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 explicitly computed without back propagation. Under this paradigm, we demonstrate that, given a pre-trained network and new data classes, our approach can provably construct a new network that emulates joint training with all past and new classes. Finally, our experiments show that our proposed learning algorithm observes significantly less decay in classification performance, outperforming state of the art methods on MNIST and CIFAR-10 by a large margin and justifying the use of "white box" algorithms for incremental learning even for sufficiently complex image data.
Dimensionality reduction plays an important role in computer vision problems since it reduces computational cost and is often capable of yielding more discriminative data representation. In this context, Partial Least Squares (PLS) has presented notable results in tasks such as image classification and neural network optimization. However, PLS is infeasible on large datasets, such as ImageNet, because it requires all the data to be in memory in advance, which is often impractical due to hardware limitations. Additionally, this requirement prevents us from employing PLS on streaming application…
University of California, Davis（加州大学戴维斯分校）；Bosch Research North America（博世北美研究院）
Dimensionality reduction (DR) methods are commonly used for analyzing and visualizing multidimensional data. However, when data is a live streaming feed, conventional DR methods cannot be directly used because of their computational complexity and inability to preserve the projected data positions at previous time points. In addition, the problem becomes even more challenging when the dynamic data records have a varying number of dimensions as often found in real-world applications. This paper presents an incremental DR solution. We enhance an existing incremental PCA method in several ways to…
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）
University of Melbourne（墨尔本大学）；Walter and Eliza Hall Institute for Medical Research（沃尔特与伊丽莎·霍尔医学研究所）
Non-parametric dimensionality reduction techniques, such as t-SNE and UMAP, are proficient in providing visualizations for datasets of fixed sizes. However, they cannot incrementally map and insert new data points into an already provided data visualization. We present Self-Organizing Nebulous Growths (SONG), a parametric nonlinear dimensionality reduction technique that supports incremental data visualization, i.e., incremental addition of new data while preserving the structure of the existing visualization. In addition, SONG is capable of handling new data increments, no matter whether they…
Incremental Gauss--Newton Methods with Superlinear Convergence Rates
School of Data Science, Fudan University（复旦大学数据科学学院）；National University of Singapore（新加坡国立大学）；Department of Computer Science and Engineering, The Chinese University of Hong Kong（香港中文大学计算机科学与工程学系）
Tianjin University of Technology（天津理工大学）；Nankai University（南开大学）；Autonomous University of Barcelona（巴塞罗那自治大学）；Computer Vision Center（计算机视觉中心）
In class-incremental semantic segmentation, we have no access to the labeled data of previous tasks. Therefore, when incrementally learning new classes, deep neural networks suffer from catastrophic forgetting of previously learned knowledge. To address this problem, we propose to apply a self-training approach that leverages unlabeled data, which is used for the rehearsal of previous knowledge. Specifically, we first learn a temporary model for the current task, and then pseudo labels for the unlabeled data are computed by fusing information from the old model of the previous task and the cur…
University of Pennsylvania（宾夕法尼亚大学）；Rutgers University（罗格斯大学）
Recently, there has been growing interest in developing optimization methods for solving large-scale machine learning problems. Most of these problems boil down to the problem of minimizing an average of a finite set of smooth and strongly convex functions where the number of functions $n$ is large. Gradient descent method (GD) is successful in minimizing convex problems at a fast linear rate; however, it is not applicable to the considered large-scale optimization setting because of the high computational complexity. Incremental methods resolve this drawback of gradient methods by replacing t…
Carnegie Mellon University（卡内基梅隆大学）；University of Southern California（南加州大学）；Indian Institute of Technology Kanpur（坎普尔印度理工学院）；J.P. Morgan AI Research（摩根大通AI研究院）
The problem of minimizing an objective that can be written as the sum of a set of $n$ smooth and strongly convex functions is considered. The Incremental Quasi-Newton (IQN) method proposed here belongs to the family of stochastic and incremental methods that have a cost per iteration independent of $n$. IQN iterations are a stochastic version of BFGS iterations that use memory to reduce the variance of stochastic approximations. The convergence properties of IQN bridge a gap between deterministic and stochastic quasi-Newton methods. Deterministic quasi-Newton methods exploit the possibility of…
Ambiata；Australian National University（澳大利亚国立大学）；INRIA（法国国家信息与自动化研究所）；École Normale Supérieure（巴黎高等师范学院）
In this work we introduce a new optimisation method called SAGA in the spirit of SAG, SDCA, MISO and SVRG, a set of recently proposed incremental gradient algorithms with fast linear convergence rates. SAGA improves on the theory behind SAG and SVRG, with better theoretical convergence rates, and has support for composite objectives where a proximal operator is used on the regulariser. Unlike SDCA, SAGA supports non-strongly convex problems directly, and is adaptive to any inherent strong convexity of the problem. We give experimental results showing the effectiveness of our method.
