mlsanityData to 7 Oct 2026

Avalanche: an End-to-End Library for Continual Learning

arXiv 2104.00405 ↗First posted 1 Apr 2021cs.LG cs.AI cs.CVcited by 124

Not on the map. Why?

Abstract (arXiv)

Learning continually from non-stationary data streams is a long-standing goal and a challenging problem in machine learning. Recently, we have witnessed a renewed and fast-growing interest in continual learning, especially within the deep learning community. However, algorithmic solutions are often difficult to re-implement, evaluate and port across different settings, where even results on standard benchmarks are hard to reproduce. In this work, we propose Avalanche, an open-source end-to-end library for continual learning research based on PyTorch. Avalanche is designed to provide a shared and collaborative codebase for fast prototyping, training, and reproducible evaluation of continual learning algorithms.

Key facts. Cited by 124 papers in the map (data through 7 Oct 2026). Builds on 37 of its 63 references that are in the map. First posted on arXiv 1 Apr 2021.

Builds on

37 of 63 references.

References · 37

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  3. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  4. 2016Learning without Forgettingcited by 2,465
  5. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  6. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  7. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,313
  8. 2018Efficient Lifelong Learning with A-GEMcited by 1,044
  9. 2013An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networkscited by 711
  10. 2018Overcoming catastrophic forgetting with hard attention to the taskcited by 672
  11. 2019Green AIcited by 620
  12. 2019Three scenarios for continual learningcited by 610
25 more
  1. 2018Progress & Compress: A scalable framework for continual learningcited by 516
  2. 2020Class-incremental learning: survey and performance evaluation on image classificationcited by 446
  3. 2020Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)cited by 318
  4. 2014Caffe: Convolutional Architecture for Fast Feature Embeddingcited by 287
  5. 2017CORe50: a New Dataset and Benchmark for Continuous Object Recognitioncited by 287
  6. 2020Towards Continual Reinforcement Learning: A Review and Perspectivescited by 268
  7. 2018Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselinescited by 228
  8. 2018Task-Free Continual Learningcited by 219
  9. 2020The Computational Limits of Deep Learningcited by 188
  10. 2020fastai: A Layered API for Deep Learningcited by 183
  11. 2018Dopamine: A Research Framework for Deep Reinforcement Learningcited by 121
  12. 2018Don't forget, there is more than forgetting: new metrics for Continual Learningcited by 113
  13. 2018Continuous Learning in Single-Incremental-Task Scenarioscited by 109
  14. 2018Generative replay with feedback connections as a general strategy for continual learningcited by 103
  15. 2019Latent Replay for Real-Time Continual Learningcited by 97
  16. 2019Continual Learning for Robotics: Definition, Framework, Learning Strategies, Opportunities and Challengescited by 92
  17. 2019A Step Toward Quantifying Independently Reproducible Machine Learning Researchcited by 77
  18. 2018ViZDoom Competitions: Playing Doom from Pixelscited by 50
  19. 2019Rehearsal-Free Continual Learning over Small Non-I.I.D. Batchescited by 46
  20. 2019A Unifying Bayesian View of Continual Learningcited by 38
  21. 2021Continual Learning for Recurrent Neural Networks: an Empirical Evaluationcited by 34
  22. 2021Continuum: Simple Management of Complex Continual Learning Scenarioscited by 33
  23. 2019OpenLORIS-Object: A Robotic Vision Dataset and Benchmark for Lifelong Deep Learningcited by 28
  24. 2019Continual Reinforcement Learning in 3D Non-stationary Environmentscited by 21
  25. 2020Online Continual Learning on Sequencescited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 18; 2022: 29; 2023: 37; 2024: 20; 2025: 14; 2026: 6.

124 papers.

