Catastrophic forgetting has been a significant problem hindering the deployment of deep learning algorithms in the continual learning setting. Numerous methods have been proposed to address the catastrophic forgetting problem where an agent loses its generalization power of old tasks while learning new tasks. We put forward an alternative strategy to handle the catastrophic forgetting with knowledge amalgamation (CFA), which learns a student network from multiple heterogeneous teacher models specializing in previous tasks and can be applied to current offline methods. The knowledge amalgamation process is carried out in a single-head manner with only a selected number of memorized samples and no annotations. The teachers and students do not need to share the same network structure, allowing heterogeneous tasks to be adapted to a compact or sparse data representation. We compare our method with competitive baselines from different strategies, demonstrating our approach's advantages.
GraphKeeper: Graph Domain-Incremental Learning via Knowledge Disentanglement and Preservation
SKLCCSE, School of Computer Science and Engineering, Beihang University（信息与通信工程学院，北京航空航天大学）；Shien-Ming Wu School of Intelligent Engineering, South China University of Technology（智能工程学院，华南理工大学）；Key Lab of Education Blockchain and Intelligent Technology, Guangxi Normal University（教育区块链与智能技术重点实验室，广西师范大学）
Indian Institute of Technology Kanpur（坎普尔印度理工学院）；Duke University（杜克大学）；Indian Institute of Technology Roorkee（鲁尔基印度理工学院）；University of Bath（巴斯大学）
We propose a novel approach for class incremental online learning in a limited data setting. This problem setting is challenging because of the following constraints: (1) Classes are given incrementally, which necessitates a class incremental learning approach; (2) Data for each class is given in an online fashion, i.e., each training example is seen only once during training; (3) Each class has very few training examples; and (4) We do not use or assume access to any replay/memory to store data from previous classes. Therefore, in this setting, we have to handle twofold problems of catastroph…
Nanyang Technological University（南洋理工大学）；Institute for Infocomm Research (I2R), A-STAR（新加坡科技研究局资讯通信研究院）
Knowledge tracing is the task of predicting a learner's future performance based on the history of the learner's performance. Current knowledge tracing models are built based on an extensive set of data that are collected from multiple schools. However, it is impossible to pool learner's data from all schools, due to data privacy and PDPA policies. Hence, this paper explores the feasibility of building knowledge tracing models while preserving the privacy of learners' data within their respective schools. This study is conducted using part of the ASSISTment 2009 dataset, with data from multipl…
Contrastive Regularization over LoRA for Multimodal Biomedical Image Incremental Learning
School of Computer Science and Engineering, Central South University（计算机科学与工程学院，中南大学）；School of Automation, Central South University（自动化学院，中南大学）；School of Computer Science and Technology, Beijing Jiaotong University（计算机科学与技术学院，北京交通大学）
Arizona State University（亚利桑那州立大学）；City University of Hong Kong（香港城市大学）
The ability to incrementally learn new classes is vital to all real-world artificial intelligence systems. A large portion of high-impact applications like social media, recommendation systems, E-commerce platforms, etc. can be represented by graph models. In this paper, we investigate the challenging yet practical problem, Graph Few-shot Class-incremental (Graph FCL) problem, where the graph model is tasked to classify both newly encountered classes and previously learned classes. Towards that purpose, we put forward a Graph Pseudo Incremental Learning paradigm by sampling tasks recurrently f…
Zhejiang University（浙江大学）；Stevens Institute of Technology（史蒂文斯理工学院）；Alibaba-Zhejiang University Joint Institute of Frontier Technologies（阿里巴巴-浙江大学前沿技术联合研究院）
A massive number of well-trained deep networks have been released by developers online. These networks may focus on different tasks and in many cases are optimized for different datasets. In this paper, we study how to exploit such heterogeneous pre-trained networks, known as teachers, so as to train a customized student network that tackles a set of selective tasks defined by the user. We assume no human annotations are available, and each teacher may be either single- or multi-task. To this end, we introduce a dual-step strategy that first extracts the task-specific knowledge from the hetero…
The University of Modena and Reggio Emilia（摩德纳-雷焦艾米利亚大学）
The staple of human intelligence is the capability of acquiring knowledge in a continuous fashion. In stark contrast, Deep Networks forget catastrophically and, for this reason, the sub-field of Class-Incremental Continual Learning fosters methods that learn a sequence of tasks incrementally, blending sequentially-gained knowledge into a comprehensive prediction. This work aims at assessing and overcoming the pitfalls of our previous proposal Dark Experience Replay (DER), a simple and effective approach that combines rehearsal and Knowledge Distillation. Inspired by the way our minds constantl…
Multi-class supervised learning systems require the knowledge of the entire range of labels they predict. Often when learnt incrementally, they suffer from catastrophic forgetting. To avoid this, generous leeways have to be made to the philosophy of incremental learning that either forces a part of the machine to not learn, or to retrain the machine again with a selection of the historic data. While these hacks work to various degrees, they do not adhere to the spirit of incremental learning. In this article, we redefine incremental learning with stringent conditions that do not allow for any …
