Research map / Label-efficient and robust learning / Recognition and long-tail
Memorizing Long-tail Data Can Help Generalization Through Composition
Mo Zhou, Haoyang Ma, Rong Ge
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 |
|---|---|---|---|
| allow memorization (WD 0 instead of 0.5) (ablation) | Sum ResNet-18 · Omniglot-once + MNIST digit-sum | test loss: 2.8744 -> 0.1760 | Improved |
| allow memorization (WD 0 instead of 0.5) (ablation) | Linear ResNet-18 · Omniglot-once + MNIST digit-sum | test loss: 1.5539 -> 0.1662 | Improved |
| allow memorization (WD 0 instead of 0.5) (ablation) | 2-layer ResNet-18 · Omniglot-once + MNIST digit-sum | test loss: 0.6447 -> 0.1351 | Improved |
| allow memorization (WD 0 instead of 0.5) (ablation) | Cross-channel ResNet-18 · Omniglot-once + MNIST digit-sum | test loss: 23.6506 -> 22.9671 | No clear effect |
| process each digit separately then aggregate, instead of cross-channel ResNet (ablation) | ResNet-18 · Heavy-tailed MNIST digit-sum, test with at least one 9 | test loss | Improved |
| rare-feature frequency alpha=1 (long-tail features appear more often) (ablation) | minimum l2-norm linear model · Synthetic linear model | in/out-of-distribution test loss | Hurt |
Closest papers by meaning
- The Pitfalls of Memorization: When Memorization Hurts Generalization (ICLR 2025 · similarity 0.89)
- How Spurious Features are Memorized: Precise Analysis for Random and NTK Features (ICML 2024 · similarity 0.89)
- Unveiling Memorization–Generalization Coexistence: A Case Study on Arithmetic Tasks with Label Noise (NeurIPS 2026 · similarity 0.87)
- To Grok or not to Grok: Disentangling Generalization and Memorization on Corrupted Algorithmic Datasets (ICLR 2024 · similarity 0.87)
- When does compositional structure yield compositional generalization? A kernel theory. (ICLR 2025 · similarity 0.87)
- A mathematical theory of balancing relational generalization and memorization (NeurIPS 2026 · similarity 0.86)
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.
