Continual learning research has shown that neural networks suffer from catastrophic forgetting "at the output level", but it is debated whether this is also the case at the level of learned representations. Multiple recent studies ascribe representations a certain level of innate robustness against forgetting -- that they only forget minimally in comparison with forgetting at the output level. We revisit and expand upon the experiments that revealed this difference in forgetting and illustrate the coexistence of two phenomena that affect the quality of continually learned representations: knowledge accumulation and feature forgetting. Taking both aspects into account, we show that, even though forgetting in the representation (i.e. feature forgetting) can be small in absolute terms, when measuring relative to how much was learned during a task, forgetting in the representation tends to be just as catastrophic as forgetting at the output level. Next we show that this feature forgetting is problematic as it substantially slows down the incremental learning of good general representations (i.e. knowledge accumulation). Finally, we study how feature forgetting and knowledge accumulation are affected by different types of continual learning methods.
University of Vermont（佛蒙特大学）；Uber AI Labs（优步人工智能实验室）；OpenAI（开放人工智能研究中心）
Continual lifelong learning requires an agent or model to learn many sequentially ordered tasks, building on previous knowledge without catastrophically forgetting it. Much work has gone towards preventing the default tendency of machine learning models to catastrophically forget, yet virtually all such work involves manually-designed solutions to the problem. We instead advocate meta-learning a solution to catastrophic forgetting, allowing AI to learn to continually learn. Inspired by neuromodulatory processes in the brain, we propose A Neuromodulated Meta-Learning Algorithm (ANML). It differ…
Scuola Normale Superiore（比萨高等师范学校）；KU Leuven（鲁汶大学）；University of Pisa（比萨大学）
Pre-trained models are nowadays a fundamental component of machine learning research. In continual learning, they are commonly used to initialize the model before training on the stream of non-stationary data. However, pre-training is rarely applied during continual learning. We formalize and investigate the characteristics of the continual pre-training scenario in both language and vision environments, where a model is continually pre-trained on a stream of incoming data and only later fine-tuned to different downstream tasks. We show that continually pre-trained models are robust against cat…
This paper considers incremental few-shot learning, which requires a model to continually recognize new categories with only a few examples provided. Our study shows that existing methods severely suffer from catastrophic forgetting, a well-known problem in incremental learning, which is aggravated due to data scarcity and imbalance in the few-shot setting. Our analysis further suggests that to prevent catastrophic forgetting, actions need to be taken in the primitive stage -- the training of base classes instead of later few-shot learning sessions. Therefore, we propose to search for flat loc…
Despite much research targeted at enabling conventional machine learning models to continually learn tasks and data distributions sequentially without forgetting the knowledge acquired, little effort has been devoted to account for more realistic situations where learning some tasks accurately might be more critical than forgetting previous ones. In this paper we propose a Bayesian inference based framework to continually learn a set of real-world, sensing-based analysis tasks that can be tuned to prioritize the remembering of previously learned tasks or the learning of new ones. Our experimen…
Computer Vision Center, UAB（巴塞罗那自治大学计算机视觉中心）；Huawei（华为）
Artificial neural networks thrive in solving the classification problem for a particular rigid task, acquiring knowledge through generalized learning behaviour from a distinct training phase. The resulting network resembles a static entity of knowledge, with endeavours to extend this knowledge without targeting the original task resulting in a catastrophic forgetting. Continual learning shifts this paradigm towards networks that can continually accumulate knowledge over different tasks without the need to retrain from scratch. We focus on task incremental classification, where tasks arrive seq…
CoMetaPNS: Continually Meta-learning Personalized Neural Surrogates for Cardiac Electrophysiology Simulations
Golisano College of Computing and Information Sciences, Rochester Institute of Technology（罗切斯特理工学院戈利萨诺计算与信息科学学院）；Department of Computer Science, Rowan University（罗文大学计算机科学系）；The University of Utah（犹他大学）
Eindhoven University of Technology（埃因霍温理工大学）；University of Twente（特文特大学）
Continual learning aims to provide intelligent agents that are capable of learning continually a sequence of tasks, building on previously learned knowledge. A key challenge in this learning paradigm is catastrophically forgetting previously learned tasks when the agent faces a new one. Current rehearsal-based methods show their success in mitigating the catastrophic forgetting problem by replaying samples from previous tasks during learning a new one. However, these methods are infeasible when the data of previous tasks is not accessible. In this work, we propose a new pseudo-rehearsal-based …
