ICLR 2024 accepted papers on Continual learning
27 of the 2,259 papers accepted at ICLR 2024 (1.2%) are on Continual learning, compared with 1.7% at ICLR 2023. They fall into 4 topics.
See ICLR 2024 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Online and replay-based · 15 papers
- Divide and not forget: Ensemble of selectively trained experts in Continual Learning (11 citations)
- How connectivity structure shapes rich and lazy learning in neural circuits (4 citations)
- A Unified and General Framework for Continual Learning (3 citations)
- Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learning (2 citations)
- Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networks (2 citations)
- Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning (1 citation)
- The Joint Effect of Task Similarity and Overparameterization on Catastrophic Forgetting — An Analytical Model (1 citation)
- A Probabilistic Framework for Modular Continual Learning
- Accurate Forgetting for Heterogeneous Federated Continual Learning
- Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation
- Function-space Parameterization of Neural Networks for Sequential Learning
- Kalman Filter for Online Classification of Non-Stationary Data
and 3 more in the interactive map.
Continual fine-tuning of LLMs · 5 papers
- Scalable Language Model with Generalized Continual Learning (2 citations)
- TiC-CLIP: Continual Training of CLIP Models (1 citation)
- CPPO: Continual Learning for Reinforcement Learning with Human Feedback
- TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models
- Dissecting learning and forgetting in language model finetuning
Class-incremental · 4 papers
- Elastic Feature Consolidation For Cold Start Exemplar-Free Incremental Learning (2 citations)
- Class Incremental Learning via Likelihood Ratio Based Task Prediction (1 citation)
- OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning
- Prediction Error-based Classification for Class-Incremental Learning