Most predictive models assume that training and test data are generated from a stationary process. However, this assumption does not hold true in practice. In this paper, we consider the scenario of a gradual concept drift due to the underlying non-stationarity of the data source. While previous work has investigated this scenario under a supervised-learning and adaption conditions, few have addressed the common, real-world scenario when labels are only available during training. We propose a novel, iterative algorithm for unsupervised adaptation of predictive models. We show that the performance of our batch adapted prediction algorithm is better than that of its corresponding unadapted version. The proposed algorithm provides similar (or better, in most cases) performance within significantly less run time compared to other state of the art methods. We validate our claims though extensive numerical evaluations on both synthetic and real data.
Disney Research（迪士尼研究院）；KTH Royal Institute of Technology（瑞典皇家理工学院）
We study a mini-batch diversification scheme for stochastic gradient descent (SGD). While classical SGD relies on uniformly sampling data points to form a mini-batch, we propose a non-uniform sampling scheme based on the Determinantal Point Process (DPP). The DPP relies on a similarity measure between data points and gives low probabilities to mini-batches which contain redundant data, and higher probabilities to mini-batches with more diverse data. This simultaneously balances the data and leads to stochastic gradients with lower variance. We term this approach Diversified Mini-Batch SGD (DM-…
Convolutional neural networks provide visual features that perform remarkably well in many computer vision applications. However, training these networks requires significant amounts of supervision. This paper introduces a generic framework to train deep networks, end-to-end, with no supervision. We propose to fix a set of target representations, called Noise As Targets (NAT), and to constrain the deep features to align to them. This domain agnostic approach avoids the standard unsupervised learning issues of trivial solutions and collapsing of features. Thanks to a stochastic batch reassignme…
Universidade Federal de Pernambuco（伯南布哥联邦大学）；Center of Informatics - CIn（信息中心）
Nowadays, with the advance of technology, there is an increasing amount of unstructured data being generated every day. However, it is a painful job to label and organize it. Labeling is an expensive, time-consuming, and difficult task. It is usually done manually, which collaborates with the incorporation of noise and errors to the data. Hence, it is of great importance to developing intelligent models that can benefit from both labeled and unlabeled data. Currently, works on unsupervised and semi-supervised learning are still being overshadowed by the successes of purely supervised learning.…
Likelihood from a generative model is a natural statistic for detecting out-of-distribution (OoD) samples. However, generative models have been shown to assign higher likelihood to OoD samples compared to ones from the training distribution, preventing simple threshold-based detection rules. We demonstrate that OoD detection fails even when using more sophisticated statistics based on the likelihoods of individual samples. To address these issues, we propose a new method that leverages batch normalization. We argue that batch normalization for generative models challenges the traditional i.i.d…
Data are being collected from various aspects of life. These data can often arrive in chunks/batches. Traditional static clustering algorithms are not suitable for dynamic datasets, i.e., when data arrive in streams of chunks/batches. If we apply a conventional clustering technique over the combined dataset, then every time a new batch of data comes, the process can be slow and wasteful. Moreover, it can be challenging to store the combined dataset in memory due to its ever-increasing size. As a result, various incremental clustering techniques have been proposed. These techniques need to effi…
A critically important, ubiquitous, and yet poorly understood ingredient in modern deep networks (DNs) is batch normalization (BN), which centers and normalizes the feature maps. To date, only limited progress has been made understanding why BN boosts DN learning and inference performance; work has focused exclusively on showing that BN smooths a DN's loss landscape. In this paper, we study BN theoretically from the perspective of function approximation; we exploit the fact that most of today's state-of-the-art DNs are continuous piecewise affine (CPA) splines that fit a predictor to the train…
We propose a novel unsupervised domain adaptation framework based on domain-specific batch normalization in deep neural networks. We aim to adapt to both domains by specializing batch normalization layers in convolutional neural networks while allowing them to share all other model parameters, which is realized by a two-stage algorithm. In the first stage, we estimate pseudo-labels for the examples in the target domain using an external unsupervised domain adaptation algorithm---for example, MSTN or CPUA---integrating the proposed domain-specific batch normalization. The second stage learns th…
The state-of-the-art unsupervised contrastive visual representation learning methods that have emerged recently (SimCLR, MoCo, SwAV) all make use of data augmentations in order to construct a pretext task of instant discrimination consisting of similar and dissimilar pairs of images. Similar pairs are constructed by randomly extracting patches from the same image and applying several other transformations such as color jittering or blurring, while transformed patches from different image instances in a given batch are regarded as dissimilar pairs. We argue that this approach can result similar…
University of Waikato（怀卡托大学）；Télécom ParisTech（巴黎高科电信学院）；Dalhousie University（达尔豪斯大学）
Concept drift detection is a crucial task in data stream evolving environments. Most of state of the art approaches designed to tackle this problem monitor the loss of predictive models. However, this approach falls short in many real-world scenarios, where the true labels are not readily available to compute the loss. In this context, there is increasing attention to approaches that perform concept drift detection in an unsupervised manner, i.e., without access to the true labels. We propose a novel approach to unsupervised concept drift detection based on a student-teacher learning paradigm.…
Intel Corp.（英特尔公司）；Seoul National University（首尔国立大学）
While many real-world data streams imply that they change frequently in a nonstationary way, most of deep learning methods optimize neural networks on training data, and this leads to severe performance degradation when dataset shift happens. However, it is less possible to annotate or inspect newly streamed data by humans, and thus it is desired to measure model drift at inference time in an unsupervised manner. In this paper, we propose a novel method of model drift estimation by exploiting statistics of batch normalization layer on unlabeled test data. To remedy possible sampling error of s…
Wrocław University of Science and Technology（弗罗茨瓦夫科技大学）
stream-learn is a Python package compatible with scikit-learn and developed for the drifting and imbalanced data stream analysis. Its main component is a stream generator, which allows to produce a synthetic data stream that may incorporate each of the three main concept drift types (i.e. sudden, gradual and incremental drift) in their recurring or non-recurring versions. The package allows conducting experiments following established evaluation methodologies (i.e. Test-Then-Train and Prequential). In addition, estimators adapted for data stream classification have been implemented, including …
An important component of unsupervised learning by instance-based discrimination is a memory bank for storing a feature representation for each training sample in the dataset. In this paper, we introduce 3 improvements to the vanilla memory bank-based formulation which brings massive accuracy gains: (a) Large mini-batch: we pull multiple augmentations for each sample within the same batch and show that this leads to better models and enhanced memory bank updates. (b) Consistency: we enforce the logits obtained by different augmentations of the same sample to be close without trying to enforce …
Courant Institute of Mathematical Sciences（柯朗数学科学研究所）；Google Research（谷歌研究院）
We present a new analysis of the problem of learning with drifting distributions in the batch setting using the notion of discrepancy. We prove learning bounds based on the Rademacher complexity of the hypothesis set and the discrepancy of distributions both for a drifting PAC scenario and a tracking scenario. Our bounds are always tighter and in some cases substantially improve upon previous ones based on the $L_1$ distance. We also present a generalization of the standard on-line to batch conversion to the drifting scenario in terms of the discrepancy and arbitrary convex combinations of hyp…
Classifiers deployed in the real world operate in a dynamic environment, where the data distribution can change over time. These changes, referred to as concept drift, can cause the predictive performance of the classifier to drop over time, thereby making it obsolete. To be of any real use, these classifiers need to detect drifts and be able to adapt to them, over time. Detecting drifts has traditionally been approached as a supervised task, with labeled data constantly being used for validating the learned model. Although effective in detecting drifts, these techniques are impractical, as la…
