Signed Bipartite Graph Neural Networks

• URL: http://arxiv.org/abs/2108.09638v1
• Date: Sun, 22 Aug 2021 05:15:45 GMT
• Title: Signed Bipartite Graph Neural Networks
• Authors: Junjie Huang, Huawei Shen, Qi Cao, Shuchang Tao, Xueqi Cheng
• Abstract summary: Signed bipartite networks are different from classical signed networks, which contain two different node sets and signed links between two node sets. In this work, we firstly define the signed relationship of the same set of nodes and provide a new perspective for analyzing signed bipartite networks. We then do some comprehensive analysis of balance theory from two perspectives on several real-world datasets.
• Score: 42.32959912473691
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Signed networks are such social networks having both positive and negative links. A lot of theories and algorithms have been developed to model such networks (e.g., balance theory). However, previous work mainly focuses on the unipartite signed networks where the nodes have the same type. Signed bipartite networks are different from classical signed networks, which contain two different node sets and signed links between two node sets. Signed bipartite networks can be commonly found in many fields including business, politics, and academics, but have been less studied. In this work, we firstly define the signed relationship of the same set of nodes and provide a new perspective for analyzing signed bipartite networks. Then we do some comprehensive analysis of balance theory from two perspectives on several real-world datasets. Specifically, in the peer review dataset, we find that the ratio of balanced isomorphism in signed bipartite networks increased after rebuttal phases. Guided by these two perspectives, we propose a novel Signed Bipartite Graph Neural Networks (SBGNNs) to learn node embeddings for signed bipartite networks. SBGNNs follow most GNNs message-passing scheme, but we design new message functions, aggregation functions, and update functions for signed bipartite networks. We validate the effectiveness of our model on four real-world datasets on Link Sign Prediction task, which is the main machine learning task for signed networks. Experimental results show that our SBGNN model achieves significant improvement compared with strong baseline methods, including feature-based methods and network embedding methods.

Related papers

• Link Prediction in Bipartite Networks [1.7446992240872337]
  We compare 19 link prediction methods able to handle bipartite graphs. We propose to repurpose recommendation systems based on graph convolutional networks (GCN) as a novel link prediction solution. Our results indicate that GCN-based personalized recommendation systems, which have received significant attention in recent years, can produce successful results for link prediction in bipartite networks.
  arXiv  Detail & Related papers  (2024-06-10T11:23:30Z)
• Improving Signed Propagation for Graph Neural Networks in Multi-Class Environments [3.4498722449655066]
  We introduce two novel strategies for improving signed propagation under multi-class graphs. The proposed scheme combines calibration to secure robustness while reducing uncertainty. We show the efficacy of our theorem through extensive experiments on six benchmark graph datasets.
  arXiv  Detail & Related papers  (2023-01-21T08:47:22Z)
• MUSE: Multi-faceted Attention for Signed Network Embedding [4.442695760653947]
  Signed network embedding is an approach to learn low-dimensional representations of nodes in signed networks with both positive and negative links. We propose MUSE, a MUlti-faceted attention-based Signed network Embedding framework to tackle this problem.
  arXiv  Detail & Related papers  (2021-04-29T16:09:35Z)
• Multiplex Bipartite Network Embedding using Dual Hypergraph Convolutional Networks [16.62391694987056]
  We develop an unsupervised Dual HyperGraph Convolutional Network (DualHGCN) model scalably transforms the multiplex bipartite network into two sets of homogeneous hypergraphs. We benchmark DualHGCN using four real-world datasets on link prediction and node classification tasks.
  arXiv  Detail & Related papers  (2021-02-12T07:20:36Z)
• SDGNN: Learning Node Representation for Signed Directed Networks [43.15277366961127]
  Graph Neural Networks (GNNs) have received widespread attention and lead to state-of-the-art performance in learning node representations. It is not trivial to transfer these models to signed directed networks, which are widely observed in the real world yet less studied. We propose a novel Signed Directed Graph Neural Networks model named SDGNN to learn node embeddings for signed directed networks.
  arXiv  Detail & Related papers  (2021-01-07T06:15:07Z)
• Interpretable Signed Link Prediction with Signed Infomax Hyperbolic Graph [54.03786611989613]
  signed link prediction in social networks aims to reveal the underlying relationships (i.e. links) among users (i.e. nodes) We develop a unified framework, termed as Signed Infomax Hyperbolic Graph (textbfSIHG) 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.
  arXiv  Detail & Related papers  (2020-11-25T05:09:03Z)
• Spectral Embedding of Graph Networks [76.27138343125985]
  We introduce an unsupervised graph embedding that trades off local node similarity and connectivity, and global structure. The embedding is based on a generalized graph Laplacian, whose eigenvectors compactly capture both network structure and neighborhood proximity in a single representation.
  arXiv  Detail & Related papers  (2020-09-30T04:59:10Z)
• Unsupervised Differentiable Multi-aspect Network Embedding [52.981277420394846]
  We propose a novel end-to-end framework for multi-aspect network embedding, called asp2vec. Our proposed framework can be readily extended to heterogeneous networks.
  arXiv  Detail & Related papers  (2020-06-07T19:26:20Z)
• Binarized Graph Neural Network [65.20589262811677]
  We develop a binarized graph neural network to learn the binary representations of the nodes with binary network parameters. Our proposed method can be seamlessly integrated into the existing GNN-based embedding approaches. Experiments indicate that the proposed binarized graph neural network, namely BGN, is orders of magnitude more efficient in terms of both time and space.
  arXiv  Detail & Related papers  (2020-04-19T09:43:14Z)
• Unifying Graph Convolutional Neural Networks and Label Propagation [73.82013612939507]
  We study the relationship between LPA and GCN in terms of two aspects: feature/label smoothing and feature/label influence. Based on our theoretical analysis, we propose an end-to-end model that unifies GCN and LPA for node classification. Our model can also be seen as learning attention weights based on node labels, which is more task-oriented than existing feature-based attention models.
  arXiv  Detail & Related papers  (2020-02-17T03:23:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.