Research map / Graph learning / GNN architectures
DREAM: Dual-Standard Semantic Homogeneity with Dynamic Optimization for Graph Learning with Label Noise
Yusheng Zhao, Jiaye Xie, Qixin Zhang, Weizhi Zhang, Xiao Luo, Zhiping Xiao, Philip S. Yu, Ming Zhang
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 topology-aware anchors (ablation) | DREAM · CiteSeer (30% uniform noise) | accuracy (%): 69.69 -> 71.06 | Improved |
| add topology-aware anchors (ablation) | DREAM · Cora (30% uniform noise) | accuracy (%): 79.60 -> 80.40 | Improved |
| add proximity-aware anchors (ablation) | DREAM · CiteSeer (30% uniform noise) | accuracy (%): 62.11 -> 71.06 | Improved |
| add proximity-aware anchors (ablation) | DREAM · Cora (30% uniform noise) | accuracy (%): 77.04 -> 80.40 | Improved |
| add temperature scaling (tau=0.04) (ablation) | DREAM · CiteSeer (30% uniform noise) | accuracy (%): 56.59 -> 71.06 | Improved |
| add temperature scaling (tau=0.04) (ablation) | DREAM · Cora (30% uniform noise) | accuracy (%): 71.78 -> 80.40 | Improved |
| add temperature scaling (tau=0.04) (ablation) | DREAM · PubMed (30% uniform noise) | accuracy (%): 66.35 -> 71.75 | Improved |
| restrict anchors to precomputed candidate sets (ablation) | DREAM · Cora (30% uniform noise) | accuracy (%): 75.81 -> 80.40 | Improved |
| restrict anchors to precomputed candidate sets (ablation) | DREAM · CiteSeer (30% uniform noise) | accuracy (%): 65.96 -> 71.06 | Improved |
| select anchors from each candidate set separately instead of their union (ablation) | DREAM · Cora (30% uniform noise) | accuracy (%): 74.77 -> 80.40 | Improved |
| select anchors from each candidate set separately instead of their union (ablation) | DREAM · PubMed (30% uniform noise) | accuracy (%): 70.62 -> 71.75 | Improved |
| add topology-aware anchors (ablation) | DREAM · PubMed (30% uniform noise) | accuracy (%): 71.48 -> 71.75 | Improved |
Closest papers by meaning
- NoisyGL: A Comprehensive Benchmark for Graph Neural Networks under Label Noise (NeurIPS 2024 · similarity 0.89)
- NoiseHGNN: Synthesized Similarity Graph-Based Neural Network for Noised Heterogeneous Graph Representation Learning (AAAI 2025 · similarity 0.88)
- Mitigating Label Noise on Graphs via Topological Sample Selection (ICML 2024 · similarity 0.87)
- Label-free Node Classification on Graphs with Large Language Models (LLMs) (ICLR 2024 · similarity 0.86)
- HeterSEED: Semantics–Structure Decoupling for Heterogeneous Graph Learning under Heterophily (NeurIPS 2026 · similarity 0.86)
- HGDL: Heterogeneous Graph Label Distribution Learning (NeurIPS 2024 · similarity 0.86)
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.
