Introduces the first active learning framework for unaligned multimodal data that selects alignments using uncertainty and diversity to cut annotation costs by up to 40% on benchmarks while preserving accuracy.
Dataset pruning: Reducing training data by examining generalization influence.arXiv preprint arXiv:2205.09329
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
REGLU guides LoRA-based unlearning via representation subspaces and orthogonal regularization to outperform prior methods on forget-retain trade-off in LLM benchmarks.
Electronic structure datasets across materials show high redundancy from low intrinsic dimensionality, allowing pruning to 1/100th size with preserved chemical accuracy.
SalUn uses gradient-based weight saliency to achieve effective machine unlearning of data, classes, or concepts in image classification and generation, narrowing the gap to exact retraining.
Adaptive Data Dropout uses performance feedback to dynamically modulate training data exposure, reducing effective steps while matching static dropout accuracy on image benchmarks.
citing papers explorer
-
Representation-Guided Parameter-Efficient LLM Unlearning
REGLU guides LoRA-based unlearning via representation subspaces and orthogonal regularization to outperform prior methods on forget-retain trade-off in LLM benchmarks.
-
Adaptive Data Dropout: Towards Self-Regulated Learning in Deep Neural Networks
Adaptive Data Dropout uses performance feedback to dynamically modulate training data exposure, reducing effective steps while matching static dropout accuracy on image benchmarks.