Research map / Graph learning / Graph self-supervised learning
Self-Supervised Graph Learning for Long-Tailed Cognitive Diagnosis
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 self-supervised graph contrastive learning with importance-based edge dropout | RCD-style graph cognitive diagnosis · ASSIST, 5:5; 6:4; 7:3; 8:2 | ACC50: 71.06 -> 73.00; 72.06 -> 73.08; 72.18 -> 73.15; 71.93 -> 72.94 | Helped |
| add self-supervised graph contrastive learning with importance-based edge dropout | RCD-style graph cognitive diagnosis · junyi, 5:5; 6:4; 7:3; 8:2 | ACC50: 77.21 -> 77.75; 77.31 -> 77.88; 77.83 -> 78.41; 77.96 -> 78.44 | Helped |
| replace importance-based edge dropout with equal-probability random edge dropout (ablation) | SCD · ASSIST and junyi, all four train:test splits | ACC50: 71.17 vs 73.00; 72.07 vs 73.08; 72.04 vs 73.15; 72.04 vs 72.94; 77.12 vs 77.75; 77.35 vs 77.88; 77.85 vs 78.41; 77.97 vs | Hurt |
| add self-supervised learning to the graph diagnosis model | RCD · students with few interactions, including groups 0-5 and 5-10 | student performance | Helped |
Closest papers by meaning
- DisenGCD: A Meta Multigraph-assisted Disentangled Graph Learning Framework for Cognitive Diagnosis (NeurIPS 2024 · similarity 0.88)
- Symbolic Cognitive Diagnosis via Hybrid Optimization for Intelligent Education Systems (AAAI 2024 · similarity 0.85)
- Zero-1-to-3: Domain-Level Zero-Shot Cognitive Diagnosis via One Batch of Early-Bird Students towards Three Diagnostic Objectives (AAAI 2024 · similarity 0.85)
- Collaborative Cognitive Diagnosis with Disentangled Representation Learning for Learner Modeling (NeurIPS 2024 · similarity 0.85)
- AD4CD: Causal-Guided Anomaly Detection for Enhancing Cognitive Diagnosis (AAAI 2025 · similarity 0.85)
- Towards Accurate and Fair Cognitive Diagnosis via Monotonic Data Augmentation (NeurIPS 2024 · 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.