Research map / Adversarial robustness and security / Certified and empirical robustness
Invariant Representations without Adversarial Training
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 a direct mutual-information penalty and conditional decoder instead of adversarial training | Fair prediction methods · German | predictive accuracy | No clear effect |
| Use a direct mutual-information penalty and conditional decoder instead of adversarial training | Fair prediction methods · German | adversarial error | No clear effect |
| Use a direct mutual-information penalty and conditional decoder instead of adversarial training | Fair prediction methods · Adult | predictive accuracy | No clear effect |
| Use a direct mutual-information penalty and conditional decoder instead of adversarial training | Fair prediction methods · Adult | adversarial error | Helped |
| Use the proposed invariant representation rather than either baseline | Latent-code class separation · Adult t-SNE visualization | class mixing | Helped |
Closest papers by meaning
- Controllable Invariance through Adversarial Feature Learning (NeurIPS 2017 · similarity 0.93)
- Unsupervised Adversarial Invariance (NeurIPS 2018 · similarity 0.91)
- Invariant Representations through Adversarial Forgetting (AAAI 2020 · similarity 0.90)
- Unsupervised Representation Learning - an Invariant Risk Minimization Perspective (ICLR 2026 · similarity 0.89)
- Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off (ICLR 2025 · similarity 0.89)
- Deep invariant networks with differentiable augmentation layers (NeurIPS 2022 · similarity 0.88)
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.