Continual Learning
847 papers with code • 29 benchmarks • 30 datasets
Continual Learning (also known as Incremental Learning, Life-long Learning) is a concept to learn a model for a large number of tasks sequentially without forgetting knowledge obtained from the preceding tasks, where the data in the old tasks are not available anymore during training new ones.
If not mentioned, the benchmarks here are Task-CL, where task-id is provided on validation.
Source:
Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation
Three scenarios for continual learning
Lifelong Machine Learning
Continual lifelong learning with neural networks: A review
Benchmarks
These leaderboards are used to track progress in Continual Learning
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Continual Learning models and implementationsDatasets
CIFAR-10
CIFAR-100
MNIST
Oxford 102 Flower
Stanford Cars
Sketch
Permuted MNIST
CORe50
WikiArt
ROAD
Subtasks
Latest papers
Function-space Parameterization of Neural Networks for Sequential Learning
Our parameterization offers: (i) a way to scale function-space methods to large data sets via sparsification, (ii) retention of prior knowledge when access to past data is limited, and (iii) a mechanism to incorporate new data without retraining.
CoLeCLIP: Open-Domain Continual Learning via Joint Task Prompt and Vocabulary Learning
Large pre-trained VLMs like CLIP have demonstrated superior zero-shot recognition ability, and a number of recent studies leverage this ability to mitigate catastrophic forgetting in CL, but they focus on closed-set CL in a single domain dataset.
Open Continual Feature Selection via Granular-Ball Knowledge Transfer
To this end, the proposed CFS method combines the strengths of continual learning (CL) with granular-ball computing (GBC), which focuses on constructing a granular-ball knowledge base to detect unknown classes and facilitate the transfer of previously learned knowledge for further feature selection.
Simple and Scalable Strategies to Continually Pre-train Large Language Models
In this work, we show that a simple and scalable combination of learning rate (LR) re-warming, LR re-decaying, and replay of previous data is sufficient to match the performance of fully re-training from scratch on all available data, as measured by the final loss and the average score on several language model (LM) evaluation benchmarks.
Consistent Prompting for Rehearsal-Free Continual Learning
Specifically, all existing classifiers are exposed to prompt training, resulting in classifier consistency learning.
DAM: Dynamic Adapter Merging for Continual Video QA Learning
klauscc/dam
•
•
Our DAM model outperforms prior state-of-the-art continual learning approaches by 9. 1% while exhibiting 1. 9% less forgetting on 6 VidQA datasets spanning various domains.
FOCIL: Finetune-and-Freeze for Online Class Incremental Learning by Training Randomly Pruned Sparse Experts
Class incremental learning (CIL) in an online continual learning setting strives to acquire knowledge on a series of novel classes from a data stream, using each data point only once for training.
Online Continual Learning For Interactive Instruction Following Agents
To take a step towards a more realistic embodied agent learning scenario, we propose two continual learning setups for embodied agents; learning new behaviors (Behavior Incremental Learning, Behavior-IL) and new environments (Environment Incremental Learning, Environment-IL) For the tasks, previous 'data prior' based continual learning methods maintain logits for the past tasks.
Continual All-in-One Adverse Weather Removal with Knowledge Replay on a Unified Network Structure
It considers the characteristics of the image restoration task with multiple degenerations in continual learning, and the knowledge for different degenerations can be shared and accumulated in the unified network structure.
Premonition: Using Generative Models to Preempt Future Data Changes in Continual Learning
We show here that the combination of a large language model and an image generation model can similarly provide useful premonitions as to how a continual learning challenge might develop over time.
