mlsanityData to 7 Oct 2026

Active Few-Shot Fine-Tuning

arXiv 2402.15441 ↗First posted 13 Feb 2024cs.LG cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

We study the question: How can we select the right data for fine-tuning to a specific task? We call this data selection problem active fine-tuning and show that it is an instance of transductive active learning, a novel generalization of classical active learning. We propose ITL, short for information-based transductive learning, an approach which samples adaptively to maximize information gained about the specified task. We are the first to show, under general regularity assumptions, that such decision rules converge uniformly to the smallest possible uncertainty obtainable from the accessible data. We apply ITL to the few-shot fine-tuning of large neural networks and show that fine-tuning with ITL learns the task with significantly fewer examples than the state-of-the-art.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 64 of its 115 references that are in the map. First posted on arXiv 13 Feb 2024.

Builds on

64 of 115 references.

References · 64

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  5. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  6. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,597
  7. 2017Billion-scale similarity search with GPUscited by 2,477
  8. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  9. 2016Matching Networks for One Shot Learningcited by 2,246
  10. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
  11. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  12. 2015Optimizing Neural Networks with Kronecker-factored Approximate Curvaturecited by 776
38 more
  1. 2019Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descentcited by 732
  2. 2017Deep Neural Networks as Gaussian Processescited by 617
  3. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  4. 2019On Exact Computation with an Infinitely Wide Neural Netcited by 572
  5. 2018Do Better ImageNet Models Transfer Better?cited by 560
  6. 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 555
  7. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 428
  8. 2017A Tutorial on Thompson Samplingcited by 420
  9. 2021Laplace Redux -- Effortless Bayesian Deep Learningcited by 359
  10. 2017On Kernelized Multi-armed Banditscited by 348
  11. 2021Curriculum Learning: A Surveycited by 257
  12. 2017Automated Curriculum Learning for Neural Networkscited by 251
  13. 2023A Cookbook of Self-Supervised Learningcited by 248
  14. 2022Surgical Fine-Tuning Improves Adaptation to Distribution Shiftscited by 205
  15. 2017Max-value Entropy Search for Efficient Bayesian Optimizationcited by 202
  16. 2014Predictive Entropy Search for Efficient Global Optimization of Black-box Functionscited by 201
  17. 2020On Information Gain and Regret Bounds in Gaussian Process Banditscited by 156
  18. 2018ANN-Benchmarks: A Benchmarking Tool for Approximate Nearest Neighbor Algorithmscited by 130
  19. 2022A Kernel-Based View of Language Model Fine-Tuningcited by 118
  20. 2022Coverage-centric Coreset Selection for High Pruning Ratescited by 115
  21. 2019Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Costcited by 114
  22. 2020Bayesian Deep Ensembles via the Neural Tangent Kernelcited by 90
  23. 2019Approximate Inference Turns Deep Networks into Gaussian Processescited by 89
  24. 2019Sequential Experimental Design for Transductive Linear Banditscited by 88
  25. 2022More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalizecited by 87
  26. 2021SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarioscited by 83
  27. 2017Deep Active Learning over the Long Tailcited by 82
  28. 2023Test-Time Training on Nearest Neighbors for Large Language Modelscited by 82
  29. 2021Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learningcited by 72
  30. 2023To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Reviewcited by 72
  31. 2015A Review of Feature Selection Methods Based on Mutual Informationcited by 67
  32. 2023Prediction-Oriented Bayesian Active Learningcited by 60
  33. 2022A Framework and Benchmark for Deep Batch Active Learning for Regressioncited by 47
  34. 2024Efficient Exploration for LLMscited by 44
  35. 2016Truncated Variance Reduction: A Unified Approach to Bayesian Optimization and Level-Set Estimationcited by 40
  36. 2021Neural Contextual Bandits without Regretcited by 40
  37. 2022Active Learning Helps Pretrained Models Learn the Intended Taskcited by 33
  38. 2022Adapting the Linearised Laplace Model Evidence for Modern Deep Learningcited by 29

50 most cited of 64 All 64 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 1.

2 papers.

  1. 2026Expert-Guided Explainable Few-Shot Learning with Active Sample Selection for Medical Image Analysiscited by 3
  2. 2024Exploring the Potential of Conversational AI Support for Agent-Based Social Simulation Model Designcited by 2