Research map / Learning theory and algorithms / Prediction and decision losses
Extreme Classification via Adversarial Softmax Approximation
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 |
|---|---|---|---|
| Sample negatives conditionally from an adversarial auxiliary model instead of using uniform or frequency-based negative sampling | Adversarial negative sampling · Wikipedia-500K and Amazon-670K | predictive accuracy | Helped |
| Sample negatives conditionally from an adversarial auxiliary model instead of using uniform or frequency-based negative sampling | Adversarial negative sampling · Amazon-670K | predictive log likelihood | Mixed |
| Use uniform negative sampling instead of full softmax classification | Affine linear classifier · EURLex-4K test | accuracy: 33.6% -> 26.4% | Hurt |
| Use adversarial negative sampling rather than the evaluated baselines | Adversarial negative sampling · Wikipedia-500K and Amazon-670K | training speed | Helped |
Closest papers by meaning
- A Tale of Two Efficient and Informative Negative Sampling Distributions (ICML 2021 · similarity 0.90)
- A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks (NeurIPS 2018 · similarity 0.88)
- Kernel Learning with Adversarial Features: Numerical Efficiency and Adaptive Regularization (NeurIPS 2025 · similarity 0.86)
- $\epsilon$-Softmax: Approximating One-Hot Vectors for Mitigating Label Noise (NeurIPS 2024 · similarity 0.86)
- Revisiting Adversarial Training Under Long-Tailed Distributions (CVPR 2024 · similarity 0.86)
- Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data (ICLR 2025 · 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.