The online learning of deep neural networks is an interesting problem of machine learning because, for example, major IT companies want to manage the information of the massive data uploaded on the web daily, and this technology can contribute to the next generation of lifelong learning. We aim to train deep models from new data that consists of new classes, distributions, and tasks at minimal computational cost, which we call online deep learning. Unfortunately, deep neural network learning through classical online and incremental methods does not work well in both theory and practice. In this paper, we introduce dual memory architectures for online incremental deep learning. The proposed architecture consists of deep representation learners and fast learnable shallow kernel networks, both of which synergize to track the information of new data. During the training phase, we use various online, incremental ensemble, and transfer learning techniques in order to achieve lower error of the architecture. On the MNIST, CIFAR-10, and ImageNet image recognition tasks, the proposed dual memory architectures performs much better than the classical online and incremental ensemble algorithm, and their accuracies are similar to that of the batch learner.
Guise AI Inc.（Guise AI 公司）；Applied Computational Intelligence Laboratory, Missouri University of Science and Technology（密苏里科技大学应用计算智能实验室）
In streaming data applications incoming samples are processed and discarded, therefore, intelligent decision-making is crucial for the performance of lifelong learning systems. In addition, the order in which samples arrive may heavily affect the performance of online (and offline) incremental learners. The recently introduced incremental cluster validity indices (iCVIs) provide valuable aid in addressing such class of problems. Their primary use-case has been cluster quality monitoring; nonetheless, they have been very recently integrated in a streaming clustering method to assist the cluster…
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…
GIST（光州科学技术院）；NAVER AI Lab（NAVER人工智能实验室）；Upstage AI Research（Upstage人工智能研究院）；Yonsei University（延世大学）
Despite rapid advances in continual learning, a large body of research is devoted to improving performance in the existing setups. While a handful of work do propose new continual learning setups, they still lack practicality in certain aspects. For better practicality, we first propose a novel continual learning setup that is online, task-free, class-incremental, of blurry task boundaries and subject to inference queries at any moment. We additionally propose a new metric to better measure the performance of the continual learning methods subject to inference queries at any moment. To address…
MIST: Reliable Streaming Decision Trees for Online Class-Incremental Learning via McDiarmid Bound
Faculty of Information and Technology University of Science Vietnam National University Ho Chi Minh City（信息科技学院科学大学越南国家大学胡志明市）；Department of Computer Science University of Warwick（计算机科学系沃里克大学）
University of Toronto（多伦多大学）；LG AI Research（LG人工智能研究院）
As image-based deep learning becomes pervasive on every device, from cell phones to smart watches, there is a growing need to develop methods that continually learn from data while minimizing memory footprint and power consumption. While memory replay techniques have shown exceptional promise for this task of continual learning, the best method for selecting which buffered images to replay is still an open question. In this paper, we specifically focus on the online class-incremental setting where a model needs to learn new classes continually from an online data stream. To this end, we contri…
University of Toronto（多伦多大学）；LG AI Research（LG人工智能研究院）
Online class-incremental continual learning (CL) studies the problem of learning new classes continually from an online non-stationary data stream, intending to adapt to new data while mitigating catastrophic forgetting. While memory replay has shown promising results, the recency bias in online learning caused by the commonly used Softmax classifier remains an unsolved challenge. Although the Nearest-Class-Mean (NCM) classifier is significantly undervalued in the CL community, we demonstrate that it is a simple yet effective substitute for the Softmax classifier. It addresses the recency bias…
Tiny machine learning (TinyML) in IoT systems exploits MCUs as edge devices for data processing. However, traditional TinyML methods can only perform inference, limited to static environments or classes. Real case scenarios usually work in dynamic environments, thus drifting the context where the original neural model is no more suitable. For this reason, pre-trained models reduce accuracy and reliability during their lifetime because the data recorded slowly becomes obsolete or new patterns appear. Continual learning strategies maintain the model up to date, with runtime fine-tuning of the pa…
