Research map / Label-efficient and robust learning / Recognition and long-tail
Fairness-aware News Recommendation with Decomposed Adversarial Learning
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 |
|---|---|---|---|
| Use decomposed adversarial learning with orthogonality regularization and rank using the bias-free embedding | NRMS-based news recommendation · Gender fairness, Top 10 | Accuracy: 70.12$\pm$0.59 -> 53.40$\pm$0.48 | Helped |
| Use decomposed adversarial learning with orthogonality regularization and rank using the bias-free embedding | NRMS-based news recommendation · News recommendation test sessions | AUC: 62.89$\pm$0.22 -> 61.95$\pm$0.22 | Hurt |
| Remove attribute prediction from the bias-aware embedding (ablation) | FairRec · Gender fairness, Top 10 | Fairness | Hurt |
| Add attribute prediction to the bias-aware embedding (ablation) | FairRec · Gender fairness, Top 10 | Fairness | Helped |
| Remove adversarial learning from the bias-free embedding (ablation) | FairRec · Gender fairness, Top 10 | Fairness | Hurt |
| Add adversarial learning to the bias-free embedding (ablation) | FairRec · Gender fairness, Top 10 | Fairness | Helped |
| Remove orthogonality regularization between the bias-aware and bias-free embeddings (ablation) | FairRec · Gender fairness, Top 10 | Fairness | Hurt |
| Add orthogonality regularization between the bias-aware and bias-free embeddings (ablation) | FairRec · Gender fairness, Top 10 | Fairness | Helped |
| Increase the attribute-prediction loss coefficient from zero to a moderate value | FairRec · Gender fairness, Top 10 | Fairness: 0.5 | Helped |
| Set the attribute-prediction loss coefficient above 0.5 | FairRec · News recommendation | Performance: 0.5 | Hurt |
| Increase the orthogonality-loss coefficient | FairRec · Gender fairness, Top 10 | Fairness: 0.3-0.6 | Helped |
| Set the adversarial-loss coefficient too small or too large | FairRec · Gender fairness, Top 10 | Fairness | Hurt |
Closest papers by meaning
- No Prejudice! Fair Federated Graph Neural Networks for Personalized Recommendation (AAAI 2024 · similarity 0.83)
- Towards S²-Challenges Underlying LLM-Based Augmentation for Personalized News Recommendation (AAAI 2025 · similarity 0.82)
- FairSIN: Achieving Fairness in Graph Neural Networks through Sensitive Information Neutralization (AAAI 2024 · similarity 0.81)
- FACTER: Fairness-Aware Conformal Thresholding and Prompt Engineering for Enabling Fair LLM-Based Recommender Systems (ICML 2025 · similarity 0.81)
- Adversarial Fairness Network (AAAI 2024 · similarity 0.81)
- MABR: Multilayer Adversarial Bias Removal Without Prior Bias Knowledge (AAAI 2025 · similarity 0.81)
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.