# Improving Few-Shot Generalization by Exploring and Exploiting Auxiliary Data

arXiv: https://arxiv.org/abs/2302.00674 · HTML: https://mlsanity.com/paper/2302.00674/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 77 references that are in the map.
- First posted on arXiv 1 Feb 2023.

## Builds on (most cited first, 30 of 44)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [Adafactor: Adaptive Learning Rates with Sublinear Memory Cost](https://mlsanity.com/paper/1804.04235/) (2018)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [Adversarial NLI: A New Benchmark for Natural Language Understanding](https://mlsanity.com/paper/1910.14599/) (2019)
- [OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework](https://mlsanity.com/paper/2202.03052/) (2022)
- [Beyond neural scaling laws: beating power law scaling via data pruning](https://mlsanity.com/paper/2206.14486/) (2022)
- [Generalizing from a Few Examples: A Survey on Few-Shot Learning](https://mlsanity.com/paper/1904.05046/) (2019)
- [WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations](https://mlsanity.com/paper/1808.09121/) (2018)
- [True Few-Shot Learning with Language Models](https://mlsanity.com/paper/2105.11447/) (2021)
- [PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts](https://mlsanity.com/paper/2202.01279/) (2022)
- [Automated Curriculum Learning for Neural Networks](https://mlsanity.com/paper/1704.03003/) (2017)
- [The Natural Language Decathlon: Multitask Learning as Question Answering](https://mlsanity.com/paper/1806.08730/) (2018)
- [Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data Tasks](https://mlsanity.com/paper/1811.01088/) (2018)
- [Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index](https://mlsanity.com/paper/1308.3052/) (2013)
- [Muppet: Massive Multi-task Representations with Pre-Finetuning](https://mlsanity.com/paper/2101.11038/) (2021)
- [Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models](https://mlsanity.com/paper/2010.05874/) (2020)
- [ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning](https://mlsanity.com/paper/2111.10952/) (2021)
- [Exploring and Predicting Transferability across NLP Tasks](https://mlsanity.com/paper/2005.00770/) (2020)
- [Intermediate-Task Transfer Learning with Pretrained Models for Natural Language Understanding: When and Why Does It Work?](https://mlsanity.com/paper/2005.00628/) (2020)
- [Understanding and Improving Information Transfer in Multi-Task Learning](https://mlsanity.com/paper/2005.00944/) (2020)
- [Adapting Auxiliary Losses Using Gradient Similarity](https://mlsanity.com/paper/1812.02224/) (2018)
- [Learning from Few Examples: A Summary of Approaches to Few-Shot Learning](https://mlsanity.com/paper/2203.04291/) (2022)
- [Self-Supervised Meta-Learning for Few-Shot Natural Language Classification Tasks](https://mlsanity.com/paper/2009.08445/) (2020)
- [Auxiliary Learning by Implicit Differentiation](https://mlsanity.com/paper/2007.02693/) (2020)

## Built on by (most cited first, 13 of 13)

- [TIES-Merging: Resolving Interference When Merging Models](https://mlsanity.com/paper/2306.01708/) (2023)
- [A Pretrainer's Guide to Training Data: Measuring the Effects of Data Age, Domain Coverage, Quality, & Toxicity](https://mlsanity.com/paper/2305.13169/) (2023)
- [Generative Reward Models](https://mlsanity.com/paper/2410.12832/) (2024)
- [Efficient Online Data Mixing For Language Model Pre-Training](https://mlsanity.com/paper/2312.02406/) (2023)
- [Harnessing Diversity for Important Data Selection in Pretraining Large Language Models](https://mlsanity.com/paper/2409.16986/) (2024)
- [Advanced Large Language Model (LLM)-Driven Verilog Development: Enhancing Power, Performance, and Area Optimization in Code Synthesis](https://mlsanity.com/paper/2312.01022/) (2023)
- [FaithUn: Toward Faithful Forgetting in Language Models by Investigating the Interconnectedness of Knowledge](https://mlsanity.com/paper/2502.19207/) (2025)
- [Forgetting: A New Mechanism Towards Better Large Language Model Fine-tuning](https://mlsanity.com/paper/2508.04329/) (2025)
- [Balancing Label Quantity and Quality for Scalable Elicitation](https://mlsanity.com/paper/2410.13215/) (2024)
- [Evaluation of Few-Shot Learning for Classification Tasks in the Polish Language](https://mlsanity.com/paper/2404.17832/) (2024)
- [Adapting Foundation Models for Few-Shot Medical Image Segmentation: Actively and Sequentially](https://mlsanity.com/paper/2502.01000/) (2025)
- [Hierarchical Relation-augmented Representation Generalization for Few-shot Action Recognition](https://mlsanity.com/paper/2504.10079/) (2025)
- [BD-Merging: Bias-Aware Dynamic Model Merging with Evidence-Guided Contrastive Learning](https://mlsanity.com/paper/2603.03920/) (2026)

## Abstract (arXiv)

Few-shot learning is valuable in many real-world applications, but learning a generalizable model without overfitting to the few labeled datapoints is challenging. In this work, we focus on Few-shot Learning with Auxiliary Data (FLAD), a training paradigm that assumes access to auxiliary data during few-shot learning in hopes of improving generalization. Previous works have proposed automated methods for mixing auxiliary and target data, but these methods typically scale linearly (or worse) with the number of auxiliary datasets, limiting their practicality. In this work we relate FLAD to the explore-exploit dilemma that is central to the multi-armed bandit setting and derive algorithms whose computational complexity is independent of the number of auxiliary datasets, allowing us to scale to 100x more auxiliary datasets than prior methods. We propose two algorithms -- EXP3-FLAD and UCB1-FLAD -- and compare them with prior FLAD methods that either explore or exploit, finding that the combination of exploration and exploitation is crucial. Through extensive experimentation we find that our methods outperform all pre-existing FLAD methods by 4% and lead to the first 3 billion parameter language models that outperform the 175 billion parameter GPT-3. Overall, our work suggests that the discovery of better, more efficient mixing strategies for FLAD may provide a viable path towards substantially improving generalization in few-shot learning.