mlsanityData to 7 Oct 2026

MODE: Multi-Objective Adaptive Coreset Selection

arXiv 2512.21152 ↗First posted 24 Dec 2025cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

We present Mode(Multi-Objective adaptive Data Efficiency), a framework that dynamically combines coreset selection strategies based on their evolving contribution to model performance. Unlike static methods, mode adapts selection criteria to training phases: emphasizing class balance early, diversity during representation learning, and uncertainty at convergence. We show that MODE achieves (1-1/e)-approximation with O(n log n) complexity and demonstrates competitive accuracy while providing interpretable insights into data utility evolution. Experiments show mode reduces memory requirements

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 16 of its 26 references that are in the map. First posted on arXiv 24 Dec 2025.

Builds on

16 of 26 references.

References · 16

  1. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2019Searching for MobileNetV3cited by 1,984
  5. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  6. 2020Meta-Learning in Neural Networks: A Surveycited by 944
  7. 2018An Empirical Study of Example Forgetting during Deep Neural Network Learningcited by 669
  8. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  9. 2021GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Trainingcited by 269
  10. 2021Curriculum Learning: A Surveycited by 257
  11. 2017Learning Active Learning from Datacited by 100
  12. 2021RETRIEVE: Coreset Selection for Efficient and Robust Semi-Supervised Learningcited by 72
4 more
  1. 2021PRISM: A Rich Class of Parameterized Submodular Information Measures for Guided Subset Selectioncited by 50
  2. 2023Towards Sustainable Learning: Coresets for Data-efficient Deep Learningcited by 44
  3. 2022Information-theoretic Online Memory Selection for Continual Learningcited by 42
  4. 2019Coresets for Data-efficient Training of Machine Learning Modelscited by 9

Built on by

Not cited yet.