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…
This paper presents a novel incremental learning algorithm for pedestrian motion prediction, with the ability to improve the learned model over time when data is incrementally available. In this setup, trajectories are modeled as simple segments called motion primitives. Transitions between motion primitives are modeled as Gaussian Processes. When new data is available, the motion primitives learned from the new data are compared with the previous ones by measuring the inner product of the motion primitive vectors. Similar motion primitives and transitions are fused and novel motion primitives…
City University of Hong Kong（香港城市大学）；Delft University of Technology（代尔夫特理工大学）；Nanyang Technological University（南洋理工大学）；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）
Safety is a top priority for civil aviation. New anomaly detection methods, primarily clustering methods, have been developed to monitor pilot operations and detect any risks from such flight data. However, all existing anomaly detection methods are offlline learning - the models are trained once using historical data and used for all future predictions. In practice, new flight data are accumulated continuously and analyzed every month at airlines. Clustering such dynamically growing data is challenging for an offlline method because it is memory and time intensive to re-train the model every …
In this study, importance of user inputs is studied in the context of personalizing human activity recognition models using incremental learning. Inertial sensor data from three body positions are used, and the classification is based on Learn++ ensemble method. Three different approaches to update models are compared: non-supervised, semi-supervised and supervised. Non-supervised approach relies fully on predicted labels, supervised fully on user labeled data, and the proposed method for semi-supervised learning, is a combination of these two. In fact, our experiments show that by relying on …
In this work we introduce an incremental learning framework for Click-Through-Rate (CTR) prediction and demonstrate its effectiveness for Taboola's massive-scale recommendation service. Our approach enables rapid capture of emerging trends through warm-starting from previously deployed models and fine tuning on "fresh" data only. Past knowledge is maintained via a teacher-student paradigm, where the teacher acts as a distillation technique, mitigating the catastrophic forgetting phenomenon. Our incremental learning framework enables significantly faster training and deployment cycles (x12 spee…
NICTA（澳大利亚国家信息与通信技术研究院）；Australian National University（澳大利亚国立大学）
Recent advances in optimization theory have shown that smooth strongly convex finite sums can be minimized faster than by treating them as a black box "batch" problem. In this work we introduce a new method in this class with a theoretical convergence rate four times faster than existing methods, for sums with sufficiently many terms. This method is also amendable to a sampling without replacement scheme that in practice gives further speed-ups. We give empirical results showing state of the art performance.
Federal University of Alagoas (UFAL)（阿拉戈阿斯联邦大学）；Linnaeus University（林奈大学）；Federal University of Bahia (UFBA)（巴伊亚联邦大学）；Dalhousie University（达尔豪斯大学）
Streaming data applications are becoming more common due to the ability of different information sources to continuously capture or produce data, such as sensors and social media. Despite recent advances, most visualization approaches, in particular, multidimensional projection or dimensionality reduction techniques, cannot be directly applied in such scenarios due to the transient nature of streaming data. Currently, only a few methods address this limitation using online or incremental strategies, continuously processing data, and updating the visualization. Despite their relative success, m…
We study decentralized non-convex finite-sum minimization problems described over a network of nodes, where each node possesses a local batch of data samples. In this context, we analyze a single-timescale randomized incremental gradient method, called GT-SAGA. GT-SAGA is computationally efficient as it evaluates one component gradient per node per iteration and achieves provably fast and robust performance by leveraging node-level variance reduction and network-level gradient tracking. For general smooth non-convex problems, we show the almost sure and mean-squared convergence of GT-SAGA to a…
Combining Statistical Features and Deep Encodings for Rehearsal-Based Class-Incremental Time Series Classification
atlanTTic – ICLAB, Universidade de Vigo（atlanTTic–ICLAB，维戈大学）；Centro Tecnolóxico de Telecomunicacións de Galicia (GRADIANT)（加利西亚电信技术中心（GRADIANT））；Universidade de Vigo（维戈大学）
University of Minnesota（明尼苏达大学）；Digital Technology Center（数字技术中心）
Belonging to the family of Bayesian nonparametrics, Gaussian process (GP) based approaches have well-documented merits not only in learning over a rich class of nonlinear functions, but also in quantifying the associated uncertainty. However, most GP methods rely on a single preselected kernel function, which may fall short in characterizing data samples that arrive sequentially in time-critical applications. To enable {\it online} kernel adaptation, the present work advocates an incremental ensemble (IE-) GP framework, where an EGP meta-learner employs an {\it ensemble} of GP learners, each h…
Deep neural networks (DNNs) have become a widely deployed model for numerous machine learning applications. However, their fixed architecture, substantial training cost, and significant model redundancy make it difficult to efficiently update them to accommodate previously unseen data. To solve these problems, we propose an incremental learning framework based on a grow-and-prune neural network synthesis paradigm. When new data arrive, the neural network first grows new connections based on the gradients to increase the network capacity to accommodate new data. Then, the framework iteratively …
In this paper, we propose an incremental learning method for end-to-end Automatic Speech Recognition (ASR) which enables an ASR system to perform well on new tasks while maintaining the performance on its originally learned ones. To mitigate catastrophic forgetting during incremental learning, we design a novel explainability-based knowledge distillation for ASR models, which is combined with a response-based knowledge distillation to maintain the original model's predictions and the "reason" for the predictions. Our method works without access to the training data of original tasks, which add…
