Research map / Graph learning / Graph self-supervised learning
Fair Attribute Completion on Graph with Missing Attributes
Dongliang Guo, Zhixuan Chu, Sheng Li
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 FairAC attention-based attribute completion with adversarial fairness losses (vs. BaseAC without them) (ablation) | GCN on Pokec-z · Pokec-z, alpha=0.3 | ΔSP+ΔEO: 2.35 -> 0.31 | Improved |
| Add adversarial fairness losses to attribute completion (BaseAC to FairAC) (ablation) | GCN on Pokec-z · Pokec-z, alpha=0.8 | ΔSP+ΔEO: 2.28 -> 0.70 | Improved |
| Use FairAC completion with fairness losses instead of average-neighbor completion | GCN · NBA | ΔSP+ΔEO: 6.16 -> 0.91 | Improved |
| Use FairAC instead of FairGNN on incomplete attributes | GCN · Pokec-z, Pokec-n, NBA | ΔSP+ΔEO: Pokec-z 2.58 -> 0.31; Pokec-n 1.24 -> 0.41; NBA 2.58 -> 0.91 | Improved |
| Increase beta (fairness trade-off weight) from 0 to 0.8 (ablation) | FairAC · Pokec-z, alpha=0.3 | accuracy: slight decline | Hurt |
| Increase beta from 0 to 0.8 (ablation) | FairAC · Pokec-z, alpha=0.3 | ΔSP+ΔEO | Improved |
| Integrate FairAC with GAT on Pokec-n | GAT · Pokec-n, alpha=0.7 | ΔSP+ΔEO: 10.84 -> 4.37 | Improved |
Closest papers by meaning
- FairSIN: Achieving Fairness in Graph Neural Networks through Sensitive Information Neutralization (AAAI 2024 · similarity 0.87)
- Fair Graph U-Net: A Fair Graph Learning Framework Integrating Group and Individual Awareness (AAAI 2025 · similarity 0.86)
- Chasing Fairness in Graphs: A GNN Architecture Perspective (AAAI 2024 · similarity 0.85)
- Reproducibility Study Of Learning Fair Graph Representations Via Automated Data Augmentations (NeurIPS 2024 · similarity 0.85)
- FairGP: A Scalable and Fair Graph Transformer Using Graph Partitioning (AAAI 2025 · similarity 0.85)
- FairWire: Fair Graph Generation (NeurIPS 2024 · similarity 0.84)
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.
