Echoless Label-Based Pre-computation for Memory-Efficient Heterogeneous Graph Learning

Jun Hu; Shangheng Chen; Yufei He; Yuan Li; Bryan Hooi; Bingsheng He

AAAI 2026technical0 citations

Echoless Label-Based Pre-computation for Memory-Efficient Heterogeneous Graph Learning

Jun Hu, Shangheng Chen, Yufei He, Yuan Li, Bryan Hooi, Bingsheng He

Abstract

Heterogeneous Graph Neural Networks (HGNNs) are widely used for deep learning on heterogeneous graphs. Typical end-to-end HGNNs require repetitive message passing during training, limiting efficiency for large-scale real-world graphs. Pre-computation-based HGNNs address this by performing message passing only once during preprocessing, collecting neighbor information into regular-shaped tensors, which enables efficient mini-batch training. Label-based pre-computation methods collect neighbors

BibTeX

@inproceedings{aaai2026_echolesslabelbas,
  title = {Echoless Label-Based Pre-computation for Memory-Efficient Heterogeneous Graph Learning},
  author = {Jun Hu and Shangheng Chen and Yufei He and Yuan Li and Bryan Hooi and Bingsheng He},
  booktitle = {AAAI 2026},
  year = {2026}
}