Log In Sign Up

Interpretable Signed Link Prediction with Signed Infomax Hyperbolic Graph

by   Yadan Luo, et al.

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-intelligible explanations for the following three questions: (1) which neighbors to aggregate, (2) which path to propagate along, and (3) which social theory to follow in the learning process. To answer the aforementioned questions, in this paper, we investigate how to reconcile the balance and status social rules with information theory and develop a unified framework, termed as Signed Infomax Hyperbolic Graph (SIHG). By maximizing the mutual information between edge polarities and node embeddings, one can identify the most representative neighboring nodes that support the inference of edge sign. Different from existing GNNs that could only group features of friends in the subspace, the proposed SIHG incorporates the signed attention module, which is also capable of pushing hostile users far away from each other to preserve the geometry of antagonism. The polarity of the learned edge attention maps, in turn, provide interpretations of the social theories used in each aggregation. In order to model high-order user relations and complex hierarchies, the node embeddings are projected and measured in a hyperbolic space with a lower distortion. Extensive experiments on four signed network benchmarks demonstrate that the proposed SIHG framework significantly outperforms the state-of-the-arts in signed link prediction.


Signed Graph Attention Networks

Graph or network data is ubiquitous in the real world, including social ...

Signed Link Representation in Continuous-Time Dynamic Signed Networks

Signed networks allow us to model bi-faceted relationships and interacti...

Learning Edge Properties in Graphs from Path Aggregations

Graph edges, along with their labels, can represent information of funda...

FakeEdge: Alleviate Dataset Shift in Link Prediction

Link prediction is a crucial problem in graph-structured data. Due to th...

Signed Bipartite Graph Neural Networks

Signed networks are such social networks having both positive and negati...

MUSE: Multi-faceted Attention for Signed Network Embedding

Signed network embedding is an approach to learn low-dimensional represe...

GIPA++: A General Information Propagation Algorithm for Graph Learning

Graph neural networks (GNNs) have been widely used in graph-structured d...