Research map / Label-efficient and robust learning / Recognition and long-tail
Towards Debiasing DNN Models from Spurious Feature Influence
Mengnan Du, Ruixiang Tang, Weijie Fu, Xia Hu
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 |
|---|---|---|---|
| Counter-teach the student using a bias-only race teacher | MEPS MLP · MEPS (race) | demographic parity: 0.857 -> 0.950 | Improved |
| Counter-teach the student using a bias-only race teacher | MEPS MLP · MEPS (race) | equality of opportunity: -0.195 -> -0.057 | Improved |
| Counter-teach the student using a bias-only race teacher | MEPS MLP · MEPS (race) | equality of odds: -0.243 -> -0.070 | Improved |
| Counter-teach the student using a bias-only race teacher | MEPS MLP · MEPS (gender) | equality of opportunity: -0.052 -> -0.081 | Hurt |
| Train separate teachers for race and gender | MEPS MLP · MEPS (race and gender) | equality of odds: Race: -0.243 -> -0.076; gender: -0.076 -> -0.036 | Improved |
| Train separate teachers for race and gender | MEPS MLP · MEPS | accuracy: 86.5 -> 84.2 | Hurt |
| Add explicit interpretation decorrelation (ablation) | DeFI on MEPS · MEPS (race) | demographic parity: 0.857 -> 0.956 | Improved |
| Add explicit interpretation decorrelation (ablation) | DeFI on MEPS · MEPS (race) | equality of opportunity: -0.195 -> -0.061 | Improved |
| Add explicit interpretation decorrelation (ablation) | DeFI on MEPS · MEPS | accuracy: 86.5 -> 84.3 | Hurt |
| Add implicit ensemble decorrelation (ablation) | DeFI on MEPS · MEPS (race) | equality of opportunity: -0.195 -> -0.037 | Improved |
| Add implicit ensemble decorrelation (ablation) | DeFI on MEPS · MEPS | accuracy: 86.5 -> 86.0 | No clear effect |
Closest papers by meaning
- Adversarial Fairness Network (AAAI 2024 · similarity 0.90)
- On the Fairness ROAD: Robust Optimization for Adversarial Debiasing (ICLR 2024 · similarity 0.88)
- FairNet: Dynamic Fairness Correction without Performance Loss via Contrastive Conditional LoRA (NeurIPS 2025 · similarity 0.88)
- FairSIN: Achieving Fairness in Graph Neural Networks through Sensitive Information Neutralization (AAAI 2024 · similarity 0.87)
- On the Alignment between Fairness and Accuracy: from the Perspective of Adversarial Robustness (ICML 2025 · similarity 0.87)
- Fairness without Demographics through Shared Latent Space-Based Debiasing (AAAI 2024 · 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.
