# GegenNet: Spectral Convolutional Neural Networks for Link Sign Prediction in Signed Bipartite Graphs

arXiv: https://arxiv.org/abs/2508.19907 · HTML: https://mlsanity.com/paper/2508.19907/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 59 references that are in the map.
- First posted on arXiv 27 Aug 2025.

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

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [Predict then Propagate: Graph Neural Networks meet Personalized PageRank](https://mlsanity.com/paper/1810.05997/) (2018)
- [Diffusion Improves Graph Learning](https://mlsanity.com/paper/1911.05485/) (2019)
- [How Powerful are Spectral Graph Neural Networks](https://mlsanity.com/paper/2205.11172/) (2022)
- [Interpreting and Unifying Graph Neural Networks with An Optimization Framework](https://mlsanity.com/paper/2101.11859/) (2021)
- [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)
- [Bipartite Graph Embedding via Mutual Information Maximization](https://mlsanity.com/paper/2012.05442/) (2020)
- [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)
- [SigMaNet: One Laplacian to Rule Them All](https://mlsanity.com/paper/2205.13459/) (2022)
- [Approximate Graph Propagation](https://mlsanity.com/paper/2106.03058/) (2021)
- [SSSNET: Semi-Supervised Signed Network Clustering](https://mlsanity.com/paper/2110.06623/) (2021)
- [Signed Bipartite Graph Neural Networks](https://mlsanity.com/paper/2108.09638/) (2021)
- [Distributed Representations of Signed Networks](https://mlsanity.com/paper/1702.06819/) (2017)
- [Node-wise Diffusion for Scalable Graph Learning](https://mlsanity.com/paper/2305.14000/) (2023)
- [Multiplex Bipartite Network Embedding using Dual Hypergraph Convolutional Networks](https://mlsanity.com/paper/2102.06371/) (2021)
- [Efficient High-Quality Clustering for Large Bipartite Graphs](https://mlsanity.com/paper/2312.16926/) (2023)
- [SlotGAT: Slot-based Message Passing for Heterogeneous Graph Neural Network](https://mlsanity.com/paper/2405.01927/) (2024)
- [Signed Graph Representation Learning: A Survey](https://mlsanity.com/paper/2402.15980/) (2024)
- [FOBE and HOBE: First- and High-Order Bipartite Embeddings](https://mlsanity.com/paper/1905.10953/) (2019)
- [Effective Edge-wise Representation Learning in Edge-Attributed Bipartite Graphs](https://mlsanity.com/paper/2406.13369/) (2024)

## Built on by (most cited first, 3 of 3)

- [Cross-Contrastive Clustering for Multimodal Attributed Graphs with Dual Graph Filtering](https://mlsanity.com/paper/2511.20030/) (2025)
- [Rethinking Message Passing Neural Networks with Diffusion Distance-guided Stress Majorization](https://mlsanity.com/paper/2511.19984/) (2025)
- [DualSpectralCF: Training-Free Sign-Aware Spectral Collaborative Filtering](https://mlsanity.com/paper/2608.10247/) (2026)

## Abstract (arXiv)

Given a signed bipartite graph (SBG) G with two disjoint node sets U and V, the goal of link sign prediction is to predict the signs of potential links connecting U and V based on known positive and negative edges in G. The majority of existing solutions towards link sign prediction mainly focus on unipartite signed graphs, which are sub-optimal due to the neglect of node heterogeneity and unique bipartite characteristics of SBGs. To this end, recent studies adapt graph neural networks to SBGs by introducing message-passing schemes for both inter-partition (UxV) and intra-partition (UxU or VxV) node pairs. However, the fundamental spectral convolutional operators were originally designed for positive links in unsigned graphs, and thus, are not optimal for inferring missing positive or negative links from known ones in SBGs. Motivated by this, this paper proposes GegenNet, a novel and effective spectral convolutional neural network model for link sign prediction in SBGs. In particular, GegenNet achieves enhanced model capacity and high predictive accuracy through three main technical contributions: (i) fast and theoretically grounded spectral decomposition techniques for node feature initialization; (ii) a new spectral graph filter based on the Gegenbauer polynomial basis; and (iii) multi-layer sign-aware spectral convolutional networks alternating Gegenbauer polynomial filters with positive and negative edges. Our extensive empirical studies reveal that GegenNet can achieve significantly superior performance (up to a gain of 4.28% in AUC and 11.69% in F1) in link sign prediction compared to 11 strong competitors over 6 benchmark SBG datasets.