Trinity College Dublin（都柏林圣三一学院）；Intel Labs China（英特尔中国研究院）
Egocentric gestures are the most natural form of communication for humans to interact with wearable devices such as VR/AR helmets and glasses. A major issue in such scenarios for real-world applications is that may easily become necessary to add new gestures to the system e.g., a proper VR system should allow users to customize gestures incrementally. Traditional deep learning methods require storing all previous class samples in the system and training the model again from scratch by incorporating previous samples and new samples, which costs humongous memory and significantly increases compu…
Most work in graph-based recommender systems considers a {\em static} setting where all information about test nodes (i.e., users and items) is available upfront at training time. However, this static setting makes little sense for many real-world applications where data comes in continuously as a stream of new edges and nodes, and one has to update model predictions incrementally to reflect the latest state. To fully capitalize on the newly available data in the stream, recent graph-based recommendation models would need to be repeatedly retrained, which is infeasible in practice. In this pap…
The performance of classification algorithms with a massive and highly imbalanced data stream depends upon efficient balancing strategy. Some techniques of balancing strategy have been applied in the past with Batch data to resolve the class imbalance problem. This paper proposes a new incremental data balancing framework which can work with massive imbalanced data streams. In this paper, we choose Racing Algorithm as an automated data balancing technique which optimizes the balancing techniques. We applied Random Forest classification algorithm which can deal with the massive data stream. We …
Recent years have witnessed growing interests in online incremental learning. However, there are three major challenges in this area. The first major difficulty is concept drift, that is, the probability distribution in the streaming data would change as the data arrives. The second major difficulty is catastrophic forgetting, that is, forgetting what we have learned before when learning new knowledge. The last one we often ignore is the learning of the latent representation. Only good latent representation can improve the prediction accuracy of the model. Our research builds on this observati…
Incremental Outlier Detection Modelling Using Streaming Analytics in Finance & Health Care
National Institute of Technology Warangal（瓦朗加尔国家理工学院）；Jawaharlal Nehru Technological University – Gurajada Vizianagaram (JNTU-GV)（贾瓦哈拉尔·尼赫鲁技术大学古拉贾达维齐亚纳格拉姆分校）
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…
Real-world item recommenders commonly suffer from a persistent cold-start problem which is caused by dynamically changing users and items. In order to overcome the problem, several context-aware recommendation techniques have been recently proposed. In terms of both feasibility and performance, factorization machine (FM) is one of the most promising methods as generalization of the conventional matrix factorization techniques. However, since online algorithms are suitable for dynamic data, the static FMs are still inadequate. Thus, this paper proposes incremental FMs (iFMs), a general online f…
Nanjing University（南京大学）；University of New South Wales（新南威尔士大学）
A central capability of a long-lived reinforcement learning (RL) agent is to incrementally adapt its behavior as its environment changes, and to incrementally build upon previous experiences to facilitate future learning in real-world scenarios. In this paper, we propose LifeLong Incremental Reinforcement Learning (LLIRL), a new incremental algorithm for efficient lifelong adaptation to dynamic environments. We develop and maintain a library that contains an infinite mixture of parameterized environment models, which is equivalent to clustering environment parameters in a latent space. The pri…
Recognising human activities from streaming videos poses unique challenges to learning algorithms: predictive models need to be scalable, incrementally trainable, and must remain bounded in size even when the data stream is arbitrarily long. Furthermore, as parameter tuning is problematic in a streaming setting, suitable approaches should be parameterless, and make no assumptions on what class labels may occur in the stream. We present here an approach to the recognition of human actions from streaming data which meets all these requirements by: (1) incrementally learning a model which adaptiv…
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）
