Research map / Graph learning / Knowledge and temporal graphs
AEGNN: Asynchronous Event-Based Graph Neural Networks
Check 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 asynchronous sparse graph updates instead of dense GNN updates | GNN · N-Caltech101 | MFLOPs per event: 1.72\cdot 10^3 -> 4.29 | Helped |
| Use asynchronous sparse graph updates instead of dense GNN updates | GNN · N-Caltech101 (25,000 events) | latency: 1014 ms -> 129 ms | Helped |
| Use AEGNN instead of AsyNet | event-based object detection · N-Caltech101 | mAP: 0.643 -> 0.595 | Hurt |
| Use AEGNN instead of AsyNet | event-based object detection · Gen1 | mAP: 0.129 -> 0.163 | Helped |
| Use AEGNN instead of AsyNet | event-based object detection · Gen1 | MFLOP/ev: 205 -> 5.26 | Helped |
| Use AEGNN instead of NVS-S | event-based object detection · N-Caltech101 | mAP: 0.346$^*$ -> 0.595 | Helped |
| Use AEGNN instead of RED | event-based object detection · Gen1 | mAP: 0.40 -> 0.163 | Hurt |
| Uniformly subsample the input events | AEGNN · object recognition | overfitting | Helped |
| Use non-uniform grid sampling instead of uniform sampling | AEGNN · object recognition | performance | No clear effect |
Closest papers by meaning
- Graph Neural Network Combining Event Stream and Periodic Aggregation for Low-Latency Event-based Vision (CVPR 2025 · similarity 0.89)
- A Dynamic GCN with Cross-Representation Distillation for Event-Based Learning (AAAI 2024 · similarity 0.88)
- Asynchronous Collaborative Graph Representation for Frames and Events (CVPR 2025 · similarity 0.88)
- Leveraging Asynchronous Spiking Neural Networks for Ultra Efficient Event-Based Visual Processing (AAAI 2025 · similarity 0.87)
- EGSST: Event-based Graph Spatiotemporal Sensitive Transformer for Object Detection (NeurIPS 2024 · similarity 0.85)
- Efficient Event-Based Object Detection: A Hybrid Neural Network with Spatial and Temporal Attention (CVPR 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.