Deep learning has proved to be a successful paradigm for solving many challenges in machine learning. However, deep neural networks fail when trained sequentially on multiple tasks, a shortcoming known as catastrophic forgetting in the continual learning literature. Despite a recent flourish of learning algorithms successfully addressing this problem, we find that provable guarantees against catastrophic forgetting are lacking. In this work, we study the relationship between learning and forgetting by looking at the geometry of neural networks' loss landscape. We offer a unifying perspective on a family of continual learning algorithms, namely methods based on parameter isolation, and we establish guarantees on catastrophic forgetting for some of them.
Task-Driven Subspace Decomposition for Knowledge Sharing and Isolation in LoRA-based Continual Learning
Department of XXX, University of YYY, Location, Country（XXX部门，YYY大学，地点，国家）；School of ZZZ, Institute of WWW, Location, Country（ZZZ学院，WWW研究所，地点，国家）；State Key Laboratory of Integrated Services Networks, School of Telecommunications Engineering, Xidian University, Xi'an, China（信息服务网络国家重点实验室，电信工程学院，西安电子科技大学，西安，中国）；School of Electronic Engineering, Xidian University, Xi'an, China（电子工程学院，西安电子科技大学，西安，中国）
Aqemia；McGill University（麦吉尔大学）；Mila；RIKEN（理化学研究所）；The University of Tokyo（东京大学）
In Continual Learning settings, deep neural networks are prone to Catastrophic Forgetting. Orthogonal Gradient Descent was proposed to tackle the challenge. However, no theoretical guarantees have been proven yet. We present a theoretical framework to study Continual Learning algorithms in the Neural Tangent Kernel regime. This framework comprises closed form expression of the model through tasks and proxies for Transfer Learning, generalisation and tasks similarity. In this framework, we prove that OGD is robust to Catastrophic Forgetting then derive the first generalisation bound for SGD and…
Jagiellonian University（雅盖隆大学）；Polish Academy of Sciences（波兰科学院）；Warsaw University of Technology（华沙理工大学）；Tooploox
We introduce a new training paradigm that enforces interval constraints on neural network parameter space to control forgetting. Contemporary Continual Learning (CL) methods focus on training neural networks efficiently from a stream of data, while reducing the negative impact of catastrophic forgetting, yet they do not provide any firm guarantees that network performance will not deteriorate uncontrollably over time. In this work, we show how to put bounds on forgetting by reformulating continual learning of a model as a continual contraction of its parameter space. To that end, we propose Hy…
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）
Is Our Benchmark Enough? An Analysis of Continual Learning for MLLMs
School of Computer Science and Statistics, Trinity College Dublin（都柏林圣三一学院计算机科学与统计学院）；Department of Mathematics and Computer Science, Eindhoven University of Technology（埃因霍温理工大学数学与计算机科学系）
Parameter Importance-Driven Continual Learning for Foundation Models
Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beihang University（未来区块链与隐私计算先进创新中心，北京航空航天大学）；School of Artificial Intelligence, Beihang University（人工智能学院，北京航空航天大学）
Rehearsal-Free Modular and Compositional Continual Learning for Language Models
Bosch Center for Artificial Intelligence（博世人工智能中心）；LMU Munich（慕尼黑大学）；Hochschule der Medien（斯图加特媒体大学）；Karlsruhe University of Applied Sciences（卡尔斯鲁厄应用技术大学）
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）
Columbia University（哥伦比亚大学）；Carnegie Mellon University（卡内基梅隆大学）
Continual learning is an emerging paradigm in machine learning, wherein a model is exposed in an online fashion to data from multiple different distributions (i.e. environments), and is expected to adapt to the distribution change. Precisely, the goal is to perform well in the new environment, while simultaneously retaining the performance on the previous environments (i.e. avoid "catastrophic forgetting") -- without increasing the size of the model. While this setup has enjoyed a lot of attention in the applied community, there hasn't be theoretical work that even formalizes the desired guara…
Current deep learning methods are regarded as favorable if they empirically perform well on dedicated test sets. This mentality is seamlessly reflected in the resurfacing area of continual learning, where consecutively arriving data is investigated. The core challenge is framed as protecting previously acquired representations from being catastrophically forgotten. However, comparison of individual methods is nevertheless performed in isolation from the real world by monitoring accumulated benchmark test set performance. The closed world assumption remains predominant, i.e. models are evaluate…
Training a neural network for a classification task typically assumes that the data to train are given from the beginning. However, in the real world, additional data accumulate gradually and the model requires additional training without accessing the old training data. This usually leads to the catastrophic forgetting problem which is inevitable for the traditional training methodology of neural networks. In this paper, we propose a continual learning method that is able to learn additional tasks while retaining the performance of previously learned tasks by stacking parameters. Composed of …
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…
Unifying Detection and Adaptation in Task-Free Continual Learning
School of Control Science and Engineering, Shandong University（山东大学控制科学与工程学院）；The Hong Kong University of Science and Technology（香港科技大学）；Shandong University（山东大学）；Qilu Hospital of Shandong University（山东大学齐鲁医院）
Convergence of Continual Learning in Homogeneous Deep Networks
Blavatnik School of Computer Science and AI, Tel Aviv University（塔夫茨大学Blavatnik计算机科学与人工智能学院）；Princeton University（普林斯顿大学）；Department of Electrical and Computing Engineering, Technion（技术学院电子与计算工程系）
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…
