Interpretable Signed Link Prediction with Signed Infomax Hyperbolic Graph

  title={Interpretable Signed Link Prediction with Signed Infomax Hyperbolic Graph},
  author={Yadan Luo and Zi-Yu Huang and Hongxu Chen and Yang Yang and Mahsa Baktash},
Signed link prediction in social networks aims to reveal the underlying relationships (i.e. links) among users (i.e. nodes) given their existing positive and negative interactions observed. Most of the prior efforts are devoted to learning node embeddings with graph neural networks (GNNs), which preserve the signed network topology by message-passing along edges to facilitate the downstream link prediction task. Nevertheless, the existing graph-based approaches could hardly provide human… 

Figures and Tables from this paper

Dual Space Graph Contrastive Learning

A novel graph contrastive learning method, namely Dual Space Graph Contrastive (DSGC) Learning is proposed, to conduct graph Contrastive learning among views generated in different spaces including the hyperbolic space and the Euclidean space to bridge the spaces and leverage advantages from both sides.

Hyper Meta-Path Contrastive Learning for Multi-Behavior Recommendation

A new graph contrastive learning based framework is proposed by coupling with hyper meta-paths, namely HMG-CR, which consistently and significantly outperforms all baselines in extensive comparison experiments.

Hyperbolic Hypergraphs for Sequential Recommendation

A novel architecture named Hyperbolic Hypergraph representation learning method for Sequential Recommendation (H2SeqRec) is proposed with the pre-training phase to alleviate the negative impact of sparse hypergraphs and design an item enhancement module to capture dynamic social information at each timestamp to improve effectiveness.



SIDE: Representation Learning in Signed Directed Networks

This paper proposes SIDE, a general network embedding method that represents both sign and direction of edges in the embedding space and carefully formulates and optimizes likelihood over both direct and indirect signed connections.

Signed Graph Attention Networks

Experimental results on three real datasets demonstrate that SiGAT outperforms feature-based method, network embedding method and state-of-the-art GNN-based methods like signed graph convolutional network (SGCN).

Learning Signed Network Embedding via Graph Attention

A novel network embedding framework SNEA is proposed to learn Signed Network Embedding via graph Attention, which leverages self-attention mechanism to estimate the importance coefficient for pair of nodes connected by different type of links during the embedding aggregation process.

Low rank modeling of signed networks

It is shown that the notion of weak structural balance in signed networks naturally leads to a global low-rank model for the network, which can be used for other analysis tasks on signed networks, such as user segmentation through signed graph clustering, with theoretical guarantees.

SIGNet: Scalable Embeddings for Signed Networks

This work proposes SIGNet, a fast scalable embedding method suitable for signed networks that builds upon the traditional word2vec family of embedding approaches and adds a new targeted node sampling strategy to maintain structural balance in higher-order neighborhoods.

Event Prediction in Complex Social Graphs using One-Dimensional Convolutional Neural Network

This research work proposes a unique approach for predicting events in social networks by learning the context of each actor/vertex using neighboring actors in a given social graph with the goal of generating vector-space embeddings for each vertex.

Signed Graph Convolutional Networks

A dedicated and principled effort that utilizes balance theory to correctly aggregate and propagate the information across layers of a signed GCN model is proposed and empirical experiments comparing the proposed signed GCNs against state-of-the-art baselines for learning node representations in signed networks are performed.

SHINE: Signed Heterogeneous Information Network Embedding for Sentiment Link Prediction

This paper establishes a labeled heterogeneous sentiment dataset which consists of users» sentiment relation, social relation and profile knowledge by entity-level sentiment extraction method, and proposes a novel and flexible end-to-end Signed Heterogeneous Information Network Embedding (SHINE) framework to extract users» latent representations from heterogeneous networks and predict the sign of unobserved sentiment links.

Spectral Embedding of Signed Networks

Two normalized spectral analysis methods for signed graphs are derived and it is shown, using realworld data, that they produce robust embeddings.

Scalable clustering of signed networks using balance normalized cut

A multilevel clustering framework for signed networks is developed that coarsen the graph level by level and refine the clustering results at each level via a k-means based algorithm so that the signed clustering objectives are optimized.