Related papers: iCaRL: Incremental Classifier and Representation L…

In multi-task reinforcement learning there are two main challenges: at training time, the ability to learn different policies with a single model; at test time, inferring which of those policies applying without an external signal. In the…

New categories may be introduced over time, or existing categories may need to be reclassified. Class incremental learning (CIL) is employed for the gradual acquisition of knowledge about new categories while preserving information about…

A major problem with Active Learning (AL) is high training costs since models are typically retrained from scratch after every query round. We start by demonstrating that standard AL on neural networks with warm starting fails, both to…

Providing a suitable reward function to reinforcement learning can be difficult in many real world applications. While inverse reinforcement learning (IRL) holds promise for automatically learning reward functions from demonstrations,…

Modern computer vision applications suffer from catastrophic forgetting when incrementally learning new concepts over time. The most successful approaches to alleviate this forgetting require extensive replay of previously seen data, which…

Statistical machine learning algorithms have achieved state-of-the-art results on benchmark datasets, outperforming humans in many tasks. However, the out-of-distribution data and confounder, which have an unpredictable causal relationship,…

Causal reasoning can be considered a cornerstone of intelligent systems. Having access to an underlying causal graph comes with the promise of cause-effect estimation and the identification of efficient and safe interventions. However,…

In spite of remarkable success of the convolutional neural networks on semantic segmentation, they suffer from catastrophic forgetting: a significant performance drop for the already learned classes when new classes are added on the data,…

Continual Imitation Learning (CiL) involves extracting and accumulating task knowledge from demonstrations across multiple stages and tasks to achieve a multi-task policy. With recent advancements in foundation models, there has been a…

Continual learning (CL) aims to train models sequentially over multiple domains without forgetting previously learned knowledge. However, existing CL methods optimize for in-domain performance and are therefore prone to learning spurious,…

In most works on deep incremental learning research, it is assumed that novel samples are pre-identified for neural network retraining. However, practical deep classifiers often misidentify these samples, leading to erroneous predictions.…

Traditional learning systems are trained in closed-world for a fixed number of classes, and need pre-collected datasets in advance. However, new classes often emerge in real-world applications and should be learned incrementally. For…

Class incremental learning (CIL) aims to enable models to continuously learn new classes without catastrophically forgetting old ones. A promising direction is to learn and use prototypes of classes during incremental updates. Despite…

Continual learning aims to improve the ability of modern learning systems to deal with non-stationary distributions, typically by attempting to learn a series of tasks sequentially. Prior art in the field has largely considered supervised…

We address the problem of incremental sequence classification, where predictions are updated as new elements in the sequence are revealed. Drawing on temporal-difference learning from reinforcement learning, we identify a…

In Continual Learning (CL), a neural network is trained on a stream of data whose distribution changes over time. In this context, the main problem is how to learn new information without forgetting old knowledge (i.e., Catastrophic…

Incremental learning remains a critical challenge in machine learning, as models often struggle with catastrophic forgetting -the tendency to lose previously acquired knowledge when learning new information. These challenges are even more…

The dynamic nature of open-world scenarios has attracted more attention to class incremental learning (CIL). However, existing CIL methods typically presume the availability of complete ground-truth labels throughout the training process,…

Many real world learning tasks involve complex or hard-to-specify objectives, and using an easier-to-specify proxy can lead to poor performance or misaligned behavior. One solution is to have humans provide a training signal by…

Contrastive Learning (CL) has been proved to be a powerful self-supervised approach for a wide range of domains, including computer vision and graph representation learning. However, the incremental learning issue of CL has rarely been…