Continual Learning for Classification Problems: A Survey

Vijayan, Mochitha; Sridhar, Sharath Nittur

doi:10.1007/978-3-030-92600-7_15

Cited by 6 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…stream of data with the goal of assimilating new knowledge preventing catastrophic forgetting [9,37]. Methods for preventing catastrophic forgetting have been explored primarily in the classification task, where catastrophic forgetting often manifests itself as a significant drop in classification accuracy [2,13,35,41,68]. The key aspects that distinguish lifelong feature learning for visual search from classification are: (i) categorical data often have coarser granularity than visual search data; (ii) evaluation metrics do not involve classification accuracy; and (iii) class labels are not required to be explicitly learned.…”

Section: Related Workmentioning

confidence: 99%

CL2R: Compatible Lifelong Learning Representations

Biondi,

Pernici,

Bruni

et al. 2022

Preprint

View full text Add to dashboard Cite

In this paper, we propose a method to partially mimic natural intelligence for the problem of lifelong learning representations that are compatible. We take the perspective of a learning agent that is interested in recognizing object instances in an open dynamic universe in a way in which any update to its internal feature representation does not render the features in the gallery unusable for visual search. We refer to this learning problem as Compatible Lifelong Learning Representations (CL 2 R) as it considers compatible representation learning within the lifelong learning paradigm. We identify stationarity as the property that the feature representation is required to hold to achieve compatibility and propose a novel training procedure that encourages local and global stationarity on the learned representation. Due to stationarity, the statistical properties of the learned features do not change over time, making them interoperable with previously learned features. Extensive experiments on standard benchmark datasets show that our CL 2 R training procedure outperforms alternative baselines and state-of-the-art methods. We also provide novel metrics to specifically evaluate compatible representation learning under catastrophic forgetting in various sequential learning tasks. Code at https://github.com/NiccoBiondi/CompatibleLifelongRepresentation. CCS Concepts: • Computing methodologies → Visual content-based indexing and retrieval.

show abstract

Section: Related Workmentioning

confidence: 99%

CL2R: Compatible Lifelong Learning Representations

Biondi,

Pernici,

Bruni

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Lastly, algorithmic approaches aim to adapt the optimization algorithm itself to avoid catastrophic forgetting, e.g., by mapping the gradient updates into a different space (Zeng et al, 2019;Wang et al, 2021). Some methods provide a combination of approaches, as it seems plausible that a mixture of approaches will provide the best-performing systems, as these methods are often complementary (Biesialska et al, 2020;De Lange et al, 2021;Vijayan & Sridhar, 2021).…”

Section: Introductionmentioning

confidence: 99%

Hierarchically structured task-agnostic continual learning

Hihn

Braun

2022

Mach Learn

View full text Add to dashboard Cite

One notable weakness of current machine learning algorithms is the poor ability of models to solve new problems without forgetting previously acquired knowledge. The Continual Learning paradigm has emerged as a protocol to systematically investigate settings where the model sequentially observes samples generated by a series of tasks. In this work, we take a task-agnostic view of continual learning and develop a hierarchical information-theoretic optimality principle that facilitates a trade-off between learning and forgetting. We derive this principle from a Bayesian perspective and show its connections to previous approaches to continual learning. Based on this principle, we propose a neural network layer, called the Mixture-of-Variational-Experts layer, that alleviates forgetting by creating a set of information processing paths through the network which is governed by a gating policy. Equipped with a diverse and specialized set of parameters, each path can be regarded as a distinct sub-network that learns to solve tasks. To improve expert allocation, we introduce diversity objectives, which we evaluate in additional ablation studies. Importantly, our approach can operate in a task-agnostic way, i.e., it does not require task-specific knowledge, as is the case with many existing continual learning algorithms. Due to the general formulation based on generic utility functions, we can apply this optimality principle to a large variety of learning problems, including supervised learning, reinforcement learning, and generative modeling. We demonstrate the competitive performance of our method on continual reinforcement learning and variants of the MNIST, CIFAR-10, and CIFAR-100 datasets.

show abstract

“…† Corresponding Author. catastrophic forgetting is typically observed by a clear reduction in classification accuracy [11,12,13,14,15]. The fundamental differences with respect to learning internal feature representation for visual search tasks are: (1) evaluation metrics do not use classification accuracy (2) visual search data have typically a finer granularity with respect to categorical data and (3) no classes are required to be specifically learned.…”

Section: Introductionmentioning

confidence: 99%

Contrastive Supervised Distillation for Continual Representation Learning

Barletti,

Biondi,

Pernici

et al. 2022

Preprint

View full text Add to dashboard Cite

In this paper, we propose a novel training procedure for the continual representation learning problem in which a neural network model is sequentially learned to alleviate catastrophic forgetting in visual search tasks. Our method, called Contrastive Supervised Distillation (CSD), reduces feature forgetting while learning discriminative features. This is achieved by leveraging labels information in a distillation setting in which the student model is contrastively learned from the teacher model. Extensive experiments show that CSD performs favorably in mitigating catastrophic forgetting by outperforming current state-ofthe-art methods. Our results also provide further evidence that feature forgetting evaluated in visual retrieval tasks is not as catastrophic as in classification tasks. Code at: https://github.com/NiccoBiondi/ContrastiveSupervisedDistillation.

show abstract

Continual Learning for Classification Problems: A Survey

Cited by 6 publications

References 18 publications

CL2R: Compatible Lifelong Learning Representations

CL2R: Compatible Lifelong Learning Representations

Hierarchically structured task-agnostic continual learning

Contrastive Supervised Distillation for Continual Representation Learning

Contact Info

Product

Resources

About