Concordia University（康考迪亚大学）；Mila – Quebec AI Institute（米拉 - 魁北克人工智能研究所）；Toyota Motor Europe（丰田汽车欧洲公司）
Continual Learning research typically focuses on tackling the phenomenon of catastrophic forgetting in neural networks. Catastrophic forgetting is associated with an abrupt loss of knowledge previously learned by a model when the task, or more broadly the data distribution, being trained on changes. In supervised learning problems this forgetting, resulting from a change in the model's representation, is typically measured or observed by evaluating the decrease in old task performance. However, a model's representation can change without losing knowledge about prior tasks. In this work we cons…
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…
Sichuan University（四川大学）；Zhejiang University（浙江大学）；ByteDance Inc.（字节跳动公司）；National University of Singapore（新加坡国立大学）
Learning from changing tasks and sequential experience without forgetting the obtained knowledge is a challenging problem for artificial neural networks. In this work, we focus on two challenging problems in the paradigm of Continual Learning (CL) without involving any old data: (i) the accumulation of catastrophic forgetting caused by the gradually fading knowledge space from which the model learns the previous knowledge; (ii) the uncontrolled tug-of-war dynamics to balance the stability and plasticity during the learning of new tasks. In order to tackle these problems, we present Progressive…
ENSTA ParisTech（巴黎高等先进技术学院）；INRIA Flowers（法国国家信息与自动化研究所Flowers实验室）；University of Bologna（博洛尼亚大学）
Continual learning consists of algorithms that learn from a stream of data/tasks continuously and adaptively thought time, enabling the incremental development of ever more complex knowledge and skills. The lack of consensus in evaluating continual learning algorithms and the almost exclusive focus on forgetting motivate us to propose a more comprehensive set of implementation independent metrics accounting for several factors we believe have practical implications worth considering in the deployment of real AI systems that learn continually: accuracy or performance over time, backward and for…
A lifelong learning agent is able to continually learn from potentially infinite streams of pattern sensory data. One major historic difficulty in building agents that adapt in this way is that neural systems struggle to retain previously-acquired knowledge when learning from new samples. This problem is known as catastrophic forgetting (interference) and remains an unsolved problem in the domain of machine learning to this day. While forgetting in the context of feedforward networks has been examined extensively over the decades, far less has been done in the context of alternative architectu…
The Australian National University（澳大利亚国立大学）；Monash University（莫纳什大学）；CSIRO（澳大利亚联邦科学与工业研究组织）；University of Turku（图尔库大学）
Neural networks suffer from catastrophic forgetting and are unable to sequentially learn new tasks without guaranteed stationarity in data distribution. Continual learning could be achieved via replay -- by concurrently training externally stored old data while learning a new task. However, replay becomes less effective when each past task is allocated with less memory. To overcome this difficulty, we supplemented replay mechanics with meta-learning for rapid knowledge acquisition. By employing a meta-learner, which \textit{learns a learning rate per parameter per past task}, we found that bas…
Continual learning tries to learn new tasks without forgetting previously learned ones. In reality, most of the existing artificial neural network(ANN) models fail, while humans do the same by remembering previous works throughout their life. Although simply storing all past data can alleviate the problem, it needs large memory and often infeasible in real-world applications where last data access is limited. We hypothesize that the model that learns to solve each task continually has some task-specific properties and some task-invariant characteristics. We propose a hybrid continual learning …
Polytechnique Montreal（蒙特利尔理工学院）；MILA, Quebec AI Institute（魁北克人工智能研究所MILA）；CHU Rennes（雷恩大学中心医院）；CHU Montpellier（蒙彼利埃大学中心医院）；Karolinska Institutet（卡罗林斯卡学院）；University of California, San Francisco（加州大学旧金山分校）；National Institute of Neurological Disorders and Stroke, National Institutes of Health（美国国立卫生研究院国家神经疾病与中风研究所）；IRCCS San Raffaele Scientific Institute（IRCCS圣拉斐尔科学研究所）；Vita-Salute San Raffaele University（圣拉斐尔生命健康大学）；Brigham and Women’s Hospital（布莱根妇女医院）；Harvard Medical School（哈佛医学院）；AP-HM, CHU Timone（马赛公共医院集团蒂莫内大学中心医院）；Aix-Marseille Univ（艾克斯-马赛大学）；CNRS（法国国家科学研究中心）
Segmentation of Multiple Sclerosis (MS) lesions is a challenging problem. Several deep-learning-based methods have been proposed in recent years. However, most methods tend to be static, that is, a single model trained on a large, specialized dataset, which does not generalize well. Instead, the model should learn across datasets arriving sequentially from different hospitals by building upon the characteristics of lesions in a continual manner. In this regard, we explore experience replay, a well-known continual learning method, in the context of MS lesion segmentation across multi-contrast d…
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）
