AI Paper Atlas

Research map / Graph learning / GNN architectures

Spiking Heterogeneous Graph Attention Networks

Buqing Cao, Qian Peng, Xiang Xie, Liang Chen, Min Shi, Jianxun Liu

AAAI 2026 · Graph learning › GNN architectures · approach: Simple and scalable GNNs · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
use SpikingHAN instead of PHGT for DBLPSpikingHAN · DBLPparameters: 8,791,360 -> 15,201Improved
use SpikingHAN instead of PHGT for DBLPSpikingHAN · DBLPmax GPU memory in training (MB): 7156.53 -> 45.2Improved
use SpikingHAN instead of PHGTSpikingHAN · DBLP, ACM, IMDBGPU energy per epoch: approximately 13 timesImproved
use SpikingHAN instead of PHGT, 40% trainingSpikingHAN · DBLP (40% training)Micro-F1 (%): 94.6 -> 93.8Hurt
use SpikingHAN instead of HAN, 60% trainingSpikingHAN · IMDB (60% training)Micro-F1 (%): 64.6 -> 65.2Improved
use SpikingHAN instead of HAN, 20% trainingSpikingHAN · DBLP (20% training)Micro-F1 (%): 93.1 -> 93.7Improved
use SpikingHAN instead of HINormer, 40% trainingSpikingHAN · ACM (40% training)Micro-F1 (%): 93.5 -> 93.0Hurt
replace IF neuron with LIF neuron (adds leakage) (ablation)SpikingHAN · DBLP, ACM, IMDB (20% training)F1Improved
replace LIF with PLIF (learnable leak) (ablation)SpikingHAN · DBLP, ACM, IMDB (20% training)F1Improved
increase time steps T (ablation)SpikingHAN · DBLP, ACM, IMDBF1 vs computeMixed

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy