# Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learning

arXiv: https://arxiv.org/abs/2104.08808 · HTML: https://mlsanity.com/paper/2104.08808/

## Key facts

- Cited by 35 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 18 Apr 2021.

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

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [Adversarial NLI: A New Benchmark for Natural Language Understanding](https://mlsanity.com/paper/1910.14599/) (2019)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Progress & Compress: A scalable framework for continual learning](https://mlsanity.com/paper/1805.06370/) (2018)
- [TabFact: A Large-scale Dataset for Table-based Fact Verification](https://mlsanity.com/paper/1909.02164/) (2019)
- [TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification](https://mlsanity.com/paper/2010.12421/) (2020)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [PAWS: Paraphrase Adversaries from Word Scrambling](https://mlsanity.com/paper/1904.01130/) (2019)
- [Dynamic Few-Shot Visual Learning without Forgetting](https://mlsanity.com/paper/1804.09458/) (2018)
- [WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations](https://mlsanity.com/paper/1808.09121/) (2018)
- ["Liar, Liar Pants on Fire": A New Benchmark Dataset for Fake News Detection](https://mlsanity.com/paper/1705.00648/) (2017)
- [Variational Continual Learning](https://mlsanity.com/paper/1710.10628/) (2017)
- [Good Debt or Bad Debt: Detecting Semantic Orientations in Economic Texts](https://mlsanity.com/paper/1307.5336/) (2013)
- [Continual learning with hypernetworks](https://mlsanity.com/paper/1906.00695/) (2019)
- [The Natural Language Decathlon: Multitask Learning as Question Answering](https://mlsanity.com/paper/1806.08730/) (2018)
- [Explainable Automated Fact-Checking for Public Health Claims](https://mlsanity.com/paper/2010.09926/) (2020)
- [Episodic Memory in Lifelong Language Learning](https://mlsanity.com/paper/1906.01076/) (2019)

## Built on by (most cited first, 30 of 35)

- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [Continual Learning of Natural Language Processing Tasks: A Survey](https://mlsanity.com/paper/2211.12701/) (2022)
- [CLiMB: A Continual Learning Benchmark for Vision-and-Language Tasks](https://mlsanity.com/paper/2206.09059/) (2022)
- [Lifelong Language Pretraining with Distribution-Specialized Experts](https://mlsanity.com/paper/2305.12281/) (2023)
- [Towards Lifelong Learning of Large Language Models: A Survey](https://mlsanity.com/paper/2406.06391/) (2024)
- [Recent Advances of Foundation Language Models-based Continual Learning: A Survey](https://mlsanity.com/paper/2405.18653/) (2024)
- [Continual Training of Language Models for Few-Shot Learning](https://mlsanity.com/paper/2210.05549/) (2022)
- [Continual Sequence Generation with Adaptive Compositional Modules](https://mlsanity.com/paper/2203.10652/) (2022)
- [Overcoming Catastrophic Forgetting in Massively Multilingual Continual Learning](https://mlsanity.com/paper/2305.16252/) (2023)
- [ConTinTin: Continual Learning from Task Instructions](https://mlsanity.com/paper/2203.08512/) (2022)
- [On Continual Model Refinement in Out-of-Distribution Data Streams](https://mlsanity.com/paper/2205.02014/) (2022)
- [Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack](https://mlsanity.com/paper/2407.16695/) (2024)
- [Carpe Diem: On the Evaluation of World Knowledge in Lifelong Language Models](https://mlsanity.com/paper/2311.08106/) (2023)
- [CL-MASR: A Continual Learning Benchmark for Multilingual ASR](https://mlsanity.com/paper/2310.16931/) (2023)
- [Knowledge Accumulation in Continually Learned Representations and the Issue of Feature Forgetting](https://mlsanity.com/paper/2304.00933/) (2023)
- [Continuous Detection, Rapidly React: Unseen Rumors Detection based on Continual Prompt-Tuning](https://mlsanity.com/paper/2203.11720/) (2022)
- [When Meta-Learning Meets Online and Continual Learning: A Survey](https://mlsanity.com/paper/2311.05241/) (2023)
- [Task-Attentive Transformer Architecture for Continual Learning of Vision-and-Language Tasks Using Knowledge Distillation](https://mlsanity.com/paper/2303.14423/) (2023)
- [LFS-GAN: Lifelong Few-Shot Image Generation](https://mlsanity.com/paper/2308.11917/) (2023)
- [Towards Anytime Fine-tuning: Continually Pre-trained Language Models with Hypernetwork Prompt](https://mlsanity.com/paper/2310.13024/) (2023)
- [Dynamic Transformer Architecture for Continual Learning of Multimodal Tasks](https://mlsanity.com/paper/2401.15275/) (2024)
- [Identification of Novel Classes for Improving Few-Shot Object Detection](https://mlsanity.com/paper/2303.10422/) (2023)
- [I2I: Initializing Adapters with Improvised Knowledge](https://mlsanity.com/paper/2304.02168/) (2023)
- [Nexus: Specialization meets Adaptability for Efficiently Training Mixture of Experts](https://mlsanity.com/paper/2408.15901/) (2024)
- [Improved Region Proposal Network for Enhanced Few-Shot Object Detection](https://mlsanity.com/paper/2308.07535/) (2023)
- [CluMo: Cluster-based Modality Fusion Prompt for Continual Learning in Visual Question Answering](https://mlsanity.com/paper/2408.11742/) (2024)
- [SimpLex: a lexical text simplification architecture](https://mlsanity.com/paper/2304.07002/) (2023)
- [Encoding Binary Concepts in the Latent Space of Generative Models for Enhancing Data Representation](https://mlsanity.com/paper/2303.12255/) (2023)
- [Towards a Unified Framework for Adaptable Problematic Content Detection via Continual Learning](https://mlsanity.com/paper/2309.16905/) (2023)

## Abstract (arXiv)

The ability to continuously expand knowledge over time and utilize it to rapidly generalize to new tasks is a key feature of human linguistic intelligence. Existing models that pursue rapid generalization to new tasks (e.g., few-shot learning methods), however, are mostly trained in a single shot on fixed datasets, unable to dynamically expand their knowledge; while continual learning algorithms are not specifically designed for rapid generalization. We present a new learning setup, Continual Learning of Few-Shot Learners (CLIF), to address the challenges of both learning settings in a unified setup. CLIF assumes a model learns from a sequence of diverse NLP tasks arriving sequentially, accumulating knowledge for improved generalization to new tasks, while also retaining performance on the tasks learned earlier. We examine how the generalization ability is affected in the continual learning setup, evaluate a number of continual learning algorithms, and propose a novel regularized adapter generation approach. We find that catastrophic forgetting affects generalization ability to a less degree than performance on seen tasks; while continual learning algorithms can still bring considerable benefit to the generalization ability.