Research map / Graph learning / GNN architectures
Echoless Label-Based Pre-computation for Memory-Efficient Heterogeneous Graph Learning
Jun Hu, Shangheng Chen, Yufei He, Yuan Li, Bryan Hooi, Bingsheng He
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 |
|---|---|---|---|
| add Echoless-LP label pre-computation | RpHGNN · DBLP | Micro-F1: 95.55 -> 95.70 | Improved |
| add Echoless-LP label pre-computation | RpHGNN · IMDB | Micro-F1: 69.77 -> 70.84 | Improved |
| add Echoless-LP label pre-computation | RpHGNN · OAG-Venue | NDCG: 53.31 -> 54.72 | Improved |
| add Echoless-LP label pre-computation | RpHGNN · OGBN-MAG | accuracy: 52.07 -> 54.04 | Improved |
| add LastResidual-LP label pre-computation | RpHGNN · OGBN-MAG | accuracy: 52.07 -> 45.88 | Hurt |
| add LastResidual-LP label pre-computation | SeHGNN · OGBN-MAG | accuracy: 51.45 -> 47.59 | Hurt |
| add LastResidual-LP label pre-computation | NARS · OGBN-MAG | accuracy: 50.66 -> 52.28 | Improved |
| replace RemoveDiag-LP with Echoless-LP | SeHGNN · OAG-Venue | NDCG: 44.21 -> 47.92 | Improved |
| replace RemoveDiag-LP with Echoless-LP | NARS · OGBN-MAG | accuracy: 53.99 -> 54.43 | Improved |
| replace RemoveDiag-LP with Echoless-LP | NARS or SeHGNN · OGBN-MAG, K=3 | memory: OOM (> 13TB) -> 70GB | Improved |
| add PFEP (partition-focused echoless propagation) (ablation) | Echoless-LP (RpHGNN) · ablation datasets | performance | Improved |
| add Asymmetric Partitioning Scheme instead of uniform random partitioning (ablation) | Echoless-LP (RpHGNN) · ablation datasets | performance | Improved |
Closest papers by meaning
- HGPrompt: Bridging Homogeneous and Heterogeneous Graphs for Few-Shot Prompt Learning (AAAI 2024 · similarity 0.86)
- Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphs (ICML 2024 · similarity 0.86)
- HGOT: Self-supervised Heterogeneous Graph Neural Network with Optimal Transport (ICML 2025 · similarity 0.86)
- HGDL: Heterogeneous Graph Label Distribution Learning (NeurIPS 2024 · similarity 0.86)
- An Efficient Subgraph-Inferring Framework for Large-Scale Heterogeneous Graphs (AAAI 2024 · similarity 0.86)
- Accurate and Scalable Graph Neural Networks via Message Invariance (ICLR 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.
