mlsanityData to 14 Oct 2026

wsGAT: Weighted and Signed Graph Attention Networks for Link Prediction

arXiv 2109.11519 ↗First posted 21 Sep 2021cs.SI cs.LG physics.soc-phcited by 8

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) have been widely used to learn representations on graphs and tackle many real-world problems from a wide range of domains. In this paper we propose wsGAT, an extension of the Graph Attention Network (GAT) layers, meant to address the lack of GNNs that can handle graphs with signed and weighted links, which are ubiquitous, for instance, in trust and correlation networks. We first evaluate the performance of our proposal by comparing against GCNII in the weighed link prediction task, and against SGCN in the link sign prediction task. After that, we combine the two tasks and show their performance on predicting the signed weight of links, and their existence. Our results on real-world networks show that models with wsGAT layers outperform the ones with GCNII and SGCN layers, and that there is no loss in performance when signed weights are predicted.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 10 of its 27 references that are in the map. First posted on arXiv 21 Sep 2021.

Builds on

10 of 27 references.

References · 10

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  5. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  6. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
  7. 2020Simple and Deep Graph Convolutional Networkscited by 860
  8. 2021Machine learning dismantling and early-warning signals of disintegration in complex systemscited by 14
  9. 2018Signed Graph Convolutional Networkcited by 10
  10. 2019Learning Multi-Stage Sparsification for Maximum Clique Enumerationcited by 6

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 1; 2024: 3; 2025: 1.

8 papers.

  1. 2024Knowledge Graph Large Language Model (KG-LLM) for Link Predictioncited by 36
  2. 2022Sparsification and Filtering for Spatial-temporal GNN in Multivariate Time-seriescited by 5
  3. 2023SignGT: Signed Attention-based Graph Transformer for Graph Representation Learningcited by 5
  4. 2022Motif-aware temporal GCN for fraud detection in signed cryptocurrency trust networkscited by 4
  5. 2022Graph Learning and Its Advancements on Large Language Models: A Holistic Surveycited by 4
  6. 2024Haar-Laplacian for directed graphscited by 1
  7. 2025Beyond MMD: Evaluating Graph Generative Models with Geometric Deep Learningcited by 1
  8. 2024Adversarial Robustness of Link Sign Prediction in Signed Graphscited by 0