Research map / Label-efficient and robust learning / Recognition and long-tail
Towards Reliable Learning in the Wild: Generalization and Adaptation
Huaxiu Yao
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
An AAAI-24 new-faculty/doctoral-style talk abstract summarizing the author's research on reliable ML under distribution shift, covering spurious-correlation mitigation, compositional adaptation with limited supervision, and interdisciplinary applications.
Problem
Machine learning systems degrade when data distributions and tasks shift between training and deployment, and they struggle to generalize or adapt to new environments with limited supervision.
Approach
Position the research agenda as building ML systems that acquire shared knowledge across environments and tasks and adapt to new ones with limited supervision, summarizing prior methods rather than introducing a new one.
Limitations
- Abstract-only talk summary; no experimental details or quantitative results are provided
Closest papers by meaning
- LOG: Active Model Adaptation for Label-Efficient OOD Generalization (NeurIPS 2022 · similarity 0.87)
- Estimating Generalization under Distribution Shifts via Domain-Invariant Representations (ICML 2020 · similarity 0.87)
- An Information-theoretic Approach to Distribution Shifts (NeurIPS 2021 · similarity 0.87)
- Explore and Exploit the Diverse Knowledge in Model Zoo for Domain Generalization (ICML 2023 · similarity 0.86)
- Adaptive Risk Minimization: Learning to Adapt to Domain Shift (NeurIPS 2021 · similarity 0.86)
- When to retrain a machine learning model (ICML 2025 · 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.
