Federated Class-Incremental Learning (FCIL) refers to a scenario where a dynamically changing number of clients collaboratively learn an ever-increasing number of incoming tasks. FCIL is known to suffer from local forgetting due to class imbalance at each client and global forgetting due to class imbalance across clients. We develop a mathematical framework for FCIL that formulates local and global forgetting. Then, we propose an approach called Hybrid Rehearsal (HR), which utilizes latent exemplars and data-free techniques to address local and global forgetting, respectively. HR employs a customized autoencoder designed for both data classification and the generation of synthetic data. To determine the embeddings of new tasks for all clients in the latent space of the encoder, the server uses the Lennard-Jones Potential formulations. Meanwhile, at the clients, the decoder decodes the stored low-dimensional latent space exemplars back to the high-dimensional input space, used to address local forgetting. To overcome global forgetting, the decoder generates synthetic data. Furthermore, our mathematical framework proves that our proposed approach HR can, in principle, tackle the two local and global forgetting challenges. In practice, extensive experiments demonstrate that while preserving privacy, our proposed approach outperforms the state-of-the-art baselines on multiple FCIL benchmarks with low compute and memory footprints.
Humans are capable of learning new concepts from only a few (labeled) exemplars, incrementally and continually. This happens within the context that we can differentiate among the exemplars, and between the exemplars and large amounts of other data (unlabeled and labeled). This suggests, in human learning, supervised learning of concepts based on exemplars takes place within the larger context of contrastive self-supervised learning (CSSL) based on unlabeled and labeled data. We discuss extending CSSL (1) to be based mainly on exemplars and only secondly on data augmentation, and (2) to apply …
Graduate School of Arts and Sciences（艺术与科学研究生院）；Columbia University, New York, USA（哥伦比亚大学）；School of Artificial Intelligence（人工智能学院）；Hebei Institute of Communications, Shijiazhuang, PR China（河北通信学院）
Gwangju Institute of Science and Technology (GIST)（光州科学技术院）
Incremental learning suffers from two challenging problems; forgetting of old knowledge and intransigence on learning new knowledge. Prediction by the model incrementally learned with a subset of the dataset are thus uncertain and the uncertainty accumulates through the tasks by knowledge transfer. To prevent overfitting to the uncertain knowledge, we propose to penalize confident fitting to the uncertain knowledge by the Maximum Entropy Regularizer (MER). Additionally, to reduce class imbalance and induce a self-paced curriculum on new classes, we exclude a few samples from the new classes in…
Shenyang Institute of Automation, Chinese Academy of Sciences（中国科学院沈阳自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Northwestern University（西北大学）；University of Technology Sydney（悉尼科技大学）
Federated learning (FL) has attracted growing attention via data-private collaborative training on decentralized clients. However, most existing methods unrealistically assume object classes of the overall framework are fixed over time. It makes the global model suffer from significant catastrophic forgetting on old classes in real-world scenarios, where local clients often collect new classes continuously and have very limited storage memory to store old classes. Moreover, new clients with unseen new classes may participate in the FL training, further aggravating the catastrophic forgetting o…
REAL: Representation Enhanced Analytic Learning for Exemplar-free Class-incremental Learning
Shien-Ming Wu School of Intelligent Engineering（申铭武智能工程学院）；School of Future Technology（未来技术学院）；Department of Electrical and Electronic Engineering（电气与电子工程系）
Georgia Institute of Technology（佐治亚理工学院）；SRI International（斯坦福国际研究院）
As progress is made on training machine learning models on incrementally expanding classification tasks (i.e., incremental learning), a next step is to translate this progress to industry expectations. One technique missing from incremental learning is automatic architecture design via Neural Architecture Search (NAS). In this paper, we show that leveraging NAS for incremental learning results in strong performance gains for classification tasks. Specifically, we contribute the following: first, we create a strong baseline approach for incremental learning based on Differentiable Architecture …
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…
An Empirical Analysis of Forgetting in Pre-trained Models with Incremental Low-Rank Updates
Computer Vision Center, Spain（西班牙计算机视觉中心）；Department of Computer Science, Universitat Autònoma de Barcelona, Spain（西班牙巴塞罗那自治大学计算机科学系）；Department of Information Engineering, University of Florence, Italy（意大利佛罗伦萨大学信息工程系）
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）
Seoul National University（首尔国立大学）；Clova AI Research（克洛娃人工智能研究院）；NAVER Corp（Naver公司）；Surromind Robotics（Surromind机器人公司）
Catastrophic forgetting is a problem of neural networks that loses the information of the first task after training the second task. Here, we propose a method, i.e. incremental moment matching (IMM), to resolve this problem. IMM incrementally matches the moment of the posterior distribution of the neural network which is trained on the first and the second task, respectively. To make the search space of posterior parameter smooth, the IMM procedure is complemented by various transfer learning techniques including weight transfer, L2-norm of the old and the new parameter, and a variant of dropo…
Catastrophic forgetting is one of the major challenges on the road for continual learning systems, which are presented with an on-line stream of tasks. The field has attracted considerable interest and a diverse set of methods have been presented for overcoming this challenge. Learning without Forgetting (LwF) is one of the earliest and most frequently cited methods. It has the advantages of not requiring the storage of samples from the previous tasks, of implementation simplicity, and of being well-grounded by relying on knowledge distillation. However, the prevailing view is that while it sh…
Seoul National University（首尔大学）；NAVER AI Lab（NAVER AI实验室）；NAVER Clova
This paper introduces a solid state-of-the-art baseline for a class-incremental semantic segmentation (CISS) problem. While the recent CISS algorithms utilize variants of the knowledge distillation (KD) technique to tackle the problem, they failed to fully address the critical challenges in CISS causing the catastrophic forgetting; the semantic drift of the background class and the multi-label prediction issue. To better address these challenges, we propose a new method, dubbed SSUL-M (Semantic Segmentation with Unknown Label with Memory), by carefully combining techniques tailored for semanti…
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Shanghai Institute for Advanced Study, Zhejiang University（浙江大学上海高等研究院）
With the memory-resource-limited constraints, class-incremental learning (CIL) usually suffers from the "catastrophic forgetting" problem when updating the joint classification model on the arrival of newly added classes. To cope with the forgetting problem, many CIL methods transfer the knowledge of old classes by preserving some exemplar samples into the size-constrained memory buffer. To utilize the memory buffer more efficiently, we propose to keep more auxiliary low-fidelity exemplar samples rather than the original real high-fidelity exemplar samples. Such a memory-efficient exemplar pre…
In class-incremental learning, the objective is to learn a number of classes sequentially without having access to the whole training data. However, due to a problem known as catastrophic forgetting, neural networks suffer substantial performance drop in such settings. The problem is often approached by experience replay, a method which stores a limited number of samples to be replayed in future steps to reduce forgetting of the learned classes. When using a pretrained network as a feature extractor, we show that instead of training a single classifier incrementally, it is better to train a nu…
MLFCIL: A Multi-Level Forgetting Mitigation Framework for Federated Class-Incremental Learning in LEO Satellites
Gannan University of Science and Technology（赣南科技学院）；Tsinghua University（清华大学）；Queen University（女王大学）；Lingnan University（岭南大学）；Central South University（中南大学）
Institute for Intelligent Systems（智能系统研究所）；University of Johannesburg（约翰内斯堡大学）
Catastrophic forgetting in neural networks during incremental learning remains a challenging problem. Previous research investigated catastrophic forgetting in fully connected networks, with some earlier work exploring activation functions and learning algorithms. Applications of neural networks have been extended to include similarity learning. Understanding how similarity learning loss functions would be affected by catastrophic forgetting is of significant interest. Our research investigates catastrophic forgetting for four well-known similarity-based loss functions during incremental class…
PASS++: A Dual Bias Reduction Framework for Non-Exemplar Class-Incremental Learning
Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science and Innovation, Chinese Academy of Sciences（中国科学院香港创新研究院人工智能与机器人中心）；Institute of Automation of Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learning
IDEAS NCBR；Warsaw University of Technology（华沙工业大学）；Gdańsk University of Technology（格但斯克工业大学）；Tooploox；Autonomous University of Barcelona（巴塞罗那自治大学）；Computer Vision Center（计算机视觉中心）
Human activity recognition (HAR) has been a classic research problem. In particular, with recent machine learning (ML) techniques, the recognition task has been largely investigated by companies and integrated into their products for customers. However, most of them apply a predefined activity set and conduct the learning process on the cloud, hindering specific personalizations from end users (i.e., edge devices). Even though recent progress in Incremental Learning allows learning new-class data on the fly, the learning process is generally conducted on the cloud, requiring constant data exch…
Real-world applications require the classification model to adapt to new classes without forgetting old ones. Correspondingly, Class-Incremental Learning (CIL) aims to train a model with limited memory size to meet this requirement. Typical CIL methods tend to save representative exemplars from former classes to resist forgetting, while recent works find that storing models from history can substantially boost the performance. However, the stored models are not counted into the memory budget, which implicitly results in unfair comparisons. We find that when counting the model size into the tot…
