We propose two general and falsifiable hypotheses about expectations on generalization error when learning in the context of concept drift. One posits that as drift rate increases, the forgetting rate that minimizes generalization error will also increase and vice versa. The other posits that as a learner's forgetting rate increases, the bias/variance profile that minimizes generalization error will have lower variance and vice versa. These hypotheses lead to the concept of the sweet path, a path through the 3-d space of alternative drift rates, forgetting rates and bias/variance profiles on which generalization error will be minimized, such that slow drift is coupled with low forgetting and low bias, while rapid drift is coupled with fast forgetting and low variance. We present experiments that support the existence of such a sweet path. We also demonstrate that simple learners that select appropriate forgetting rates and bias/variance profiles are highly competitive with the state-of-the-art in incremental learners for concept drift on real-world drift problems.
Working with a non-stationary stream of data requires for the analysis system to evolve its model (the parameters as well as the structure) over time. In particular, concept drifts can occur, which makes it necessary to forget knowledge that has become obsolete. However, the forgetting is subjected to the stability-plasticity dilemma, that is, increasing forgetting improve reactivity of adapting to the new data while reducing the robustness of the system. Based on a set of inference rules, Evolving Fuzzy Systems-EFS-have proven to be effective in solving the data stream learning problem. Howev…
China University of Petroleum, Beijing Campus (CUP)（中国石油大学（北京）校区）；Department of Automation, College of Information Science and Engineering, China University of Petroleum, Beijing Campus (CUP)（中国石油大学（北京）校区信息科学与工程学院自动化系）
Recent years have witnessed enormous progress of online learning. However, a major challenge on the road to artificial agents is concept drift, that is, the data probability distribution would change where the data instance arrives sequentially in a stream fashion, which would lead to catastrophic forgetting and degrade the performance of the model. In this paper, we proposed a new Bilevel Online Deep Learning (BODL) framework, which combine bilevel optimization strategy and online ensemble classifier. In BODL algorithm, we use an ensemble classifier, which use the output of different hidden l…
Evolving Machine Learning in Non-Stationary Environments: A Unified Survey of Drift, Forgetting, and Adaptation
School of Architecture, Technology and Engineering, University of Brighton（建筑、技术与工程学院，布里奇顿大学）；Department of Mathematics and Computer Science, Eindhoven University of Technology（数学与计算机科学系，埃因霍温理工大学）
CapTrack: Multifaceted Evaluation of Forgetting in LLM Post-Training
Thomson Reuters Foundational Research（汤姆森路透基础研究）；Tübingen AI Center, University of Tübingen（图宾根人工智能中心，图宾根大学）；Munich Center for Machine Learning (MCML), Technical University Munich（慕尼黑机器学习中心（MCML），慕尼黑技术大学）；Imperial College London（伦敦帝国理工学院）
National University of Singapore（新加坡国立大学）；Massachusetts Institute of Technology（麻省理工学院）
We introduce data-driven decision-making algorithms that achieve state-of-the-art \emph{dynamic regret} bounds for non-stationary bandit settings. These settings capture applications such as advertisement allocation, dynamic pricing, and traffic network routing in changing environments. We show how the difficulty posed by the (unknown \emph{a priori} and possibly adversarial) non-stationarity can be overcome by an unconventional marriage between stochastic and adversarial bandit learning algorithms. Our main contribution is a general algorithmic recipe for a wide variety of non-stationary band…
Energy Systems Institute SB RAS（俄罗斯科学院西伯利亚分院能源系统研究所）；Irkutsk State University（伊尔库茨克国立大学）；Queens University Belfast（贝尔法斯特女王大学）
Concept drift has potential in smart grid analysis because the socio-economic behaviour of consumers is not governed by the laws of physics. Likewise there are also applications in wind power forecasting. In this paper we present decision tree ensemble classification method based on the Random Forest algorithm for concept drift. The weighted majority voting ensemble aggregation rule is employed based on the ideas of Accuracy Weighted Ensemble (AWE) method. Base learner weight in our case is computed for each sample evaluation using base learners accuracy and intrinsic proximity measure of Rand…
PASs-MoE: Mitigating Misaligned Co-drift among Router and Experts via Pathway Activation Subspaces for Continual Learning
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；National University of Singapore（新加坡国立大学）；Southeast University, Nanjing, China（南京东南大学）；Wuhan AI Research, Wuhan, China（武汉人工智能研究院）
Northwestern Polytechnical University（西北工业大学）；Universitat Autonoma de Barcelona（巴塞罗那自治大学）；Huawei Kirin Solution（华为麒麟解决方案）
Class-incremental learning of deep networks sequentially increases the number of classes to be classified. During training, the network has only access to data of one task at a time, where each task contains several classes. In this setting, networks suffer from catastrophic forgetting which refers to the drastic drop in performance on previous tasks. The vast majority of methods have studied this scenario for classification networks, where for each new task the classification layer of the network must be augmented with additional weights to make room for the newly added classes. Embedding net…
Overcoming Domain Drift in Online Continual Learning
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Suzhou University of Science and Technology（苏州科技大学）；Youtu Lab, Tencent（腾讯优图实验室）；College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）
Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning
School of Computer Science and Technology, Xi’an Jiaotong University（西安交通大学计算机科学与技术学院）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）
Advanced Research Lab, NavInfo Europe（四维图新欧洲高级研究实验室）；Eindhoven University of Technology（埃因霍温理工大学）
Humans excel at lifelong learning, as the brain has evolved to be robust to distribution shifts and noise in our ever-changing environment. Deep neural networks (DNNs), however, exhibit catastrophic forgetting and the learned representations drift drastically as they encounter a new task. This alludes to a different error-based learning mechanism in the brain. Unlike DNNs, where learning scales linearly with the magnitude of the error, the sensitivity to errors in the brain decreases as a function of their magnitude. To this end, we propose \textit{ESMER} which employs a principled mechanism t…