Towards Computational Performance Engineering for Unsupervised Concept Drift Detection -- Complexities, Benchmarking, Performance Analysis
Center for Interdisciplinary Digital Sciences (CIDS), Technische Universität Dresden（德累斯顿工业大学跨学科数字科学中心（CIDS））；Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI) Dresden/Leipzig（德累斯顿/莱可堡可扩展数据分析与人工智能中心（ScaDS.AI））；Chair of Computer Graphics and Visualization (CGV), Technische Universität Dresden（德累斯顿工业大学计算机图形与可视化讲座）；Center for Information Services and High Performance Computing (ZIH), Technische Universität Dresden（德累斯顿工业大学信息服务与高性能计算中心（ZIH））
University of Cyprus（塞浦路斯大学）；Bielefeld University（比勒费尔德大学）
The notion of concept drift refers to the phenomenon that the data generating distribution changes over time; as a consequence machine learning models may become inaccurate and need adjustment. In this paper we consider the problem of detecting those change points in unsupervised learning. Many unsupervised approaches rely on the discrepancy between the sample distributions of two time windows. This procedure is noisy for small windows, hence prone to induce false positives and not able to deal with more than one drift event in a window. In this paper we rely on structural properties of drift …
From drift to adaptation to the failed ml model: Transfer Learning in Industrial MLOps
University College London（伦敦大学学院）；The Alan Turing Institute（艾伦·图灵研究所）；Univeristy of Engineering and Technology（工程与技术大学）；Sahiwal Coal Fired Power Plant（萨希瓦尔燃煤发电厂）
RIKEN Center for Advanced Intelligence Project (RIKEN AIP)（理化学研究所先进智能项目中心）；Advanced Telecommunications Research Institute International (ATR)（国际电气通信基础技术研究所）
Electroencephalography (EEG) provides access to neuronal dynamics non-invasively with millisecond resolution, rendering it a viable method in neuroscience and healthcare. However, its utility is limited as current EEG technology does not generalize well across domains (i.e., sessions and subjects) without expensive supervised re-calibration. Contemporary methods cast this transfer learning (TL) problem as a multi-source/-target unsupervised domain adaptation (UDA) problem and address it with deep learning or shallow, Riemannian geometry aware alignment methods. Both directions have, so far, fa…
Tensor decompositions are used in various data mining applications from social network to medical applications and are extremely useful in discovering latent structures or concepts in the data. Many real-world applications are dynamic in nature and so are their data. To deal with this dynamic nature of data, there exist a variety of online tensor decomposition algorithms. A central assumption in all those algorithms is that the number of latent concepts remains fixed throughout the entire stream. However, this need not be the case. Every incoming batch in the stream may have a different number…
We present K-Means Batch Bayesian Optimization (KMBBO), a novel batch sampling algorithm for Bayesian Optimization (BO). KMBBO uses unsupervised learning to efficiently estimate peaks of the model acquisition function. We show in empirical experiments that our method outperforms the current state-of-the-art batch allocation algorithms on a variety of test problems including tuning of algorithm hyper-parameters and a challenging drug discovery problem. In order to accommodate the real-world problem of high dimensional data, we propose a modification to KMBBO by combining it with compressed sens…
Unsupervised Online Detection of Pipe Blockages and Leakages in Water Distribution Networks
KIOS Research and Innovation Center of Excellence, University of Cyprus（希腊塞浦路斯大学KIOS研究中心）；Department of Electrical and Computer Engineering, University of Cyprus（塞浦路斯大学电气与计算机工程系）
Many real-world applications adopt multi-label data streams as the need for algorithms to deal with rapidly changing data increases. Changes in data distribution, also known as concept drift, cause the existing classification models to rapidly lose their effectiveness. To assist the classifiers, we propose a novel algorithm called Label Dependency Drift Detector (LD3), an implicit (unsupervised) concept drift detector using label dependencies within the data for multi-label data streams. Our study exploits the dynamic temporal dependencies between labels using a label influence ranking method,…
Currently the amount of data produced worldwide is increasing beyond measure, thus a high volume of unsupervised data must be processed continuously. One of the main unsupervised data analysis is clustering. In streaming data scenarios, the data is composed by an increasing sequence of batches of samples where the concept drift phenomenon may happen. In this paper, we formally define the Streaming $K$-means(S$K$M) problem, which implies a restart of the error function when a concept drift occurs. We propose a surrogate error function that does not rely on concept drift detection. We proof that…
