We provide a statistical analysis of regularization-based continual learning on a sequence of linear regression tasks, with emphasis on how different regularization terms affect the model performance. We first derive the convergence rate for the oracle estimator obtained as if all data were available simultaneously. Next, we consider a family of generalized $\ell_2$-regularization algorithms indexed by matrix-valued hyperparameters, which includes the minimum norm estimator and continual ridge regression as special cases. As more tasks are introduced, we derive an iterative update formula for the estimation error of generalized $\ell_2$-regularized estimators, from which we determine the hyperparameters resulting in the optimal algorithm. Interestingly, the choice of hyperparameters can effectively balance the trade-off between forward and backward knowledge transfer and adjust for data heterogeneity. Moreover, the estimation error of the optimal algorithm is derived explicitly, which is of the same order as that of the oracle estimator. In contrast, our lower bounds for the minimum norm estimator and continual ridge regression show their suboptimality. A byproduct of our theoretical analysis is the equivalence between early stopping and generalized $\ell_2$-regularization in continual learning, which may be of independent interest. Finally, we conduct experiments to complement our theory.
University of Montréal（蒙特利尔大学）；MILA - Quebec AI Institute（魁北克人工智能研究所）；Thales（泰雷兹公司）；Flowers Laboratory (ENSTA ParisTech & INRIA)（Flowers实验室（ENSTA巴黎高科与INRIA））
In most machine learning algorithms, training data is assumed to be independent and identically distributed (iid). When it is not the case, the algorithm's performances are challenged, leading to the famous phenomenon of catastrophic forgetting. Algorithms dealing with it are gathered in the Continual Learning research field. In this paper, we study the regularization based approaches to continual learning and show that those approaches can not learn to discriminate classes from different tasks in an elemental continual benchmark: the class-incremental scenario. We make theoretical reasoning t…
Sungkyunkwan University（成均馆大学）；Harvard University（哈佛大学）；Seoul National University（首尔大学）
We propose a general, yet simple patch that can be applied to existing regularization-based continual learning methods called classifier-projection regularization (CPR). Inspired by both recent results on neural networks with wide local minima and information theory, CPR adds an additional regularization term that maximizes the entropy of a classifier's output probability. We demonstrate that this additional term can be interpreted as a projection of the conditional probability given by a classifier's output to the uniform distribution. By applying the Pythagorean theorem for KL divergence, we…
We propose a novel regularization-based continual learning method, dubbed as Adaptive Group Sparsity based Continual Learning (AGS-CL), using two group sparsity-based penalties. Our method selectively employs the two penalties when learning each node based its the importance, which is adaptively updated after learning each new task. By utilizing the proximal gradient descent method for learning, the exact sparsity and freezing of the model is guaranteed, and thus, the learner can explicitly control the model capacity as the learning continues. Furthermore, as a critical detail, we re-initializ…
Neural networks have achieved remarkable success in many cognitive tasks. However, when they are trained sequentially on multiple tasks without access to old data, their performance on early tasks tend to drop significantly. This problem is often referred to as catastrophic forgetting, a key challenge in continual learning of neural networks. The regularization-based approach is one of the primary classes of methods to alleviate catastrophic forgetting. In this paper, we provide a novel viewpoint of regularization-based continual learning by formulating it as a second-order Taylor approximatio…
The early and robust detection of anomalies occurring in discrete manufacturing processes allows operators to prevent harm, e.g. defects in production machinery or products. While current approaches for data-driven anomaly detection provide good results on the exact processes they were trained on, they often lack the ability to flexibly adapt to changes, e.g. in products. Continual learning promises such flexibility, allowing for an automatic adaption of previously learnt knowledge to new tasks. Therefore, this article discusses different continual learning approaches from the group of regular…
We propose an effective regularization strategy (CW-TaLaR) for solving continual learning problems. It uses a penalizing term expressed by the Cramer-Wold distance between two probability distributions defined on a target layer of an underlying neural network that is shared by all tasks, and the simple architecture of the Cramer-Wold generator for modeling output data representation. Our strategy preserves target layer distribution while learning a new task but does not require remembering previous tasks' datasets. We perform experiments involving several common supervised frameworks, which pr…
We introduce a new neural network-based continual learning algorithm, dubbed as Uncertainty-regularized Continual Learning (UCL), which builds on traditional Bayesian online learning framework with variational inference. We focus on two significant drawbacks of the recently proposed regularization-based methods: a) considerable additional memory cost for determining the per-weight regularization strengths and b) the absence of gracefully forgetting scheme, which can prevent performance degradation in learning new tasks. In this paper, we show UCL can solve these two problems by introducing a f…
