Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Signed Graph Representation Learning: A Survey (2402.15980v1)

Published 25 Feb 2024 in cs.SI

Abstract: With the prevalence of social media, the connectedness between people has been greatly enhanced. Real-world relations between users on social media are often not limited to expressing positive ties such as friendship, trust, and agreement, but they also reflect negative ties such as enmity, mistrust, and disagreement, which can be well modelled by signed graphs. Signed Graph Representation Learning (SGRL) is an effective approach to analyze the complex patterns in real-world signed graphs with the co-existence of positive and negative links. In recent years, SGRL has witnesses fruitful results. SGRL tries to allocate low-dimensional representations to nodes and edges which could preserve the graph structure, attribute and some collective properties, e.g., balance theory and status theory. To the best of knowledge, there is no survey paper about SGRL up to now. In this paper, we present a broad review of SGRL methods and discuss some future research directions.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (62)
  1. Discovering polarized communities in signed networks. In CIKM, 2019.
  2. A comprehensive survey of graph embedding: Problems, techniques, and applications. TKDE, 2018.
  3. Siggan: Adversarial model for learning signed relationships in networks. TKDD, 2023.
  4. ”bridge”: Enhanced signed directed network embedding. In CIKM, 2018.
  5. Neural feature-aware recommendation with signed hypergraph convolutional network. TOIS, 2020.
  6. Exploring the potential of large language models (llms) in learning on graphs. arXiv preprint arXiv:2307.03393, 2023.
  7. Scalable clustering of signed networks using balance normalized cut. In CIKM, 2012.
  8. SPONGE: A generalized eigenproblem for clustering signed networks. In AISTATS, 2019.
  9. A survey on network embedding. TKDE, 2018.
  10. Signed graph convolutional networks. In ICDM, 2018.
  11. Inductive representation learning on large graphs. In NeurIPS, 2017.
  12. Lightgcn: Simplifying and powering graph convolution network for recommendation. In SIGIR, 2020.
  13. Positive influence maximization in signed networks within a limited time. IEEE TCSS, 2022.
  14. Sssnet: Semi-supervised signed network clustering. In SDM, 2022.
  15. PyTorch Geometric Signed Directed: A Software Package on Graph Neural Networks for Signed and Directed Graphs. In LoG, 2023.
  16. Fritz Heider. Attitudes and cognitive organization. The Journal of psychology, 1946.
  17. Signed graph attention networks. In ICANN, 2019.
  18. Signed bipartite graph neural networks. In CIKM, 2021.
  19. SDGNN: learning node representation for signed directed networks. In AAAI, 2021.
  20. Pole: Polarized embedding for signed networks. In WSDM, 2022.
  21. Negative can be positive: Signed graph neural networks for recommendation. IPM, 2023.
  22. Signet: Scalable embeddings for signed networks. In PAKDD. Springer, 2018.
  23. ROSE: role-based signed network embedding. In WWW, 2020.
  24. SIDE: representation learning in signed directed networks. In WWW, 2018.
  25. Semi-supervised classification with graph convolutional networks. In ICLR, 2017.
  26. Edge weight prediction in weighted signed networks. In ICDM, 2016.
  27. Graph neural networks meet neural-symbolic computing: A survey and perspective. In IJCAI, 2020.
  28. ASiNE: Adversarial signed network embedding. In SIGIR, 2020.
  29. Signed networks in social media. In CHI, 2010.
  30. Senti2pop: sentiment-aware topic popularity prediction on social media. In ICDM, 2019.
  31. Learning signed network embedding via graph attention. In AAAI, 2020.
  32. Signed graph neural network with latent groups. In KDD, 2021.
  33. Local augmentation for graph neural networks. In ICML, 2022.
  34. Graph pooling for graph neural networks: Progress, challenges, and opportunities. In IJCAI, 2023.
  35. Ssne: status signed network embedding. In PAKDD, 2019.
  36. Enhancing student performance prediction on learnersourced questions with sgnn-llm synergy. ArXiv preprint, 2023.
  37. Learning stance embeddings from signed social graphs. In WSDM, 2023.
  38. Siren: Sign-aware recommendation using graph neural networks. TNNLS, 2022.
  39. Representation learning in continuous-time dynamic signed networks. In CIKM, 2023.
  40. Deep network embedding for graph representation learning in signed networks. IEEE Transactions on Cybernetics, 2018.
  41. Sgcl: Contrastive representation learning for signed graphs. In CIKM, 2021.
  42. Stable community detection in signed social networks. TKDE, (10), 2020.
  43. Recommendations in signed social networks. In WWW, 2016.
  44. A survey of signed network mining in social media. ACM CSUR, 2016.
  45. Graph attention networks. In ICLR, 2018.
  46. Signed network embedding in social media. In SDM, 2017.
  47. SHINE: signed heterogeneous information network embedding for sentiment link prediction. In WSDM, 2018.
  48. Graph neural networks in recommender systems: a survey. ACM CSUR, 2020.
  49. A comprehensive survey on graph neural networks. TNNLS, 2020.
  50. Searching for polarization in signed graphs: a local spectral approach. In WWW, 2020.
  51. Deep feedback network for recommendation. In IJCAI, 2020.
  52. Graph convolutional neural networks for web-scale recommender systems. In KDD, 2018.
  53. SNE: Signed Network Embedding. In PAKDD, 2017.
  54. Explainability in graph neural networks: A taxonomic survey. TPAMI, 2022.
  55. Deep learning on graphs: A survey. TKDE, 2020.
  56. Contrastive learning for signed bipartite graphs. In SIGIR, 2023.
  57. Rsgnn: A model-agnostic approach for enhancing the robustness of signed graph neural networks. In Web Conference, 2023.
  58. Sga: A graph augmentation method for signed graph neural networks. ArXiv preprint, 2023.
  59. Social balance in signed networks. Information Systems Frontiers, 2015.
  60. Graph neural networks: A review of methods and applications. AI Open, 2020.
  61. Black-box attacks against signed graph analysis via balance poisoning. ArXiv preprint, 2023.
  62. Modeling polypharmacy side effects with graph convolutional networks. Bioinformatics, 2018.
Citations (3)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now