# Toward Robust Signed Graph Learning through Joint Input-Target Denoising

arXiv: https://arxiv.org/abs/2510.22513 · HTML: https://mlsanity.com/paper/2510.22513/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 54 references that are in the map.
- First posted on arXiv 26 Oct 2025.

## Builds on (most cited first, 25 of 25)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [Graph Structure Learning for Robust Graph Neural Networks](https://mlsanity.com/paper/2005.10203/) (2020)
- [Adversarial Attacks on Graph Neural Networks via Meta Learning](https://mlsanity.com/paper/1902.08412/) (2019)
- [Learning Discrete Structures for Graph Neural Networks](https://mlsanity.com/paper/1903.11960/) (2019)
- [Adversarial Graph Augmentation to Improve Graph Contrastive Learning](https://mlsanity.com/paper/2106.05819/) (2021)
- [Graph Information Bottleneck](https://mlsanity.com/paper/2010.12811/) (2020)
- [Graph Information Bottleneck for Subgraph Recognition](https://mlsanity.com/paper/2010.05563/) (2020)
- [Signed Graph Attention Networks](https://mlsanity.com/paper/1906.10958/) (2019)
- [SDGNN: Learning Node Representation for Signed Directed Networks](https://mlsanity.com/paper/2101.02390/) (2021)
- [MSGNN: A Spectral Graph Neural Network Based on a Novel Magnetic Signed Laplacian](https://mlsanity.com/paper/2209.00546/) (2022)
- [SPONGE: A generalized eigenproblem for clustering signed networks](https://mlsanity.com/paper/1904.08575/) (2019)
- [Distributed Representations of Signed Networks](https://mlsanity.com/paper/1702.06819/) (2017)
- [HILL: Hierarchy-aware Information Lossless Contrastive Learning for Hierarchical Text Classification](https://mlsanity.com/paper/2403.17307/) (2024)
- [Clustering Signed Networks with the Geometric Mean of Laplacians](https://mlsanity.com/paper/1701.00757/) (2017)
- [Robust Deep Signed Graph Clustering via Weak Balance Theory](https://mlsanity.com/paper/2502.05472/) (2025)
- [Measuring Partial Balance in Signed Networks](https://mlsanity.com/paper/1509.04037/) (2015)
- [NC-NCD: Novel Class Discovery for Node Classification](https://mlsanity.com/paper/2407.17816/) (2024)
- [Black-Box Attacks against Signed Graph Analysis via Balance Poisoning](https://mlsanity.com/paper/2309.02396/) (2023)
- [Rumor Detection on Social Media with Temporal Propagation Structure Optimization](https://mlsanity.com/paper/2412.08316/) (2024)
- [Molecular Graph Contrastive Learning with Line Graph](https://mlsanity.com/paper/2501.08589/) (2025)
- [Structural Entropy Guided Unsupervised Graph Out-Of-Distribution Detection](https://mlsanity.com/paper/2503.03241/) (2025)
- [Link Polarity Prediction from Sparse and Noisy Labels via Multiscale Social Balance](https://mlsanity.com/paper/2407.15643/) (2024)

## Abstract (arXiv)

Signed Graph Neural Networks (SGNNs) are widely adopted to analyze complex patterns in signed graphs with both positive and negative links. Given the noisy nature of real-world connections, the robustness of SGNN has also emerged as a pivotal research area. Under the supervision of empirical properties, graph structure learning has shown its robustness on signed graph representation learning, however, there remains a paucity of research investigating a robust SGNN with theoretical guidance. Inspired by the success of graph information bottleneck (GIB) in information extraction, we propose RIDGE, a novel framework for Robust sI gned graph learning through joint Denoising of Graph inputs and supervision targEts. Different from the basic GIB, we extend the GIB theory with the capability of target space denoising as the co-existence of noise in both input and target spaces. In instantiation, RIDGE effectively cleanses input data and supervision targets via a tractable objective function produced by reparameterization mechanism and variational approximation. We extensively validate our method on four prevalent signed graph datasets, and the results show that RIDGE clearly improves the robustness of popular SGNN models under various levels of noise.