Research map / Graph learning / GNN architectures
Deep Learning on Graphs: A Data-Centric Exploration
Wei Jin
Read the paperCheck your idea against 137,217 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.
A data-centric survey/position on deep learning for graphs, arguing that improving graph data quality and structure, rather than only model architecture, is key to GNN efficiency and effectiveness.
Problem
GNNs face efficiency and effectiveness limitations on graph data, which the abstract attributes to issues with the data itself rather than only model design.
Approach
Reframes graph learning from a data-centric perspective, emphasizing data-side techniques for GNNs as an alternative to purely model-centric work.
Closest papers by meaning
- Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study (TPAMI 2022 · similarity 0.90)
- Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellence (ICML 2025 · similarity 0.89)
- TRACI: A Data-centric Approach for Multi-Domain Generalization on Graphs (AAAI 2025 · similarity 0.88)
- Generalizing CNNs to graphs with learnable neighborhood quantization (NeurIPS 2024 · similarity 0.88)
- On the Scalability of GNNs for Molecular Graphs (NeurIPS 2024 · similarity 0.88)
- On the Stability of Graph Convolutional Neural Networks: A Probabilistic Perspective (NeurIPS 2025 · similarity 0.87)
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.