Given the growing trend of continual learning techniques for deep neural networks focusing on the domain of computer vision, there is a need to identify which of these generalizes well to other tasks such as human activity recognition (HAR). As recent methods have mostly been composed of loss regularization terms and memory replay, we provide a constituent-wise analysis of some prominent task-incremental learning techniques employing these on HAR datasets. We find that most regularization approaches lack substantial effect and provide an intuition of when they fail. Thus, we make the case that…
In recent years, the use of lithium-ion batteries has greatly expanded into products from many industrial sectors, e.g. cars, power tools or medical devices. An early prediction and robust understanding of battery faults could therefore greatly increase product quality in those fields. While current approaches for data-driven fault prediction provide good results on the exact processes they were trained on, they often lack the ability to flexibly adapt to changes, e.g. in operational or environmental parameters. Continual learning promises such flexibility, allowing for an automatic adaption o…
Optimal L2 Regularization in High-dimensional Continual Linear Regression
Department of Data and Decisions Sciences, Technion（以色列理工学院数据与决策科学系）；School of Engineering, University of Edinburgh（爱丁堡大学工程学院）；Department of Computer Science, Technion（以色列理工学院计算机科学系）；Department of Electrical and Computing Engineering, Technion（以色列理工学院电气与计算机工程系）；Meta
Ca’ Foscari University（威尼斯福斯卡里大学）；University of New South Wales（新南威尔士大学）；Computer Vision Center（计算机视觉中心）
In this paper, we investigate the continual learning of Vision Transformers (ViT) for the challenging exemplar-free scenario, with special focus on how to efficiently distill the knowledge of its crucial self-attention mechanism (SAM). Our work takes an initial step towards a surgical investigation of SAM for designing coherent continual learning methods in ViTs. We first carry out an evaluation of established continual learning regularization techniques. We then examine the effect of regularization when applied to two key enablers of SAM: (a) the contextualized embedding layers, for their abi…
The ability to learn different tasks sequentially is essential to the development of artificial intelligence. In general, neural networks lack this capability, the major obstacle being catastrophic forgetting. It occurs when the incrementally available information from non-stationary data distributions is continually acquired, disrupting what the model has already learned. Our approach remembers old tasks by projecting the representations of new tasks close to that of old tasks while keeping the decision boundaries unchanged. We employ the center loss as a regularization penalty that enforces …
Korea Advanced Institute of Science and Technology（韩国科学技术院）；LG AI Research（LG人工智能研究院）
Pre-trained representation is one of the key elements in the success of modern deep learning. However, existing works on continual learning methods have mostly focused on learning models incrementally from scratch. In this paper, we explore an alternative framework to incremental learning where we continually fine-tune the model from a pre-trained representation. Our method takes advantage of linearization technique of a pre-trained neural network for simple and effective continual learning. We show that this allows us to design a linear model where quadratic parameter regularization method is…
Sapienza University of Rome（罗马第一大学）；University of Bologna（博洛尼亚大学）
Continual learning of deep neural networks is a key requirement for scaling them up to more complex applicative scenarios and for achieving real lifelong learning of these architectures. Previous approaches to the problem have considered either the progressive increase in the size of the networks, or have tried to regularize the network behavior to equalize it with respect to previously observed tasks. In the latter case, it is essential to understand what type of information best represents this past behavior. Common techniques include regularizing the past outputs, gradients, or individual w…
Revisiting Weight Regularization for Low-Rank Continual Learning
State Key Laboratory of Human-Machine Hybrid Augmented Intelligence（人机混合增强智能国家重点实验室）；Institute of Artificial Intelligence and Robotics（人工智能与机器人研究院）；Computer Vision Center（计算机视觉中心）；Universitat Autònoma de Barcelona（巴塞罗那自治大学）；School of Instrument Science and Engineering（仪器科学与工程学院）；Bernoulli Institute（伯努利学院）；University of Groningen（格罗宁根大学）；School of Software Engineering（软件工程学院）
Continual (or "incremental") learning approaches are employed when additional knowledge or tasks need to be learned from subsequent batches or from streaming data. However these approaches are typically adversary agnostic, i.e., they do not consider the possibility of a malicious attack. In our prior work, we explored the vulnerabilities of Elastic Weight Consolidation (EWC) to the perceptible misinformation. We now explore the vulnerabilities of other regularization-based as well as generative replay-based continual learning algorithms, and also extend the attack to imperceptible misinformati…
AImageLab - University of Modena and Reggio Emilia（AImageLab - 摩德纳和雷焦艾米利亚大学）
Continual Learning has inspired a plethora of approaches and evaluation settings; however, the majority of them overlooks the properties of a practical scenario, where the data stream cannot be shaped as a sequence of tasks and offline training is not viable. We work towards General Continual Learning (GCL), where task boundaries blur and the domain and class distributions shift either gradually or suddenly. We address it through mixing rehearsal with knowledge distillation and regularization; our simple baseline, Dark Experience Replay, matches the network's logits sampled throughout the opti…
ENSTA ParisTech（巴黎高等先进技术学院）；INRIA（法国国家信息与自动化研究所）；Thales（泰雷兹集团）；Fulda University of Applied Sciences（富尔达应用科学大学）