University of Waikato（怀卡托大学）；Télécom ParisTech（巴黎高等电信学院）；Institut Polytechnique de Paris（巴黎理工学院）
Boosting is an ensemble method that combines base models in a sequential manner to achieve high predictive accuracy. A popular learning algorithm based on this ensemble method is eXtreme Gradient Boosting (XGB). We present an adaptation of XGB for classification of evolving data streams. In this setting, new data arrives over time and the relationship between the class and the features may change in the process, thus exhibiting concept drift. The proposed method creates new members of the ensemble from mini-batches of data as new data becomes available. The maximum ensemble size is fixed, but …
Mila；Université de Montréal（蒙特利尔大学）；Imperial College London（帝国理工学院）；Microsoft Research（微软研究院）
Unsupervised domain transfer is the task of transferring or translating samples from a source distribution to a different target distribution. Current solutions unsupervised domain transfer often operate on data on which the modes of the distribution are well-matched, for instance have the same frequencies of classes between source and target distributions. However, these models do not perform well when the modes are not well-matched, as would be the case when samples are drawn independently from two different, but related, domains. This mode imbalance is problematic as generative adversarial …
Johns Hopkins University（约翰斯·霍普金斯大学）；Robert Bosch LLC Research and Technology Center North America（罗伯特·博世有限责任公司北美研究与技术中心）
Common statistical prediction models often require and assume stationarity in the data. However, in many practical applications, changes in the relationship of the response and predictor variables are regularly observed over time, resulting in the deterioration of the predictive performance of these models. This paper presents Linear Four Rates (LFR), a framework for detecting these concept drifts and subsequently identifying the data points that belong to the new concept (for relearning the model). Unlike conventional concept drift detection approaches, LFR can be applied to both batch and st…
When monitoring machine learning systems, two-sample tests of homogeneity form the foundation upon which existing approaches to drift detection build. They are used to test for evidence that the distribution underlying recent deployment data differs from that underlying the historical reference data. Often, however, various factors such as time-induced correlation mean that batches of recent deployment data are not expected to form an i.i.d. sample from the historical data distribution. Instead we may wish to test for differences in the distributions conditional on \textit{context} that is per…
Lifelong Learning (LL) refers to the ability to continually learn and solve new problems with incremental available information over time while retaining previous knowledge. Much attention has been given lately to Supervised Lifelong Learning (SLL) with a stream of labelled data. In contrast, we focus on resolving challenges in Unsupervised Lifelong Learning (ULL) with streaming unlabelled data when the data distribution and the unknown class labels evolve over time. Bayesian framework is natural to incorporate past knowledge and sequentially update the belief with new data. We develop a fully…
This article studies how to detect and explain concept drift. Human activity recognition is used as a case study together with a online batch learning situation where the quality of the labels used in the model updating process starts to decrease. Drift detection is based on identifying a set of features having the largest relevance difference between the drifting model and a model that is known to be accurate and monitoring how the relevance of these features changes over time. As a main result of this article, it is shown that feature relevance analysis cannot only be used to detect the conc…
The challenge of describing model drift is an open question in unsupervised learning. It can be difficult to evaluate at what point an unsupervised model has deviated beyond what would be expected from a different sample from the same population. This is particularly true for models without a probabilistic interpretation. One such family of techniques, Topological Data Analysis, and the Mapper algorithm in particular, has found use in a variety of fields, but describing model drift for Mapper graphs is an understudied area as even existing techniques for measuring distances between related con…
