Network representation learning systematic review: ancestors and current development state

  title={Network representation learning systematic review: ancestors and current development state},
  author={Amina Amara and Mohamed Ali Hadj Taieb and Mohamed Benaouicha},
Real-world information networks are increasingly occurring across various disciplines including online social networks and citation networks. These network data are generally characterized by sparseness, nonlinearity and heterogeneity bringing different challenges to the network analytics task to capture inherent properties from network data. Artificial intelligence and machine learning have been recently leveraged as powerful systems to learn insights from network data and deal with presented… 
Knowledge-Based Construction of Confusion Matrices for Multi-Label Classification Algorithms using Semantic Similarity Measures
A novel approach that aligns expected labels with predicted labels in multi-label classification using ontology-driven feature-based semantic similarity measures is defined and used to develop a method for creating precise confusion matrices for a more effective evaluation of multi- label classification algorithms.


Network representation learning: a systematic literature review
This survey comprehensively presents an overview of a large number of network representation learning algorithms from two clear points of view of homogeneous network and heterogeneous network.
Network Representation Learning: A Survey
A comprehensive review of the current literature on network representation learning in the data mining and machine learning field, proposing new taxonomies to categorize and summarize the state-of-the-art network representationLearning techniques according to the underlying learning mechanisms, the network information intended to preserve, as well as the algorithmic designs and methodologies.
Representation Learning for Heterogeneous Information Networks via Embedding Events
A new NRL framework, called Event2vec, for HINs to consider both quantities and properties of relations during the representation learning process, and theoretically prove how event-driven proximities can be preserved in the embedding space by this framework.
MEgo2Vec: Embedding Matched Ego Networks for User Alignment Across Social Networks
A graph neural network is proposed to directly represent the ego networks of two users to be aligned into an embedding, based on which the alignment label is predicted, which achieves significantly better performance than the state-of-the-art comparison methods.
Heterogeneous Network Representation Learning: Survey, Benchmark, Evaluation, and Beyond
This work aims to provide a unified framework to deeply summarize and evaluate existing research on heterogeneous network embedding (HNE), and provides a generic paradigm for the systematic categorization and analysis over the merits of various existing HNE algorithms.
CRL: Collaborative Representation Learning by Coordinating Topic Modeling and Network Embeddings.
A unified model based on matrix factorization (MF), named collaborative representation learning (CRL), which considers complementary global and local information simultaneously and models topics and learns network embeddings collaboratively and incorporates the Fletcher-Reeves (FR) MF, a conjugate gradient method, to optimize the embedding matrices in an alternative mode.
dynnode2vec: Scalable Dynamic Network Embedding
The proposed dynamic embedding method dynnode2vec uses evolving random walks and initializes the current graph embedding with previous embedding vectors, which demonstrates the advantages of the proposed dynamic network embedding by conducting empirical evaluations on several large dynamic network datasets.
node2vec: Scalable Feature Learning for Networks
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.
W-Metagraph2Vec: a novel approval of enriched schematic topic-driven heterogeneous information network embedding
This paper proposes a novel embedding approach, namely W-MetaGraph2Vec, which uses the topic-driven meta-graph-based random walk mechanism in weighted HIN to guide the generation of heterogeneous neighborhood of a node.
A Survey on Network Embedding
This survey focuses on categorizing and then reviewing the current development on network embedding methods, and point out its future research directions, covering the structure- and property-preserving network embeding methods, the network embedded methods with side information, and the advanced information preserving network embedting methods.