Research map / Graph learning / GNN architectures
Spiking Heterogeneous Graph Attention Networks
Buqing Cao, Qian Peng, Xiang Xie, Liang Chen, Min Shi, Jianxun Liu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 SpikingHAN instead of PHGT for DBLP | SpikingHAN · DBLP | parameters: 8,791,360 -> 15,201 | Improved |
| use SpikingHAN instead of PHGT for DBLP | SpikingHAN · DBLP | max GPU memory in training (MB): 7156.53 -> 45.2 | Improved |
| use SpikingHAN instead of PHGT | SpikingHAN · DBLP, ACM, IMDB | GPU energy per epoch: approximately 13 times | Improved |
| use SpikingHAN instead of PHGT, 40% training | SpikingHAN · DBLP (40% training) | Micro-F1 (%): 94.6 -> 93.8 | Hurt |
| use SpikingHAN instead of HAN, 60% training | SpikingHAN · IMDB (60% training) | Micro-F1 (%): 64.6 -> 65.2 | Improved |
| use SpikingHAN instead of HAN, 20% training | SpikingHAN · DBLP (20% training) | Micro-F1 (%): 93.1 -> 93.7 | Improved |
| use SpikingHAN instead of HINormer, 40% training | SpikingHAN · ACM (40% training) | Micro-F1 (%): 93.5 -> 93.0 | Hurt |
| replace IF neuron with LIF neuron (adds leakage) (ablation) | SpikingHAN · DBLP, ACM, IMDB (20% training) | F1 | Improved |
| replace LIF with PLIF (learnable leak) (ablation) | SpikingHAN · DBLP, ACM, IMDB (20% training) | F1 | Improved |
| increase time steps T (ablation) | SpikingHAN · DBLP, ACM, IMDB | F1 vs compute | Mixed |
Closest papers by meaning
- SGNNBench: A Holistic Evaluation of Spiking Graph Neural Networks on Large-scale Graphs (NeurIPS 2026 · similarity 0.90)
- Simple and Efficient Heterogeneous Temporal Graph Neural Network (NeurIPS 2025 · similarity 0.88)
- HeterGP: Bridging Heterogeneity in Graph Neural Networks with Multi-View Prompting (AAAI 2025 · similarity 0.88)
- Delay-DSGN: A Dynamic Spiking Graph Neural Network with Delay Mechanisms for Evolving Graph (ICML 2025 · similarity 0.87)
- Dynamic Reactive Spiking Graph Neural Network (AAAI 2024 · similarity 0.87)
- An Efficient Subgraph-Inferring Framework for Large-Scale Heterogeneous Graphs (AAAI 2024 · 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.
