Research map / Graph learning / GNN architectures
Beyond Node-Centric Modeling: Sketching Signed Networks with Simplicial Complexes
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a signed network sketching approach based on simplicial complexes, moving beyond node-centric GNN embeddings, for link sign prediction.
Problem
Link sign prediction in signed networks; existing signed network embedding methods learn node-wise representations in GNN frameworks guided by balance theory, which the abstract suggests is limiting for modeling complex higher-order connections.
Approach
Replaces node-centric modeling with simplicial complexes to sketch signed networks, capturing higher-order structure through positive and negative edges for cost-effective sign prediction.
Experimental setup
Builds on: balance theory graph neural networks
Closest papers by meaning
- Self-Explainable Graph Transformer for Link Sign Prediction (AAAI 2025 · similarity 0.87)
- Structure Balance and Gradient Matching-Based Signed Graph Condensation (AAAI 2025 · similarity 0.87)
- DropEdge not Foolproof: Effective Augmentation Method for Signed Graph Neural Networks (NeurIPS 2024 · similarity 0.87)
- A Signed Graph Approach to Understanding and Mitigating Oversmoothing (NeurIPS 2025 · similarity 0.86)
- Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphs (ICML 2024 · similarity 0.86)
- Sketch-Augmented Features Improve Learning Long-Range Dependencies in Graph Neural Networks (NeurIPS 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.