We present a new replay-based method of continual classification learning that we term "conditional replay" which generates samples and labels together by sampling from a distribution conditioned on the class. We compare conditional replay to another replay-based continual learning paradigm (which we term "marginal replay") that generates samples independently of their class and assigns labels in a separate step. The main improvement in conditional replay is that labels for generated samples need not be inferred, which reduces the margin for error in complex continual classification learning t…
COPR: Continual Learning Human Preference through Optimal Policy Regularization
Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；Peng Cheng Laboratory（鹏城实验室）；King’s College London（伦敦国王学院）；National University of Defense Technology（国防科技大学）
University of Wisconsin–Madison（威斯康星大学麦迪逊分校）；Google（谷歌）
Continual learning in neural networks suffers from a phenomenon called catastrophic forgetting, in which a network quickly forgets what was learned in a previous task. The human brain, however, is able to continually learn new tasks and accumulate knowledge throughout life. Neuroscience findings suggest that continual learning success in the human brain is potentially associated with its modular structure and memory consolidation mechanisms. In this paper we propose a novel topological regularization that penalizes cycle structure in a neural network during training using principled theory fro…
SAE-FD: Sparse Autoencoder Feature Distillation for Continual Learning of Large Language Models
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；The 63rd Research Institute, National University of Defense Technology, Nanjing（国防科技大学第六十三研究所，南京）
Deep neural networks struggle to continually learn multiple sequential tasks due to catastrophic forgetting of previously learned tasks. Rehearsal-based methods which explicitly store previous task samples in the buffer and interleave them with the current task samples have proven to be the most effective in mitigating forgetting. However, Experience Replay (ER) does not perform well under low-buffer regimes and longer task sequences as its performance is commensurate with the buffer size. Consistency in predictions of soft-targets can assist ER in preserving information pertaining to previous…
Gradient-Free Continual Learning in Spiking Neural Networks via Inter-Spike Interval Regularization
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Indian Institute of Technology Delhi（印度理工学院德里）；University of Texas at El Paso（得克萨斯大学埃尔帕索分校）；National Center for Supercomputing Applications（国家超级计算应用中心）
Continual Learning with Elastic Regularization and Synthetic Replay for Federated MLLM Fine-Tuning
The University of British Columbia（英属哥伦比亚大学）；Fudan University（复旦大学）；Royal College of Science, Imperial College London（伦敦帝国理工学院皇家科学学院）；Dyson School of Design Engineering（戴森设计工程学院）；Suzhou Institute of Biomedical Engineering and Technology (SIBET), Chinese Academy of Sciences（中国科学院苏州生物医学工程技术研究所）；East China Normal University（华东师范大学）
Continual Instruction Tuning for Large Multimodal Models
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；The Peng Cheng Laboratory（鹏城实验室）；Wuhan AI Research（武汉人工智能研究院）
Warwick University（华威大学）；The Alan Turing Institute（艾伦·图灵研究所）；Australian National University（澳大利亚国立大学）；Data61（Data61研究所）；Amazon（亚马逊）
Continual Learning (CL) algorithms incrementally learn a predictor or representation across multiple sequentially observed tasks. Designing CL algorithms that perform reliably and avoid so-called catastrophic forgetting has proven a persistent challenge. The current paper develops a theoretical approach that explains why. In particular, we derive the computational properties which CL algorithms would have to possess in order to avoid catastrophic forgetting. Our main finding is that such optimal CL algorithms generally solve an NP-hard problem and will require perfect memory to do so. The find…
Octopus: History-Free Gradient Orthogonalization for Continual Learning in Multimodal Large Language Models
MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University（人工智能大模型关键实验室，人工智能研究院，上海交通大学）；vivo Mobile Communication Co., Ltd.（vivo移动通信有限公司）
University of Cambridge（剑桥大学）；Baylor College of Medicine（贝勒医学院）；MediaTek Research（联发科技研究）
Biological agents are known to learn many different tasks over the course of their lives, and to be able to revisit previous tasks and behaviors with little to no loss in performance. In contrast, artificial agents are prone to 'catastrophic forgetting' whereby performance on previous tasks deteriorates rapidly as new ones are acquired. This shortcoming has recently been addressed using methods that encourage parameters to stay close to those used for previous tasks. This can be done by (i) using specific parameter regularizers that map out suitable destinations in parameter space, or (ii) gui…
Indian Institute of Technology, Kanpur（印度理工学院坎普尔分校）
Continual Learning is a learning paradigm where learning systems are trained with sequential or streaming tasks. Two notable directions among the recent advances in continual learning with neural networks are ($i$) variational Bayes based regularization by learning priors from previous tasks, and, ($ii$) learning the structure of deep networks to adapt to new tasks. So far, these two approaches have been orthogonal. We present a novel Bayesian approach to continual learning based on learning the structure of deep neural networks, addressing the shortcomings of both these approaches. The propos…
Catastrophic forgetting (CF) happens whenever a neural network overwrites past knowledge while being trained on new tasks. Common techniques to handle CF include regularization of the weights (using, e.g., their importance on past tasks), and rehearsal strategies, where the network is constantly re-trained on past data. Generative models have also been applied for the latter, in order to have endless sources of data. In this paper, we propose a novel method that combines the strengths of regularization and generative-based rehearsal approaches. Our generative model consists of a normalizing fl…
