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

By Vincenzo Lomonaco, Lorenzo Pellegrini, Andrea Cossu, Antonio Carta, Gabriele Graffieti, Tyler L. Hayes, Matthias De Lange, Marc Masana, Jary Pomponi, Gido M. van de Ven and 18 more. 2021

219 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Meta & Continual Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Meta & Continual Learning

Citations in the corpus

Continual Learning with Guarantees via Weight Interval Constraints (2022, methodology): “In our experiments, we use the Avalanche (Lomonaco et al., 2021) library to facilitate easier and fairer comparisons.”
Continual Learning via Local Module Composition (2021, background): “The rapid growth of continual learning has lead researchers to work on empirical studies [20, 58, 56], surveys [32, 42, 55, 66, 67] as well as CL-specific software [72, 22, 59].”
Technical Report for ICCV 2021 Challenge SSLAD-Track3B: Transformers Are Better Continual Learners (2022, positive): “The algorithm is implemented using Avalanche [12].”
3rd Continual Learning Workshop Challenge on Egocentric Category and Instance Level Object Understanding (2022, methodology): “The devkit was based on the Avalanche [63] continual learning library.”
Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation (2024, methodology): “We follow Avalanche library (Lomonaco et al., 2021) to implement offline EWC and MAS.”
CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning Agents (2021, background): “, 2022) introduces a library for continual RL, whose functionality will be merged into Avalanche (Lomonaco et al., 2021), is a popular library for continual learning.”
A Contrastive Continual Learning for the Classification of Remote Sensing Imagery (2022, methodology): “Implementation of proposed method was done using Python and Pytorch Library, in addition to the use of Avalanche (End-to-End Library for Continual Learning) [14] to continually expose our model to new classes and PML (PyTorch Metric Learning) [17] to use their implementation of contrastive losses.”
Practical Recommendations for Replay-based Continual Learning Methods (2022, methodology): “For the experimental part we used Avalanche [15] the reference continual learning framework based on PyTorch.”
Pretrained Language Model in Continual Learning: A Comparative Study (2022, background): “…researchers to work on empirical studies (De Lange et al., 2019; Lesort et al., 2021b), surveys (Hadsell et al., 2020; Khetarpal et al., 2020; Lesort et al., 2021a; Mundt et al., 2020; 2021) as well as CL-speciﬁc software (Normandin et al., 2021; Douillard & Lesort, 2021; Lomonaco et al., 2021).”
Three types of incremental learning (2022, unknown): “These experiences are the incremental steps of a continual learning problem, in the sense that at each step, the algorithm has free access to the data of the current experience, but not to the data from past or future experiences (see also ref.”