Continual Learning
33개 벤치마크 · 논문 3,531편 · 이 태스크의 논문 보기 →
Benchmarks
ASC (19 tasks)
Cifar100 (20 tasks)
Tiny-ImageNet (10tasks)
F-CelebA (10 tasks)
20Newsgroup (10 tasks)
DSC (10 tasks)
Cifar100 (10 tasks)
ImageNet-50 (5 tasks)
Permuted MNIST
split CIFAR-100
5-Datasets
5-dataset - 1 epoch
AIDS
Coarse-CIFAR100
MLT17
Rotated MNIST
Split CIFAR-10 (5 tasks)
Split MNIST (5 tasks)
miniImagenet
Most implemented
Overcoming catastrophic forgetting in neural networks
Learning without Forgetting
Progressive Neural Networks
Continual learning with hypernetworks
Three scenarios for continual learning
Variational Continual Learning
Papers
PaLoRA: Paced Low-Rank Adaptation for Continual Learning
LoRA-based continual learning methods mitigate catastrophic forgetting through various mechanisms, yet nearly all complement these with small learning rates as a heuristic to restrict gradient scaling magnitude. Such fix…
Continual LearningTask-Oriented Rank Adaptation for Continual Learning in Text Classification
Continual learning (CL) in text classification faces two critical challenges: catastrophic forgetting and negative transfer across sequential tasks. Parameter-Efficient Fine-Tuning (PEFT) methods such as LoRA enable effi…
parameter-efficient fine-tuningText ClassificationContinual LearningContinual Reinforcement Learning with Neuroevolution
Despite many studies about causes and remedies of plasticity loss in Reinforcement Learning (RL) under continual task changes, no RL method has yet consistently achieved a good balance between adaptation and forgetting. …
Reinforcement LearningContinual LearningLearning Dynamics of Continual Learning: A Unified View of Data Attribution, Forgetting, and Plasticity Loss
Modern language models are likely to be updated throughout their lifetime rather than trained once and frozen. Each update therefore participates in a recurring cycle: decide which experience to learn from, understand wh…
Continual LearningACLArena: Agent Continue Learning in Multi-stage Post-training
Building general-purpose agents for industrial deployment requires integrating multiple capabilities, each typically acquired at a distinct stage of training. Yet there is currently no well-established recipe for Agent C…
Continual LearningScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
We introduce and release ScienceBuddy, an interactive scientific research workspace that brings continually improving scientific agents into researchers' everyday workflows. ScienceBuddy supports researchers in carrying …
Reinforcement LearningContinual Learning