Zhejiang University（浙江大学）；Stevens Institute of Technology（史蒂文斯理工学院）；Alibaba Group（阿里巴巴集团）；Yunnan University（云南大学）
An increasing number of well-trained deep networks have been released online by researchers and developers, enabling the community to reuse them in a plug-and-play way without accessing the training annotations. However, due to the large number of network variants, such public-available trained models are often of different architectures, each of which being tailored for a specific task or dataset. In this paper, we study a deep-model reusing task, where we are given as input pre-trained networks of heterogeneous architectures specializing in distinct tasks, as teacher models. We aim to learn …
Few-Shot Class-Incremental Learning with Prior Knowledge
East China Normal University（华东师范大学）；DiDi（滴滴）；Shanghai Jiao Tong University（上海交通大学）；Tsinghua Berkeley Shenzhen Institute（清华伯克利深圳学院）；Toronto Metropolitan University（多伦多都会大学）
ANU（澳大利亚国立大学）；Data to Decision CRC（数据决策合作研究中心）；Data61
Knowledge graph construction consists of two tasks: extracting information from external resources (knowledge population) and inferring missing information through a statistical analysis on the extracted information (knowledge completion). In many cases, insufficient external resources in the knowledge population hinder the subsequent statistical inference. The gap between these two processes can be reduced by an incremental population approach. We propose a new probabilistic knowledge graph factorisation method that benefits from the path structure of existing knowledge (e.g. syllogism) and e…
Class Incremental Fault Diagnosis under Limited Fault Data via Supervised Contrastive Knowledge Distillation
ZJU-UIUC Joint Institute at Zhejiang University（浙江大学-伊利诺伊大学厄巴纳-香槟分校联合研究所）；ZJU-UoE Institute at Zhejiang University（浙江大学-爱丁堡大学联合研究所）；College of Biomedical Engineering and Instrument Science at Zhejiang University（浙江大学生物医学工程与仪器科学学院）；College of Computer Science and Technology in Zhejiang University（浙江大学计算机科学与技术学院）
National University of Science and Technology（国立科技大学）
The ability to learn from incrementally arriving data is essential for any life-long learning system. However, standard deep neural networks forget the knowledge about the old tasks, a phenomenon called catastrophic forgetting, when trained on incrementally arriving data. We discuss the biases in current Generative Adversarial Networks (GAN) based approaches that learn the classifier by knowledge distillation from previously trained classifiers. These biases cause the trained classifier to perform poorly. We propose an approach to remove these biases by distilling knowledge from the classifier…
We propose an algorithm for incremental learning of classifiers. The proposed method enables an ensemble of classifiers to learn incrementally by accommodating new training data. We use an effective mechanism to overcome the stability-plasticity dilemma. In incremental learning, the general convention is to use only the knowledge acquired in the previous phase but not the previously seen data. We follow this convention by retaining the previously acquired knowledge which is relevant and using it along with the current data. The performance of each classifier is monitored to eliminate the poorl…
University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；Beihang University（北京航空航天大学）；Macquarie University（麦考瑞大学）
Social events provide valuable insights into group social behaviors and public concerns and therefore have many applications in fields such as product recommendation and crisis management. The complexity and streaming nature of social messages make it appealing to address social event detection in an incremental learning setting, where acquiring, preserving, and extending knowledge are major concerns. Most existing methods, including those based on incremental clustering and community detection, learn limited amounts of knowledge as they ignore the rich semantics and structural information con…
Harmony: A Unified Framework for Modality Incremental Learning
Peng Cheng Laboratory（鹏城实验室）；State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS)（中国科学院大学人工智能学院）
Zhejiang University（浙江大学）；University of Illinois Urbana–Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of Science and Technology Beijing（北京科技大学）
Intelligent fault diagnosis has made extraordinary advancements currently. Nonetheless, few works tackle class-incremental learning for fault diagnosis under limited fault data, i.e., imbalanced and long-tailed fault diagnosis, which brings about various notable challenges. Initially, it is difficult to extract discriminative features from limited fault data. Moreover, a well-trained model must be retrained from scratch to classify the samples from new classes, thus causing a high computational burden and time consumption. Furthermore, the model may suffer from catastrophic forgetting when tra…
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…
We present a novel class incremental learning approach based on deep neural networks, which continually learns new tasks with limited memory for storing examples in the previous tasks. Our algorithm is based on knowledge distillation and provides a principled way to maintain the representations of old models while adjusting to new tasks effectively. The proposed method estimates the relationship between the representation changes and the resulting loss increases incurred by model updates. It minimizes the upper bound of the loss increases using the representations, which exploits the estimated…
Deep learning architectures have shown remarkable results in scene understanding problems, however they exhibit a critical drop of performances when they are required to learn incrementally new tasks without forgetting old ones. This catastrophic forgetting phenomenon impacts on the deployment of artificial intelligence in real world scenarios where systems need to learn new and different representations over time. Current approaches for incremental learning deal only with image classification and object detection tasks, while in this work we formally introduce incremental learning for semanti…