Deep neural networks (DNNs) have recently achieved a great success in computer vision and several related fields. Despite such progress, current neural architectures still suffer from catastrophic interference (a.k.a. forgetting) which obstructs DNNs to learn continually. While several state-of-the-art methods have been proposed to mitigate forgetting, these existing solutions are either highly rigid (as regularization) or time/memory demanding (as replay). An intermediate class of methods, based on dynamic networks, has been proposed in the literature and provides a reasonable balance between…
Computer Vision Center (CVC)（计算机视觉中心）；Universitat Autonoma of Barcelona (UAB)（巴塞罗那自治大学）；Media Integration and Communication Center（媒体整合与传播中心）
Recent self-supervised learning methods are able to learn high-quality image representations and are closing the gap with supervised approaches. However, these methods are unable to acquire new knowledge incrementally -- they are, in fact, mostly used only as a pre-training phase over IID data. In this work we investigate self-supervised methods in continual learning regimes without any replay mechanism. We show that naive functional regularization, also known as feature distillation, leads to lower plasticity and limits continual learning performance. Instead, we propose Projected Functional …
Natural language generation (NLG) is an essential component of task-oriented dialog systems. Despite the recent success of neural approaches for NLG, they are typically developed in an offline manner for particular domains. To better fit real-life applications where new data come in a stream, we study NLG in a "continual learning" setting to expand its knowledge to new domains or functionalities incrementally. The major challenge towards this goal is catastrophic forgetting, meaning that a continually trained model tends to forget the knowledge it has learned before. To this end, we propose a …
Artificial neural networks are well-known to be susceptible to catastrophic forgetting when continually learning from sequences of tasks. Various continual (or "incremental") learning approaches have been proposed to avoid catastrophic forgetting, but they are typically adversary agnostic, i.e., they do not consider the possibility of a malicious attack. In this effort, we explore the vulnerability of Elastic Weight Consolidation (EWC), a popular continual learning algorithm for avoiding catastrophic forgetting. We show that an intelligent adversary can bypass the EWC's defenses, and instead c…
ElementAI（ElementAI公司）；Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）；Université de Montréal（蒙特利尔大学）；Facebook AI Research（脸书人工智能研究院）；McGill University（麦吉尔大学）；HEC Montréal（蒙特利尔高等商学院）
Continual learning studies agents that learn from streams of tasks without forgetting previous ones while adapting to new ones. Two recent continual-learning scenarios have opened new avenues of research. In meta-continual learning, the model is pre-trained to minimize catastrophic forgetting of previous tasks. In continual-meta learning, the aim is to train agents for faster remembering of previous tasks through adaptation. In their original formulations, both methods have limitations. We stand on their shoulders to propose a more general scenario, OSAKA, where an agent must quickly solve new…
Current deep learning models often suffer from catastrophic forgetting of old knowledge when continually learning new knowledge. Existing strategies to alleviate this issue often fix the trade-off between keeping old knowledge (stability) and learning new knowledge (plasticity). However, the stability-plasticity trade-off during continual learning may need to be dynamically changed for better model performance. In this paper, we propose two novel ways to adaptively balance model stability and plasticity. The first one is to adaptively integrate multiple levels of old knowledge and transfer it …
While deep learning has led to remarkable advances across diverse applications, it struggles in domains where the data distribution changes over the course of learning. In stark contrast, biological neural networks continually adapt to changing domains, possibly by leveraging complex molecular machinery to solve many tasks simultaneously. In this study, we introduce intelligent synapses that bring some of this biological complexity into artificial neural networks. Each synapse accumulates task relevant information over time, and exploits this information to rapidly store new memories without f…
School of Electrical and Computer Engineering, Purdue University（普渡大学电气与计算机工程学院）
The ability to learn continually without forgetting the past tasks is a desired attribute for artificial learning systems. Existing approaches to enable such learning in artificial neural networks usually rely on network growth, importance based weight update or replay of old data from the memory. In contrast, we propose a novel approach where a neural network learns new tasks by taking gradient steps in the orthogonal direction to the gradient subspaces deemed important for the past tasks. We find the bases of these subspaces by analyzing network representations (activations) after learning e…
Learning and adapting to new distributions or learning new tasks sequentially without forgetting the previously learned knowledge is a challenging phenomenon in continual learning models. Most of the conventional deep learning models are not capable of learning new tasks sequentially in one model without forgetting the previously learned ones. We address this issue by using a Kalman Optimiser. The Kalman Optimiser divides the neural network into two parts: the long-term and short-term memory units. The long-term memory unit is used to remember the learned tasks and the short-term memory unit i…
