Research map / Graph learning / GNN architectures
Demystifying Oversmoothing in Attention-Based Graph Neural Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use attention-based aggregation (GAT) instead of constant random-walk GCN aggregation | 128-layer GNN · Cora, CiteSeer, PubMed, Cornell, Texas, Wisconsin | rate of oversmoothing | Mixed |
| switch activation function between ReLU, LeakyReLU and GELU | 128-layer GAT and GCN · six citation and WebKB graphs | rate of oversmoothing | Mixed |
Closest papers by meaning
- A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Attention Networks (ICML 2025 · similarity 0.93)
- Graph Neural Networks Do Not Always Oversmooth (NeurIPS 2024 · similarity 0.93)
- Relieving the Over-Aggregating Effect in Graph Transformers (NeurIPS 2025 · similarity 0.89)
- On Oversquashing in Graph Neural Networks Through the Lens of Dynamical Systems (AAAI 2025 · similarity 0.88)
- A Signed Graph Approach to Understanding and Mitigating Oversmoothing (NeurIPS 2025 · similarity 0.88)
- Deep Hypergraph Neural Networks with Tight Framelets (AAAI 2025 · similarity 0.88)
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.