Research map / Graph learning / Graph self-supervised learning
HIAL: Towards Semantics-Aware Hypergraph Active Learning via Dual-Perspective Information Maximization
Yanheng Hou, Xunkai Li, Yanzhe Wen, Zhenjun Li, Bing Zhou, Rong-Hua Li, Guoren Wang
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 MFS feature-coverage term (ablation) | HIAL · Citeseer | accuracy: 55.78 -> 61.55 | Improved |
| add MFS feature-coverage term (ablation) | HIAL · PubMed | accuracy: 72.45 -> 76.14 | Improved |
| add ESR structural reachability term (ablation) | HIAL · DBLP | accuracy: 75.66 -> 78.41 | Improved |
| add ESR structural reachability term (ablation) | HIAL · Citeseer | accuracy: 60.22 -> 61.55 | Improved |
| add HOI-aware propagation (ablation) | HIAL · DBLP | accuracy: 66.75 -> 78.41 | Improved |
| add HOI-aware propagation (ablation) | HIAL · Cora | accuracy: 68.84 -> 72.97 | Improved |
| add inverse-cardinality weighting to clique expansion (ablation) | CE + residual propagation · Citeseer, B=5C | accuracy: 34.21 -> 40.70 | Improved |
| add semantic consistency weighting to clique expansion (ablation) | CE + residual propagation · Citeseer, B=5C | accuracy: 34.21 -> 44.60 | Improved |
| combine both corrections (HOIP) instead of clique expansion (ablation) | CE + residual propagation · Citeseer, B=5C | accuracy: 34.21 -> 46.90 | Improved |
| use HOIP instead of clique expansion with residual (ablation) | propagation · PubMed, B=10C | accuracy: 69.48 -> 72.99 | Improved |
| replace uniform clique expansion with HOIP in ESR scoring (ablation) | ESR scoring · Cora | Structural Bias Coefficient: 0.9988 -> 0.8856 | Improved |
| use HOIP propagation instead of HGNN propagation matrix (ablation) | HIAL selection · Cora | accuracy: 70.95 -> 72.97 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- GRAIN — GRAIN: Multi-Granular and Implicit Information Aggregation Graph Neural Network for Heterophilous Graphs (AAAI 2025) · better on 8 of 8 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- HyperMixup: Hypergraph-Augmented with Higher-order Information Mixup (NeurIPS 2025 · similarity 0.90)
- SPHINX: Structural Prediction using Hypergraph Inference Network (ICML 2025 · similarity 0.89)
- MC-HNN: Learning Latent Structural Semantics and High-Rank Representations for Hypergraph Neural Networks (ICML 2026 · similarity 0.89)
- Training-Free Message Passing for Learning on Hypergraphs (ICLR 2025 · similarity 0.89)
- PANDA: Prior-guided Attentional Dual-path Architecture (NeurIPS 2026 · similarity 0.87)
- When Hypergraph Meets Heterophily: New Benchmark Datasets and Baseline (AAAI 2025 · similarity 0.87)
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.