Université de Montréal（蒙特利尔大学）；MILA - Quebec AI Institute（MILA - 魁北克人工智能研究所）
We study how different output layer parameterizations of a deep neural network affects learning and forgetting in continual learning settings. The following three effects can cause catastrophic forgetting in the output layer: (1) weights modifications, (2) interference, and (3) projection drift. In this paper, our goal is to provide more insights into how changing the output layer parameterization may address (1) and (2). Some potential solutions to those issues are proposed and evaluated here in several continual learning scenarios. We show that the best-performing type of output layer depend…
Modern machine learning systems need to be able to cope with constantly arriving and changing data. Two main areas of research dealing with such scenarios are continual learning and data stream mining. Continual learning focuses on accumulating knowledge and avoiding forgetting, assuming information once learned should be stored. Data stream mining focuses on adaptation to concept drift and discarding outdated information, assuming that only the most recent data is relevant. While these two areas are mainly being developed in separation, they offer complementary views on the problem of learnin…
We tackle the problem of Federated Learning in the non i.i.d. case, in which local models drift apart, inhibiting learning. Building on an analogy with Lifelong Learning, we adapt a solution for catastrophic forgetting to Federated Learning. We add a penalty term to the loss function, compelling all local models to converge to a shared optimum. We show that this can be done efficiently for communication (adding no further privacy risks), scaling with the number of nodes in the distributed setting. Our experiments show that this method is superior to competing ones for image recognition on the …
Exploring the Impact of Parameter Update Magnitude on Forgetting and Generalization of Continual Learning
Institute of Intelligent Information Processing, Shanxi University（山西大学智能信息处理研究所）；Alliance Manchester Business School, The University of Manchester（曼彻斯特大学阿利安斯商学院）
On Forgetting and Stability of Score-based Generative models
Sorbonne Université and Université Paris Cité, CNRS, LPSM（索邦大学和巴黎大学，CNRS，LPSM）；Center for Statistics and Images, Mines Paris, PSL University（统计与图像中心，巴黎 Mines，PSL 大学）；CREST, ENSAE Paris, Institut Polytechnique de Paris（CREST，ENSAE 巴黎，巴黎理工学院）
BCAM-Basque Center for Applied Mathematics（巴斯克应用数学中心）；University of the Basque Country UPV/EHU（巴斯克大学UPV/EHU）
The statistical characteristics of instance-label pairs often change with time in practical scenarios of supervised classification. Conventional learning techniques adapt to such concept drift accounting for a scalar rate of change by means of a carefully chosen learning rate, forgetting factor, or window size. However, the time changes in common scenarios are multidimensional, i.e., different statistical characteristics often change in a different manner. This paper presents adaptive minimax risk classifiers (AMRCs) that account for multidimensional time changes by means of a multivariate and…
In recent years, we have seen a handful of work on inference algorithms over non-stationary data streams. Given their flexibility, Bayesian non-parametric models are a good candidate for these scenarios. However, reliable streaming inference under the concept drift phenomenon is still an open problem for these models. In this work, we propose a variational inference algorithm for Dirichlet process mixture models. Our proposal deals with the concept drift by including an exponential forgetting over the prior global parameters. Our algorithm allows to adapt the learned model to the concept drift…
University of Groningen（格罗宁根大学）；Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence（伯努利数学、计算机科学与人工智能研究所）；Bielefeld University（比勒费尔德大学）
We present a modelling framework for the investigation of prototype-based classifiers in non-stationary environments. Specifically, we study Learning Vector Quantization (LVQ) systems trained from a stream of high-dimensional, clustered data.We consider standard winner-takes-all updates known as LVQ1. Statistical properties of the input data change on the time scale defined by the training process. We apply analytical methods borrowed from statistical physics which have been used earlier for the exact description of learning in stationary environments. The suggested framework facilitates the c…
University of Guelph（圭尔夫大学）；Vector Institute for Artificial Intelligence（矢量人工智能研究所）；Uber AI
Continual learning is the problem of sequentially learning new tasks or knowledge while protecting previously acquired knowledge. However, catastrophic forgetting poses a grand challenge for neural networks performing such learning process. Thus, neural networks that are deployed in the real world often struggle in scenarios where the data distribution is non-stationary (concept drift), imbalanced, or not always fully available, i.e., rare edge cases. We propose a Differentiable Hebbian Consolidation model which is composed of a Differentiable Hebbian Plasticity (DHP) Softmax layer that adds a…
Continuous Evolution Pool: Taming Recurring Concept Drift in Online Time Series Forecasting
University of Electronic Science and Technology of China（电子科技大学）；Griffith University（格里菲斯大学）；Peking University（北京大学）；Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen（格罗宁根大学伯努利数学、计算机科学与人工智能研究所）；Aksum University（阿克苏姆大学）；Bielefeld University（比勒费尔德大学）
We present a modelling framework for the investigation of supervised learning in non-stationary environments. Specifically, we model two example types of learning systems: prototype-based Learning Vector Quantization (LVQ) for classification and shallow, layered neural networks for regression tasks. We investigate so-called student teacher scenarios in which the systems are trained from a stream of high-dimensional, labeled data. Properties of the target task are considered to be non-stationary due to drift processes while the training is performed. Different types of concept drift are studied…