We investigate the performance of DNNs when trained on class-incremental visual problems consisting of initial training, followed by retraining with added visual classes. Catastrophic forgetting (CF) behavior is measured using a new evaluation procedure that aims at an application-oriented view of incremental learning. In particular, it imposes that model selection must be performed on the initial dataset alone, as well as demanding that retraining control be performed only using the retraining dataset, as initial dataset is usually too large to be kept. Experiments are conducted on class-incr…
University at Buffalo（布法罗大学）；Penn State Erie（宾州州立大学伊利分校）
Exemplar-free Class-incremental Learning (CIL) is a challenging problem because rehearsing data from previous phases is strictly prohibited, causing catastrophic forgetting of Deep Neural Networks (DNNs). In this paper, we present iVoro, a holistic framework for CIL, derived from computational geometry. We found Voronoi Diagram (VD), a classical model for space subdivision, is especially powerful for solving the CIL problem, because VD itself can be constructed favorably in an incremental manner -- the newly added sites (classes) will only affect the proximate classes, making the non-contiguou…
A plain well-trained deep learning model often does not have the ability to learn new knowledge without forgetting the previously learned knowledge, which is known as catastrophic forgetting. Here we propose a novel method, SupportNet, to efficiently and effectively solve the catastrophic forgetting problem in the class incremental learning scenario. SupportNet combines the strength of deep learning and support vector machine (SVM), where SVM is used to identify the support data from the old data, which are fed to the deep learning model together with the new data for further training so that …
School of Communication & Information Engineering, Shanghai University（上海大学通信与信息工程学院）
The main purpose of incremental learning is to learn new knowledge while not forgetting the knowledge which have been learned before. At present, the main challenge in this area is the catastrophe forgetting, namely the network will lose their performance in the old tasks after training for new tasks. In this paper, we introduce an ensemble method of incremental classifier to alleviate this problem, which is based on the cosine distance between the output feature and the pre-defined center, and can let each task to be preserved in different networks. During training, we make use of PEDCC-Loss …
The Australian National University（澳大利亚国立大学）；Monash University（莫纳什大学）；Data61-CSIRO（Data61-澳大利亚联邦科学与工业研究组织）
Neural networks notoriously suffer from the problem of catastrophic forgetting, the phenomenon of forgetting the past knowledge when acquiring new knowledge. Overcoming catastrophic forgetting is of significant importance to emulate the process of "incremental learning", where the model is capable of learning from sequential experience in an efficient and robust way. State-of-the-art techniques for incremental learning make use of knowledge distillation towards preventing catastrophic forgetting. Therein, one updates the network while ensuring that the network's responses to previously seen co…
University of Hamburg（汉堡大学）；University of Malaya（马来亚大学）
Lifelong learning is a long-standing aim for artificial agents that act in dynamic environments, in which an agent needs to accumulate knowledge incrementally without forgetting previously learned representations. We investigate methods for learning from data produced by event cameras and compare techniques to mitigate forgetting while learning incrementally. We propose a model that is composed of both, feature extraction and continuous learning. Furthermore, we introduce a habituation-based method to mitigate forgetting. Our experimental results show that the combination of different techniqu…
One of the major limitations of deep learning models is that they face catastrophic forgetting in an incremental learning scenario. There have been several approaches proposed to tackle the problem of incremental learning. Most of these methods are based on knowledge distillation and do not adequately utilize the information provided by older task models, such as uncertainty estimation in predictions. The predictive uncertainty provides the distributional information can be applied to mitigate catastrophic forgetting in a deep learning framework. In the proposed work, we consider a Bayesian fo…
Traditional learning systems are trained in closed-world for a fixed number of classes, and need pre-collected datasets in advance. However, new classes often emerge in real-world applications and should be learned incrementally. For example, in electronic commerce, new types of products appear daily, and in a social media community, new topics emerge frequently. Under such circumstances, incremental models should learn several new classes at a time without forgetting. We find a strong correlation between old and new classes in incremental learning, which can be applied to relate and facilitat…
Boise State University（博伊西州立大学）；University of Delaware（特拉华大学）
Deep Neural Networks (DNNs) have two key deficiencies, their dependence on high precision computing and their inability to perform sequential learning, that is, when a DNN is trained on a first task and the same DNN is trained on the next task it forgets the first task. This phenomenon of forgetting previous tasks is also referred to as catastrophic forgetting. On the other hand a mammalian brain outperforms DNNs in terms of energy efficiency and the ability to learn sequentially without catastrophically forgetting. Here, we use bio-inspired Spike Timing Dependent Plasticity (STDP)in the featu…
