JMLR 2021 papers on Label-efficient and robust learning
16 of the 285 papers published in JMLR 2021 (5.6%) are on Label-efficient and robust learning, compared with 6.9% at JMLR 2020. They fall into 5 topics.
See JMLR 2021 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Recognition and long-tail · 10 papers
- Explaining by Removing: A Unified Framework for Model Explanation (167 citations)
- Explaining Explanations: Axiomatic Feature Interactions for Deep Networks (96 citations)
- Alibi Explain: Algorithms for Explaining Machine Learning Models (79 citations)
- Dynamic Tensor Recommender Systems (24 citations)
- Interpretable Deep Generative Recommendation Models (9 citations)
- An Importance Weighted Feature Selection Stability Measure (8 citations)
- A General Framework for Adversarial Label Learning (5 citations)
- A flexible model-free prediction-based framework for feature ranking (4 citations)
- Factorization Machines with Regularization for Sparse Feature Interactions (4 citations)
- NEU: A Meta-Algorithm for Universal UAP-Invariant Feature Representation
