MARINE: Multi-relational Network Embeddings with Relational Proximity and Node Attributes

@article{Feng2019MARINEMN,
  title={MARINE: Multi-relational Network Embeddings with Relational Proximity and Node Attributes},
  author={Ming-Han Feng and Chin-Chi Hsu and Cheng-te Li and Mi-Yen Yeh and Shou-de Lin},
  journal={The World Wide Web Conference},
  year={2019}
}
Network embedding aims at learning an effective vector transformation for entities in a network. [] Key Method Our solution possesses complexity linear to the number of edges, which is suitable for large-scale network applications. Experiments conducted on several real-world network datasets, along with applications in link prediction and multi-label classification, exhibit the superiority of our proposed MARINE.

Figures and Tables from this paper

Hier2vec: Interpretable Multi-granular Representation Learning for Hierarchy in Social Networks
TLDR
This paper measures the distance and importance degree of nodes in the original network and map the nodes to a tree space and proposes a novel network representation learning framework that can encode the interpretable hierarchical structural semantics into the representation vectors.
SAEA: Self-Attentive Heterogeneous Sequence Learning Model for Entity Alignment
TLDR
A Self-Attentive heterogeneous sequence learning model for Entity Alignment (SAEA) that allows us to capture long-term structural dependencies within entities and a degree-aware random walk to generate heterogeneous sequential data for self-attentive learning.
A joint optimization framework for better community detection based on link prediction in social networks
TLDR
A joint optimization framework, Communities detected on Predicted Edges, is proposed to improve the quality of community detection through learning the probabilities of unseen links and the probability of community affiliation of nodes simultaneously.
A Survey on Knowledge Graph Embeddings for Link Prediction
TLDR
A comprehensive survey on KG-embedding models for link prediction in knowledge graphs is provided and a theoretical analysis and comparison of existing methods proposed to date for generating KG embedding are investigated.
Spotting Terrorists by Learning Behavior-aware Heterogeneous Network Embedding
TLDR
This work proposes a novel unsupervised method, Outlier Spotting with behavior-aware Network Embedding (OSNE), to identify terrorists among potential criminals using six criminal network datasets provided by DARPA, and makes comparison with strong competitors.
GCAN: Graph-aware Co-Attention Networks for Explainable Fake News Detection on Social Media
TLDR
This paper solves the fake news detection problem under a more realistic scenario on social media by developing a novel neural network-based model, Graph-aware Co-Attention Networks (GCAN), which can significantly outperform state-of-the-art methods by 16% in accuracy on average.
Zero-Shot Ingredient Recognition by Multi-Relational Graph Convolutional Network
TLDR
Multi-relational GCN (graph convolutional network) is introduced that integrates ingredient hierarchy, attribute as well as co-occurrence for zero-shot ingredient recognition and sheds light on zero- shot ingredients recognition.
FairSR: Fairness-aware Sequential Recommendation through Multi-Task Learning with Preference Graph Embeddings
TLDR
A novel fairness-aware sequential recommendation task, in which a new metric, interaction fairness, is defined to estimate how recommended items are fairly interacted by users with different protected attribute groups, is proposed.
SenseLens: An Efficient Social Signal Conditioning System for True Event Detection
TLDR
A novel algorithm for extracting information signals is defined and an iterative framework is introduced that jointly improves miscroblog clustering and truth discovery and proposes a new distance metric for efficient short text similarity estimation that improves the ability to meaningfully cluster microblog posts in the latent information signal space.
Augmenting Knowledge Graphs for Better Link Prediction
TLDR
This paper proposes KGA : a knowledge graph augmentation method that incorporates literals in an embedding model without modifying its loss function, and makes the code, models, and the DWD benchmark publicly available to facilitate re-producibility and future research.
...
1
2
...

References

SHOWING 1-10 OF 53 REFERENCES
Label Informed Attributed Network Embedding
TLDR
A novel Label informed Attributed Network Embedding (LANE) framework that can smoothly incorporate label information into the attributed network embedding while preserving their correlations is proposed and achieves significantly better performance compared with the state-of-the-art embedding algorithms.
Translating Embeddings for Modeling Multi-relational Data
TLDR
TransE is proposed, a method which models relationships by interpreting them as translations operating on the low-dimensional embeddings of the entities, which proves to be powerful since extensive experiments show that TransE significantly outperforms state-of-the-art methods in link prediction on two knowledge bases.
LINE: Large-scale Information Network Embedding
TLDR
A novel network embedding method called the ``LINE,'' which is suitable for arbitrary types of information networks: undirected, directed, and/or weighted, and optimizes a carefully designed objective function that preserves both the local and global network structures.
Scalable Graph Embedding for Asymmetric Proximity
TLDR
This paper proposes an asymmetric proximity preserving (APP) graph embedding method via random walk with restart, which captures both asymmetric and high-order similarities between node pairs, and gives theoretical analysis that this method implicitly preserves the Rooted PageRank score for any two vertices.
TransG : A Generative Model for Knowledge Graph Embedding
TLDR
This paper proposes a novel generative model (TransG) to address the issue of multiple relation semantics that a relation may have multiple meanings revealed by the entity pairs associated with the corresponding triples.
A latent factor model for highly multi-relational data
TLDR
This paper proposes a method for modeling large multi-relational datasets, with possibly thousands of relations, based on a bilinear structure, which captures various orders of interaction of the data and also shares sparse latent factors across different relations.
Cross View Link Prediction by Learning Noise-resilient Representation Consensus
TLDR
This paper aims to bridge the information gap by learning a robust consensus for link-based and attribute-based representations so that nodes become comparable in the latent space and develops an alternating optimization framework to solve the problem.
GraRep: Learning Graph Representations with Global Structural Information
TLDR
A novel model for learning vertex representations of weighted graphs that integrates global structural information of the graph into the learning process and significantly outperforms other state-of-the-art methods in such tasks.
Knowledge Graph Completion with Adaptive Sparse Transfer Matrix
TLDR
Experimental results show that TranSparse outperforms Trans(E, H, R, and D) significantly, and achieves state-of-the-art performance on triplet classification and link prediction tasks.
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.
...
1
2
3
4
5
...