Acquiring new knowledge without forgetting what has been learned in a sequence of tasks is the central focus of continual learning (CL). While tasks arrive sequentially, the training data are often prepared and annotated independently, leading to the CL of incoming supervised learning tasks. This paper considers the under-explored problem of active continual learning (ACL) for a sequence of active learning (AL) tasks, where each incoming task includes a pool of unlabelled data and an annotation budget. We investigate the effectiveness and interplay between several AL and CL algorithms in the domain, class and task-incremental scenarios. Our experiments reveal the trade-off between two contrasting goals of not forgetting the old knowledge and the ability to quickly learn new knowledge in CL and AL, respectively. While conditioning the AL query strategy on the annotations collected for the previous tasks leads to improved task performance on the domain and task incremental learning, our proposed forgetting-learning profile suggests a gap in balancing the effect of AL and CL for the class-incremental scenario.
SEEKR: Selective Attention-Guided Knowledge Retention for Continual Learning of Large Language Models
Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所基础模型研究中心）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Chongqing University（重庆大学）；Peng Cheng Laboratory（鹏城实验室）；Wuhan AI Research（武汉人工智能研究院）
Artificial neural networks (ANNs), despite their universal function approximation capability and practical success, are subject to catastrophic forgetting. Catastrophic forgetting refers to the abrupt unlearning of a previous task when a new task is learned. It is an emergent phenomenon that hinders continual learning. Existing universal function approximation theorems for ANNs guarantee function approximation ability, but do not predict catastrophic forgetting. This paper presents a novel universal approximation theorem for multi-variable functions using only single-variable functions and exp…
A Retention-Centric Framework for Continual Learning with Guaranteed Model Developmental Safety
Department of Computer Science & Engineering, Texas A&M University, College Station, USA（德克萨斯A&M大学计算机科学与工程系）；Department of Mathematics, The University of Iowa, Iowa City, USA（爱荷华大学数学系）；Global Research and Development, General Motors, Warren, USA（通用汽车全球研发）；Department of Electrical and Computer Engineering, The Ohio State University, Columbus, UAS（俄亥俄州立大学电气与计算机工程系）；Tippie College of Business, The University of Iowa, Iowa City, USA（爱荷华大学蒂皮学院）
Looking through the past: better knowledge retention for generative replay in continual learning
IDEAS NCBR；Gdańsk University of Technology（格但斯克工业大学）；Warsaw University of Technology（华沙工业大学）；Jagiellonian University（雅盖隆大学）；Tooploox；Computer Vision Center（计算机视觉中心）；Universitat Autònoma Barcelona（巴塞罗那自治大学）
DeepMind（深度思维）；University of Toronto（多伦多大学）；Vector Institute（向量研究所）；Google Brain（谷歌大脑）；Baidu Apollo（百度阿波罗）
A challenging problem in task-free continual learning is the online selection of a representative replay memory from data streams. In this work, we investigate the online memory selection problem from an information-theoretic perspective. To gather the most information, we propose the \textit{surprise} and the \textit{learnability} criteria to pick informative points and to avoid outliers. We present a Bayesian model to compute the criteria efficiently by exploiting rank-one matrix structures. We demonstrate that these criteria encourage selecting informative points in a greedy algorithm for o…
To Retain or to Adapt? Generalizing Continual Learning
ETH AI Center, Department of Computer Science, ETH Zürich（苏黎世联邦理工学院人工智能中心，计算机科学系）；Mila - Quebec AI Institute, School of Computer Science, McGill University（魁北克人工智能研究所，麦吉尔大学计算机科学系）；University of Technology Nuremberg（纽伦堡技术大学）
McGill University（麦吉尔大学）；Facebook AI Research（脸书人工智能研究院）
This paper presents SPeCiaL: a method for unsupervised pretraining of representations tailored for continual learning. Our approach devises a meta-learning objective that differentiates through a sequential learning process. Specifically, we train a linear model over the representations to match different augmented views of the same image together, each view presented sequentially. The linear model is then evaluated on both its ability to classify images it just saw, and also on images from previous iterations. This gives rise to representations that favor quick knowledge retention with minima…
Large Language Models (LMs) are known to encode world knowledge in their parameters as they pretrain on a vast amount of web corpus, which is often utilized for performing knowledge-dependent downstream tasks such as question answering, fact-checking, and open dialogue. In real-world scenarios, the world knowledge stored in the LMs can quickly become outdated as the world changes, but it is non-trivial to avoid catastrophic forgetting and reliably acquire new knowledge while preserving invariant knowledge. To push the community towards better maintenance of ever-changing LMs, we formulate a ne…
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 …
Neural networks have been criticised for their inability to perform continual learning due to catastrophic forgetting and rapid unlearning of a past concept when a new concept is introduced. Catastrophic forgetting can be alleviated by specifically designed models and training techniques. This paper outlines a novel Spline Additive Model (SAM). SAM exhibits intrinsic memory retention with sufficient expressive power for many practical tasks, but is not a universal function approximator. SAM is extended with the Kolmogorov-Arnold representation theorem to a novel universal function approximator…
Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning
The University of Hong Kong（香港大学）；The Hong Kong University of Science and Technology（香港科学与技术大学）；Hong Kong Generative AI Research and Development Center（香港生成式人工智能研究与开发中心）
Unsupervised continual learning remains a relatively uncharted territory in the existing literature because the vast majority of existing works call for unlimited access of ground truth incurring expensive labelling cost. Another issue lies in the problem of task boundaries and task IDs which must be known for model's updates or model's predictions hindering feasibility for real-time deployment. Knowledge Retention in Self-Adaptive Deep Continual Learner, (KIERA), is proposed in this paper. KIERA is developed from the notion of flexible deep clustering approach possessing an elastic network st…
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；ZJU-Ant Group Joint Research Center for Knowledge Graphs, Zhejiang University（浙江大学-蚂蚁集团知识图谱联合研究中心）；School of Software Technology, Zhejiang University（浙江大学软件学院）；Monash University（莫纳什大学）；Hangzhou Dianzi University（杭州电子科技大学）；Zhejiang Lab（之江实验室）
Understanding the Role of Rehearsal Scale in Continual Learning under Varying Model Capacities
Institute of Intelligent Information Processing, Shanxi University（山西大学智能信息处理研究院）；Alliance Manchester Business School, The University of Manchester（曼彻斯特大学阿联酋商业学院）
Statistical Theory of Multi-stage Newton Iteration Algorithm for Online Continual Learning
School of Mathematics and Statistics, Xi’an Jiaotong University（西安交通大学数学与统计学院）；Department of Statistics, Beijing Normal University at Zhuhai（珠海市北京师范大学统计学系）
MM-Prompt: Cross-Modal Prompt Tuning for Continual Visual Question Answering
Khoury College of Computer Sciences, Northeastern University（东北大学克劳尔计算机科学学院）；New Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所模式识别新实验室）
Huazhong University of Science and Technology（华中科技大学）；Nanyang Technological University（南洋理工大学）；Singapore Institute of Manufacturing Technology, A*Star（新加坡科技研究局新加坡制造技术研究院）
Learning from streaming tasks leads a model to catastrophically erase unique experiences it absorbs from previous episodes. While regularization techniques such as LWF, SI, EWC have proven themselves as an effective avenue to overcome this issue by constraining important parameters of old tasks from changing when accepting new concepts, these approaches do not exploit common information of each task which can be shared to existing neurons. As a result, they do not scale well to large-scale problems since the parameter importance variables quickly explode. An Inter-Task Synaptic Mapping (ISYANA…
Prototype-Guided Non-Exemplar Continual Learning for Cross-subject EEG Decoding
Dept. of Artificial Intelligence Korea University Seoul, Republic of Korea（人工智能系 韩国大学首尔共和国）；Cognitive Engineering Korea University Seoul, Republic of Korea（认知工程 韩国大学首尔共和国）
Few-shot Continual Relation Extraction via Open Information Extraction
Hanoi University of Science and Technology（河内科技大学）；Oraichain Labs Inc.（Oraichain实验室公司）；VinAI Research（VinAI研究院）；Bytedance（字节跳动）；VNU University of Engineering and Technology（越南国家大学工程技术大学）；University of Oregon（俄勒冈大学）