Sort:

By area:

  1. 2022The CLEAR Benchmark: Continual LEArning on Real-World Imagerycited by 92
  2. 2022Continual Pre-Training Mitigates Forgetting in Language and Visioncited by 82
  3. 2021Rehearsal revealed: The limits and merits of revisiting samples in continual learningcited by 76
  4. 2022CLIP model is an Efficient Continual Learnercited by 64
  5. 2023PILOT: A Pre-Trained Model-Based Continual Learning Toolboxcited by 64
  6. 2021Continual Learning via Local Module Compositioncited by 61
  7. 2022Re-basin via implicit Sinkhorn differentiationcited by 61
  8. 2022Continual evaluation for lifelong learning: Identifying the stability gapcited by 55
  9. 2023Real-Time Evaluation in Online Continual Learning: A New Hopecited by 47
  10. 2023Recent Advances on Federated Learning: A Systematic Surveycited by 40
  11. 2021CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning Agentscited by 36
  12. 2023Avalanche: A PyTorch Library for Deep Continual Learningcited by 33
38 more
  1. 2022Sample Condensation in Online Continual Learningcited by 31
  2. 2023Task Arithmetic with LoRA for Continual Learningcited by 31
  3. 2021CLEVA-Compass: A Continual Learning EValuation Assessment Compass to Promote Research Transparency and Comparabilitycited by 28
  4. 2022LifeLonger: A Benchmark for Continual Disease Classificationcited by 28
  5. 2022Continual Object Detection: A review of definitions, strategies, and challengescited by 25
  6. 2021Optimizing Reusable Knowledge for Continual Learning via Metalearningcited by 24
  7. 2023Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomycited by 24
  8. 2023Overcoming Generic Knowledge Loss with Selective Parameter Updatecited by 23
  9. 2021Is Class-Incremental Enough for Continual Learning?cited by 22
  10. 2021Continual Learning at the Edge: Real-Time Training on Smartphone Devicescited by 20
  11. 2022Technical Report for ICCV 2021 Challenge SSLAD-Track3B: Transformers Are Better Continual Learnerscited by 20
  12. 2021Sequoia: A Software Framework to Unify Continual Learning Researchcited by 19
  13. 2023Multimodal Parameter-Efficient Few-Shot Class Incremental Learningcited by 19
  14. 2023Continual Learning of Diffusion Models with Generative Distillationcited by 19
  15. 2022Sparsity and Heterogeneous Dropout for Continual Learning in the Null Space of Neural Activationscited by 18
  16. 2022Practical Recommendations for Replay-based Continual Learning Methodscited by 16
  17. 2023CL-MASR: A Continual Learning Benchmark for Multilingual ASRcited by 16
  18. 2023Improving Online Continual Learning Performance and Stability with Temporal Ensemblescited by 14
  19. 2022Lifelong Learning Metricscited by 13
  20. 2023A Domain-Agnostic Approach for Characterization of Lifelong Learning Systemscited by 13
  21. 2024Continual Learning with Weight Interpolationcited by 13
  22. 2021Ex-Model: Continual Learning from a Stream of Trained Modelscited by 11
  23. 2022Beyond Supervised Continual Learning: a Reviewcited by 11
  24. 2022Continual Learning with Guarantees via Weight Interval Constraintscited by 10
  25. 2021ModelCI-e: Enabling Continual Learning in Deep Learning Serving Systemscited by 9
  26. 2022Memory Population in Continual Learning via Outlier Eliminationcited by 9
  27. 2022Learning to Learn: How to Continuously Teach Humans and Machinescited by 9
  28. 2023Class-Incremental Learning with Repetitioncited by 9
  29. 2021Continual Learning with Echo State Networkscited by 8
  30. 2022Entropy-based Stability-Plasticity for Lifelong Learningcited by 8
  31. 2022Alleviating Representational Shift for Continual Fine-tuningcited by 8
  32. 2022BeGin: Extensive Benchmark Scenarios and An Easy-to-use Framework for Graph Continual Learningcited by 8
  33. 2023AR-TTA: A Simple Method for Real-World Continual Test-Time Adaptationcited by 8
  34. 2023MIND: Multi-Task Incremental Network Distillationcited by 8
  35. 2021Continual Learning for Unsupervised Anomaly Detection in Continuous Auditing of Financial Accounting Datacited by 7
  36. 2023On the Usage of Continual Learning for Out-of-Distribution Generalization in Pre-trained Language Models of Codecited by 7
  37. 2023Partial Hypernetworks for Continual Learningcited by 7
  38. 2022Feature Forgetting in Continual Representation Learningcited by 6

50 most cited of 124 All 124 (JSON)