMPLEX NETWORKS},
  year={2018}
}
Representation learning of networks has witnessed significant progress in recent times. Such representations have been effectively used for classic network-based machine learning tasks like node classification, link prediction, and network alignment. However, very few methods focus on capturing representations for multiplex or multilayer networks, which are more accurate and detailed representations of complex networks. In this work, we propose Multi-Net a fast and scalable embedding technique… 
Pay Attention to Relations: Multi-embeddings for Attributed Multiplex Networks
TLDR
RAHMeN is a novel unified relation-aware embedding framework for attributed heterogeneous multiplex networks that embraces the multi-faceted nature of nodes in such networks, producing a set of multi-embeddings that capture the varied and diverse contexts of nodes.
Layer Information Similarity Concerned Network Embedding
TLDR
This paper proposes a Layer Information Similarity Concerned Network Embedding (LISCNE) model considering the similarities between layers, and defines an index to formalize the similarity between different layers and the cross-network association.
Efficient Algorithms for Constructing Multiplex Networks Embedding
TLDR
This paper presents a random walkbased multilayer network embedding and compares it with single layer and multilayers network embeddings and uses severalclassic datasets usually used in network embeding experiments and alsocollected the authors' own dataset of papers and authors indexed in Scopus.
NECo: A node embedding algorithm for multiplex heterogeneous networks
TLDR
This paper evaluated the performance of NECo using genotypic and phenotypic datasets from rat (Rattus norvegicus) disease models to classify hypertension disease-related genes, and significantly outperformed the state-of-the-art node embedding methods.
NECo: A node embedding algorithm for multiplex heterogeneous networks
TLDR
This paper evaluated the performance of NECo using genotypic and phenotypic datasets from rat (Rattus norvegicus) disease models to classify hypertension disease-related genes and significantly outperformed the state-of-the-art node embedding methods.
SI-spreading-based network embedding in static and temporal networks
TLDR
This study proposes two SI-spreadingbased algorithms, SINE and TSINE, to embed static and temporal networks, respectively, and studies the effect of the sampling size, quantified as the total length of the trajectory paths, on the performance of the embedding algorithms.
Gene Embeddings of Complex network (GECo) and hypertension disease gene classification
TLDR
A network embedding algorithm named GECo is developed that can utilize multilayered heterogeneous networks of genes and phenotypes and significantly outperformed the state-of-the-art network embeddings methods in prediction.
Drug Repositioning Using Multiplex-Heterogeneous Network Embedding: A Case Study on SARS-CoV2
  • L. Pio-Lopez
  • Computer Science
    Complex Networks & Their Applications X
  • 2022
TLDR
Experimental results show that the approach is highly robust and effective for finding new drug-target associations and validated on a task of link prediction and on a case study for SARS-CoV2 drug repositioning.
Comparing Temporal Graphs Using Dynamic Time Warping
TLDR
This work defines the dynamic temporal graph warping distance (dtgw) to determine the (dis)similarity of two temporal graphs and develops an efficient heuristic which performs well in empirical studies and performs favorably in de-anonymizing networks.
Predicting Protein-Protein Interaction in Multi-layer Blood Cell PPI Networks
TLDR
It is found that multi-layer node embedding that captures inter-layer dependencies perform better than single layer algorithms applied on the multi- layer network even on a limited data set constrained by simplifying assumptions and limited computational resources.
...
1
2
...

References

SHOWING 1-10 OF 27 REFERENCES
Scalable Multiplex Network Embedding
TLDR
This paper presents a scalable multiplex network embedding model to represent information of multi-type relations into a unified embedding space, and proposes one high-dimensional common embedding and a lower-dimensional additional embedding for each type of relation.
node2vec: Scalable Feature Learning for Networks
TLDR
In node2vec, an algorithmic framework for learning continuous feature representations for nodes in networks, a flexible notion of a node's network neighborhood is defined and a biased random walk procedure is designed, which efficiently explores diverse neighborhoods.
DeepWalk: online learning of social representations
TLDR
DeepWalk is an online learning algorithm which builds useful incremental results, and is trivially parallelizable, which make it suitable for a broad class of real world applications such as network classification, and anomaly detection.
The physics of spreading processes in multilayer networks
TLDR
Progress is surveyed towards attaining a deeper understanding of spreading processes on multilayer networks, and some of the physical phenomena related to spreading processes that emerge from multilayered structure are highlighted.
Motifs in Temporal Networks
TLDR
A notion of a temporal network motif as an elementary unit of temporal networks is developed and a general methodology for counting such motifs is provided and it is found that measuring motif counts at various time scales reveals different behavior.
Supervised random walks: predicting and recommending links in social networks
TLDR
An algorithm based on Supervised Random Walks is developed that naturally combines the information from the network structure with node and edge level attributes and outperforms state-of-the-art unsupervised approaches as well as approaches that are based on feature extraction.
It's who you know: graph mining using recursive structural features
TLDR
ReFeX (Recursive Feature eXtraction), a novel algorithm, that recursively combines local features with neighborhood features; and outputs regional features -- capturing "behavioral" information in large graphs, is proposed.
Computing communities in large networks using random walks (long version)
TLDR
A measure of similarities between vertices based on random walks which captures well the community structure in a network, can be computed efficiently, and it can be used in an agglomerative algorithm to compute efficiently thecommunity structure of a network.
Higher-order organization of complex networks
TLDR
A generalized framework for clustering networks on the basis of higher-order connectivity patterns provides mathematical guarantees on the optimality of obtained clusters and scales to networks with billions of edges.
Link prediction based on local random walk
TLDR
This letter proposed a method based on local random walk, which can give competitively good or even better prediction than other random-walk–based methods while having a much lower computational complexity.
...
1
2
3
...