mlsanityData to 7 Oct 2026

Avalanche: A PyTorch Library for Deep Continual Learning

arXiv 2302.01766 ↗First posted 2 Feb 2023cs.LGcited by 33

Not on the map. Why?

Abstract (arXiv)

Continual learning is the problem of learning from a nonstationary stream of data, a fundamental issue for sustainable and efficient training of deep neural networks over time. Unfortunately, deep learning libraries only provide primitives for offline training, assuming that model's architecture and data are fixed. Avalanche is an open source library maintained by the ContinualAI non-profit organization that extends PyTorch by providing first-class support for dynamic architectures, streams of datasets, and incremental training and evaluation methods. Avalanche provides a large set of predefined benchmarks and training algorithms and it is easy to extend and modular while supporting a wide range of continual learning scenarios. Documentation is available at urlhttps://avalanche.continualai.org.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Builds on 7 of its 10 references that are in the map. First posted on arXiv 2 Feb 2023.

Builds on

7 of 10 references.

References · 7

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2016Progressive Neural Networkscited by 1,332
  3. 2020Class-incremental learning: survey and performance evaluation on image classificationcited by 446
  4. 2021Avalanche: an End-to-End Library for Continual Learningcited by 124
  5. 2021Continual World: A Robotic Benchmark For Continual Reinforcement Learningcited by 112
  6. 2021Continuum: Simple Management of Complex Continual Learning Scenarioscited by 33
  7. 2021Sequoia: A Software Framework to Unify Continual Learning Researchcited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 13; 2025: 11; 2026: 5.

33 papers.

Sort:

  1. 2023On Efficient Training of Large-Scale Deep Learning Models: A Literature Reviewcited by 26
  2. 2023A Comprehensive Empirical Evaluation on Online Continual Learningcited by 24
  3. 2024Layerwise Proximal Replay: A Proximal Point Method for Online Continual Learningcited by 12
  4. 2025On the Computation of the Fisher Information in Continual Learningcited by 12
  5. 2024Continual Learning in the Presence of Repetitioncited by 10
  6. 2025MCITlib: Multimodal Continual Instruction Tuning Library and Benchmarkcited by 10
  7. 2024Class-incremental Learning for Time Series: Benchmark and Evaluationcited by 9
  8. 2025Online Curvature-Aware Replay: Leveraging mathbf2nd Order Information for Online Continual Learningcited by 8
  9. 2024Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applicationscited by 7
  10. 2024Calibration of Continual Learning Modelscited by 6
  11. 2024An Empirical Analysis of Forgetting in Pre-trained Models with Incremental Low-Rank Updatescited by 6
  12. 2024Overcoming Catastrophic Forgetting in Tabular Data Classification: A Pseudorehearsal-based approachcited by 5
21 more
  1. 2024On the Convergence of Continual Federated Learning Using Incrementally Aggregated Gradientscited by 5
  2. 2025Active Learning for Continual Learning: Keeping the Past Alive in the Presentcited by 5
  3. 2024CODE-CL: Conceptor-Based Gradient Projection for Deep Continual Learningcited by 4
  4. 2023A Protocol for Continual Explanation of SHAPcited by 2
  5. 2023Keep Moving: identifying task-relevant subspaces to maximise plasticity for newly learned taskscited by 2
  6. 2024RECAST: Reparameterized, Compact weight Adaptation for Sequential Taskscited by 2
  7. 2025Regression-aware Continual Learning for Android Malware Detectioncited by 2
  8. 2026A Practical Guide to Streaming Continual Learningcited by 2
  9. 2025CapyMOA: Efficient Machine Learning for Data Streams and Online Continual Learning in Pythoncited by 1
  10. 2025Sample Compression for Self Certified Continual Learningcited by 1
  11. 2025Compact Memory for Continual Logistic Regressioncited by 1
  12. 2026Mitigating Forgetting in Continual Learning with Selective Gradient Projectioncited by 1
  13. 2024Sample Weight Estimation Using Meta-Updates for Online Continual Learningcited by 0
  14. 2024Continual Learning by Three-Phase Consolidationcited by 0
  15. 2024Examining Changes in Internal Representations of Continual Learning Models Through Tensor Decompositioncited by 0
  16. 2025Technical Report for the 5th CLVision Challenge at CVPR: Addressing the Class-Incremental with Repetition using Unlabeled Data -- 4th Place Solutioncited by 0
  17. 2025Noise-Tolerant Coreset-Based Class Incremental Continual Learningcited by 0
  18. 2025Exploring Cross-Stage Adversarial Transferability in Class-Incremental Continual Learningcited by 0
  19. 2026RoAD Benchmark: How LiDAR Models Fail under Coupled Domain Shifts and Label Evolutioncited by 0
  20. 2026Continual Learning for non-stationary regression via Memory-Efficient Replaycited by 0
  21. 2026Forgetting, plasticity, and co-observation: a third facet of continual learningcited by 0