AI Paper Atlas

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

ICML 2026 · Graph learning › Graph self-supervised learning · approach: LLMs and graph foundation models

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
add MFS feature-coverage term (ablation)HIAL · Citeseeraccuracy: 55.78 -> 61.55Improved
add MFS feature-coverage term (ablation)HIAL · PubMedaccuracy: 72.45 -> 76.14Improved
add ESR structural reachability term (ablation)HIAL · DBLPaccuracy: 75.66 -> 78.41Improved
add ESR structural reachability term (ablation)HIAL · Citeseeraccuracy: 60.22 -> 61.55Improved
add HOI-aware propagation (ablation)HIAL · DBLPaccuracy: 66.75 -> 78.41Improved
add HOI-aware propagation (ablation)HIAL · Coraaccuracy: 68.84 -> 72.97Improved
add inverse-cardinality weighting to clique expansion (ablation)CE + residual propagation · Citeseer, B=5Caccuracy: 34.21 -> 40.70Improved
add semantic consistency weighting to clique expansion (ablation)CE + residual propagation · Citeseer, B=5Caccuracy: 34.21 -> 44.60Improved
combine both corrections (HOIP) instead of clique expansion (ablation)CE + residual propagation · Citeseer, B=5Caccuracy: 34.21 -> 46.90Improved
use HOIP instead of clique expansion with residual (ablation)propagation · PubMed, B=10Caccuracy: 69.48 -> 72.99Improved
replace uniform clique expansion with HOIP in ESR scoring (ablation)ESR scoring · CoraStructural Bias Coefficient: 0.9988 -> 0.8856Improved
use HOIP propagation instead of HGNN propagation matrix (ablation)HIAL selection · Coraaccuracy: 70.95 -> 72.97Improved

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.

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

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