Keep Rehearsing and Refining: Lifelong Learning Vehicle Routing under Continually Drifting Tasks
Center of Data Science and Artificial Intelligence & School of Engineering and Computer Science（数据科学与人工智能中心及工程与计算机科学学院）；Victoria University of Wellington（怀特维尔大学）；School of Data Science（数据科学学院）
本文提出了一种应对持续漂移任务的终身学习方法，通过Dual Replay with Experience Enhancement框架提升学习效率并缓解灾难性遗忘。
National Institute of Advanced Industrial Science and Technology (AIST)（国立先进工业科学技术研究院（产业技术综合研究所））
Sequential training from task to task is becoming one of the major objects in deep learning applications such as continual learning and transfer learning. Nevertheless, it remains unclear under what conditions the trained model's performance improves or deteriorates. To deepen our understanding of sequential training, this study provides a theoretical analysis of generalization performance in a solvable case of continual learning. We consider neural networks in the neural tangent kernel (NTK) regime that continually learn target functions from task to task, and investigate the generalization b…
In many real-world scenarios, data to train machine learning models become available over time. However, neural network models struggle to continually learn new concepts without forgetting what has been learnt in the past. This phenomenon is known as catastrophic forgetting and it is often difficult to prevent due to practical constraints, such as the amount of data that can be stored or the limited computation sources that can be used. Moreover, training large neural networks, such as Transformers, from scratch is very costly and requires a vast amount of training data, which might not be ava…
Humans learn all their life long. They accumulate knowledge from a sequence of learning experiences and remember the essential concepts without forgetting what they have learned previously. Artificial neural networks struggle to learn similarly. They often rely on data rigorously preprocessed to learn solutions to specific problems such as classification or regression. In particular, they forget their past learning experiences if trained on new ones. Therefore, artificial neural networks are often inept to deal with real-life settings such as an autonomous-robot that has to learn on-line to ad…
Despite advances in deep learning, neural networks can only learn multiple tasks when trained on them jointly. When tasks arrive sequentially, they lose performance on previously learnt tasks. This phenomenon called catastrophic forgetting is a fundamental challenge to overcome before neural networks can learn continually from incoming data. In this work, we derive inspiration from human memory to develop an architecture capable of learning continuously from sequentially incoming tasks, while averting catastrophic forgetting. Specifically, our contributions are: (i) a dual memory architecture …
Arizona State University（亚利桑那州立大学）；University of California, Davis（加利福尼亚大学戴维斯分校）
By learning a sequence of tasks continually, an agent in continual learning (CL) can improve the learning performance of both a new task and `old' tasks by leveraging the forward knowledge transfer and the backward knowledge transfer, respectively. However, most existing CL methods focus on addressing catastrophic forgetting in neural networks by minimizing the modification of the learnt model for old tasks. This inevitably limits the backward knowledge transfer from the new task to the old tasks, because judicious model updates could possibly improve the learning performance of the old tasks …
University of Toronto（多伦多大学）；LG AI Research（LG人工智能研究院）
As image-based deep learning becomes pervasive on every device, from cell phones to smart watches, there is a growing need to develop methods that continually learn from data while minimizing memory footprint and power consumption. While memory replay techniques have shown exceptional promise for this task of continual learning, the best method for selecting which buffered images to replay is still an open question. In this paper, we specifically focus on the online class-incremental setting where a model needs to learn new classes continually from an online data stream. To this end, we contri…
MEGA: Second-Order Gradient Alignment for Catastrophic Forgetting Mitigation in GFSCIL
Beijing Institute of Technology（北京理工大学）；Department of Biomedical Engineering, Hefei University of Technology（合肥工业大学生物医学工程学院）；School of Artificial Intelligence and Computer Science, Nantong University（南通大学人工智能与计算机科学学院）；Faculty of Data Science, City University of Macau（澳门城市大学数据科学学院）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）
Tsinghua University（清华大学）；Peng Cheng Laboratory（鹏城实验室）；University of Connecticut（康涅狄格大学）
Deep neural networks (DNNs) have been applied in class incremental learning, which aims to solve common real-world problems of learning new classes continually. One drawback of standard DNNs is that they are prone to catastrophic forgetting. Knowledge distillation (KD) is a commonly used technique to alleviate this problem. In this paper, we demonstrate it can indeed help the model to output more discriminative results within old classes. However, it cannot alleviate the problem that the model tends to classify objects into new classes, causing the positive effect of KD to be hidden and limite…
