REVIEW 4 cited by
Curriculum Learning: A Survey
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Training machine learning models in a meaningful order, from the easy samples to the hard ones, using curriculum learning can provide performance improvements over the standard training approach based on random data shuffling, without any additional computational costs. Curriculum learning strategies have been successfully employed in all areas of machine learning, in a wide range of tasks. However, the necessity of finding a way to rank the samples from easy to hard, as well as the right pacing function for introducing more difficult data can limit the usage of the curriculum approaches. In this survey, we show how these limits have been tackled in the literature, and we present different curriculum learning instantiations for various tasks in machine learning. We construct a multi-perspective taxonomy of curriculum learning approaches by hand, considering various classification criteria. We further build a hierarchical tree of curriculum learning methods using an agglomerative clustering algorithm, linking the discovered clusters with our taxonomy. At the end, we provide some interesting directions for future work.
Forward citations
Cited by 4 Pith papers
-
Pretraining Curricula Enable Selective Fine-tuning
Imbalanced pretraining curricula disentangle task circuits in transformers, improving in-context learning and the selectivity of refusal fine-tuning relative to balanced training.
-
Simulation-based inference using splitting schemes for partially observed diffusions in chemical reaction networks
Chemical Langevin equations are rewritten as perturbed CIR-type SDEs, enabling a structure-preserving splitting scheme and an ABC-SMC algorithm for inference on partially observed reaction networks.
-
Surrogate models for Rock-Fluid Interaction: A Grid-Size-Invariant Approach
Fully convolutional surrogate models trained on 64×64 patches predict 256×256 reactive-flow fields with competitive accuracy and lower GPU memory than full-domain or reduced-order models.
-
Your Pretrained Model Tells the Difficulty Itself: A Self-Adaptive Curriculum Learning Paradigm for Natural Language Understanding
The paper proposes six curriculum sampling strategies driven by a pretrained language model's own prompt-based confidence scores and reports mixed, mostly small, improvements over random sampling on four NLU datasets.
Discussion (0). Sign in to comment.