Personalized Federated Domain-Incremental Learning based on Adaptive Knowledge Matching
School of Computer Science and Technology, Huazhong University of Science and Technology（华中科技大学计算机科学与技术学院）；Department of Computing, The Hong Kong Polytechnic University（香港理工大学计算学系）
Université Paris-Saclay（巴黎-萨克雷大学）；CEA（法国原子能和替代能源委员会）；IMT Atlantique（大西洋电信学院）；West University of Timisoara（蒂米什瓦拉西部大学）
Incremental learning enables artificial agents to learn from sequential data. While important progress was made by exploiting deep neural networks, incremental learning remains very challenging. This is particularly the case when no memory of past data is allowed and catastrophic forgetting has a strong negative effect. We tackle class-incremental learning without memory by adapting prediction bias correction, a method which makes predictions of past and new classes more comparable. It was proposed when a memory is allowed and cannot be directly used without memory, since samples of past class…
Continual learning has been a major problem in the deep learning community, where the main challenge is how to effectively learn a series of newly arriving tasks without forgetting the knowledge of previous tasks. Initiated by Learning without Forgetting (LwF), many of the existing works report that knowledge distillation is effective to preserve the previous knowledge, and hence they commonly use a soft label for the old task, namely a knowledge distillation (KD) loss, together with a class label for the new task, namely a cross entropy (CE) loss, to form a composite loss for a single neural …
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…
Current deep learning architectures suffer from catastrophic forgetting, a failure to retain knowledge of previously learned classes when incrementally trained on new classes. The fundamental roadblock faced by deep learning methods is that deep learning models are optimized as "black boxes," making it difficult to properly adjust the model parameters to preserve knowledge about previously seen data. To overcome the problem of catastrophic forgetting, we propose utilizing an alternative "white box" architecture derived from the principle of rate reduction, where each layer of the network is ex…
University of Alberta（阿尔伯塔大学）；Alberta Machine Intelligence Institute（阿尔伯塔机器智能研究所）
Predictions and predictive knowledge have seen recent success in improving not only robot control but also other applications ranging from industrial process control to rehabilitation. A property that makes these predictive approaches well suited for robotics is that they can be learned online and incrementally through interaction with the environment. However, a remaining challenge for many prediction-learning approaches is an appropriate choice of prediction-learning parameters, especially parameters that control the magnitude of a learning machine's updates to its predictions (the learning …
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 …
Quantum-Gated Task-interaction Knowledge Distillation for Pre-trained Model-based Class-Incremental Learning
School of Information and Communication Engineering, BUPT（北京邮电大学信息与通信工程学院）；BUPT: Beijing University of Posts and Telecommunications（北京邮电大学）；Engineering Research Center for Information Network, Ministry of Education（教育部信息网络工程研究中心）
University of Cambridge（剑桥大学）；Singapore Management University（新加坡管理大学）
Many deep learning applications, like keyword spotting, require the incorporation of new concepts (classes) over time, referred to as Class Incremental Learning (CIL). The major challenge in CIL is catastrophic forgetting, i.e., preserving as much of the old knowledge as possible while learning new tasks. Various techniques, such as regularization, knowledge distillation, and the use of exemplars, have been proposed to resolve this issue. However, prior works primarily focus on the incremental learning step, while ignoring the optimization during the base model training. We hypothesize that a …
On Distilling the Displacement Knowledge for Few-Shot Class-Incremental Learning
School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education（教育部新一代人工智能技术及交叉应用重点实验室（东南大学））
Indian Institute of Technology (BHU)（印度理工学院（瓦拉纳西））；Wichita State University（威奇托州立大学）
Incremental learning enables the learner to accommodate new knowledge without retraining the existing model. It is a challenging task which requires learning from new data as well as preserving the knowledge extracted from the previously accessed data. This challenge is known as the stability-plasticity dilemma. We propose AILearn, a generic model for incremental learning which overcomes the stability-plasticity dilemma by carefully integrating the ensemble of base classifiers trained on new data with the current ensemble without retraining the model from scratch using entire data. We demonstr…
The ability to incrementally learn new classes is crucial to the development of real-world artificial intelligence systems. In this paper, we focus on a challenging but practical few-shot class-incremental learning (FSCIL) problem. FSCIL requires CNN models to incrementally learn new classes from very few labelled samples, without forgetting the previously learned ones. To address this problem, we represent the knowledge using a neural gas (NG) network, which can learn and preserve the topology of the feature manifold formed by different classes. On this basis, we propose the TOpology-Preservi…
External Knowledge Injection for CLIP-Based Class-Incremental Learning
School of Artificial Intelligence, Nanjing University（人工智能学院，南京大学）；National Key Laboratory for Novel Software Technology, Nanjing University（新型软件技术国家实验室，南京大学）
