# Signed Graph Diffusion Network

arXiv: https://arxiv.org/abs/2012.14191 · HTML: https://mlsanity.com/paper/2012.14191/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Dec 2020.

## Built on by (most cited first, 13 of 13)

- [Model-Agnostic Augmentation for Accurate Graph Classification](https://mlsanity.com/paper/2202.10107/) (2022)
- [Contrastive Brain Network Learning via Hierarchical Signed Graph Pooling Model](https://mlsanity.com/paper/2207.07650/) (2022)
- [Self-Explainable Graph Transformer for Link Sign Prediction](https://mlsanity.com/paper/2408.08754/) (2024)
- [Enhancing Student Performance Prediction on Learnersourced Questions with SGNN-LLM Synergy](https://mlsanity.com/paper/2309.13500/) (2023)
- [DropEdge not Foolproof: Effective Augmentation Method for Signed Graph Neural Networks](https://mlsanity.com/paper/2409.19620/) (2024)
- [A Graph Convolution for Signed Directed Graphs](https://mlsanity.com/paper/2208.11511/) (2022)
- [Mitigating Degree Bias in Signed Graph Neural Networks](https://mlsanity.com/paper/2408.08508/) (2024)
- [DFGNN: Dual-frequency Graph Neural Network for Sign-aware Feedback](https://mlsanity.com/paper/2405.15280/) (2024)
- [SGA: A Graph Augmentation Method for Signed Graph Neural Networks](https://mlsanity.com/paper/2310.09705/) (2023)
- [Enhancing Signed Graph Neural Networks through Curriculum-Based Training](https://mlsanity.com/paper/2310.11083/) (2023)
- [Graph Spring Neural ODEs for Link Sign Prediction](https://mlsanity.com/paper/2412.12916/) (2024)
- [Effective and Lightweight Representation Learning for Link Sign Prediction in Signed Bipartite Graphs](https://mlsanity.com/paper/2412.18720/) (2024)
- [AlphaFree: Recommendation Free from Users, IDs, and GNNs](https://mlsanity.com/paper/2603.02653/) (2026)

## Abstract (arXiv)

Given a signed social graph, how can we learn appropriate node representations to infer the signs of missing edges? Signed social graphs have received considerable attention to model trust relationships. Learning node representations is crucial to effectively analyze graph data, and various techniques such as network embedding and graph convolutional network (GCN) have been proposed for learning signed graphs. However, traditional network embedding methods are not end-to-end for a specific task such as link sign prediction, and GCN-based methods suffer from a performance degradation problem when their depth increases. In this paper, we propose Signed Graph Diffusion Network (SGDNet), a novel graph neural network that achieves end-to-end node representation learning for link sign prediction in signed social graphs. We propose a random walk technique specially designed for signed graphs so that SGDNet effectively diffuses hidden node features. Through extensive experiments, we demonstrate that SGDNet outperforms state-of-the-art models in terms of link sign prediction accuracy.