graphs-2

Link Sign Prediction

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in link-sign-prediction-2

Trend

Dataset

Best Model

Actions

Bitcoin-Alpha

Slashdot

Epinions

Libraries

i

Use these libraries to find link-sign-prediction-2 models and implementations

Datasets

Slashdot

Epinions

Subtasks

No subtasks available.

Most implemented papers

Deep Network Embedding for Graph Representation Learning in Signed Networks

X. Shen, F. Chung•Sun Jan 06 2019

Extensive experimental results in real-world datasets demonstrate the superiority of the proposed model over the state-of-the-art network embedding algorithms for graph representation learning in signed networks.

98

Content

0

Paper Graph

Learning Opinion Dynamics From Social Traces

Corrado Monti, G. D. F. Morales, F. Bonchi•Mon Jun 01 2020

This work proposes an inference mechanism for fitting a generative, agent-like model of opinion dynamics to real-world social traces, and designs an inference algorithm that can recover the latent opinion trajectories from traces generated by the classical agent-based model.

37 0

Paper Graph

Decoupled Variational Embedding for Signed Directed Networks

Maosen Li, Xu Chen, Ya Zhang, Yanfeng Wang, Jiangchao Yao•Thu Aug 27 2020

The representation learning problem on signed directed networks is reformulated from a variational auto-encoding perspective and a decoupled variational embedding (DVE) method is developed that leverages a specially designed auto- Encoding structure to capture both the first-order and high-order topology of signed directed Networks, and thus learns more representative node embeddings.

5 0

Paper Graph

Signed Bipartite Graph Neural Networks

Huawei Shen, Shuchang Tao, Xueqi Cheng, Qi Cao, Junjie Huang•Sat Aug 21 2021

A novel Signed Bipartite Graph Neural Networks (SBGNNs) is proposed to learn node embeddings for signed bipartite networks and some comprehensive analysis of balance theory from two perspectives on several real-world datasets are done.

55 0

Paper Graph

SSSNET: Semi-Supervised Signed Network Clustering

Yixuan He, G. Reinert, Songchao Wang, Mihai Cucuringu•Tue Oct 12 2021

A novel probabilistic balanced normalized cut loss for training nodes in a GNN framework for semi-supervised signed network clustering, called SSSNET, which has node clustering as main focus, with an emphasis on polarization effects arising in networks.

38 0

Paper Graph

Adding a benchmark result helps the community track progress.