The ability to learn more and more concepts over time from incrementally arriving data is essential for the development of a life-long learning system. However, deep neural networks often suffer from forgetting previously learned concepts when continually learning new concepts, which is known as catastrophic forgetting problem. The main reason for catastrophic forgetting is that the past concept data is not available and neural weights are changed during incrementally learning new concepts. In this paper, we propose a pseudo-rehearsal based class incremental learning approach to make neural ne…
New York University（纽约大学）；Courant Institute of Mathematical Sciences（库朗数学科学研究所）
Database research can help machine learning performance in many ways. One way is to design better data structures. This paper combines the use of incremental computation and sequential and probabilistic filtering to enable "forgetful" tree-based learning algorithms to cope with concept drift data (i.e., data whose function from input to classification changes over time). The forgetful algorithms described in this paper achieve high time performance while maintaining high quality predictions on streaming data. Specifically, the algorithms are up to 24 times faster than state-of-the-art incremen…
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…
RiverText: A Python Library for Training and Evaluating Incremental Word Embeddings from Text Data Streams
Department of Computer Science, University of Chile（智利大学计算机科学系）；National Center for Artificial Intelligence (CENIA)（人工智能国家中心）；Millennium Institute for Foundational Research on Data (IMFD)（数据基础研究千年研究所）
ShanghaiTech University（上海科技大学）；Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences（中国科学院上海微系统与信息技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Shanghai Engineering Research Center of Intelligent Vision and Imaging（上海智能视觉成像工程技术研究中心）
Incremental learning of semantic segmentation has emerged as a promising strategy for visual scene interpretation in the open- world setting. However, it remains challenging to acquire novel classes in an online fashion for the segmentation task, mainly due to its continuously-evolving semantic label space, partial pixelwise ground-truth annotations, and constrained data availability. To ad- dress this, we propose an incremental learning strategy that can fast adapt deep segmentation models without catastrophic forgetting, using a streaming input data with pixel annotations on the novel classe…
AIGS: Adaptive Incremental Gating System for Online Representation Learning in Non-Stationary Data Streams
Xiamen University Malaysia（厦门大学马来西亚分校）；Multimedia University（多媒体大学）；School of Economics and Management, Xiamen University Malaysia（厦门大学马来西亚分校经济与管理学院）；School of Computing and Data Science, Xiamen University Malaysia（厦门大学马来西亚分校计算与数据科学学院）
The Hong Kong Polytechnic University（香港理工大学）；Huazhong University of Science and Technology（华中科技大学）；Beijing Institute of Technology（北京理工大学）；KAUST（阿卜杜拉国王科技大学）；SDAIA-KAUST AI Center（沙特数据与人工智能局-阿卜杜拉国王科技大学人工智能中心）
Online Class-Incremental (OCI) learning has sparked new approaches to expand the previously trained model knowledge from sequentially arriving data streams with new classes. Unfortunately, OCI learning can suffer from catastrophic forgetting (CF) as the decision boundaries for old classes can become inaccurate when perturbated by new ones. Existing literature have applied the data augmentation (DA) to alleviate the model forgetting, while the role of DA in OCI has not been well understood so far. In this paper, we theoretically show that augmented samples with lower correlation to the original…
Resilient Class-Incremental Learning: on the Interplay of Drifting, Unlabelled and Imbalanced Data Streams
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）
This study presents a rapid multiple incremental and decremental mechanism based on Weight-Error Curves (WECs) for support-vector analysis. Recursion-free computation is proposed for predicting the Lagrangian multipliers of new samples. This study examines Ridge Support Vector Models, subsequently devising a recursion-free function derived from WECs. With the proposed function, all the new Lagrangian multipliers can be computed at once without using any gradual step sizes. Moreover, such a function relaxes a constraint, where the increment of new multiple Lagrangian multipliers should be the s…
One of the most well-established applications of machine learning is in deciding what content to show website visitors. When observation data comes from high-velocity, user-generated data streams, machine learning methods perform a balancing act between model complexity, training time, and computational costs. Furthermore, when model freshness is critical, the training of models becomes time-constrained. Parallelized batch offline training, although horizontally scalable, is often not time-considerate or cost-effective. In this paper, we propose Lambda Learner, a new framework for training mod…
MindLab（思维实验室）；Universidad Nacional de Colombia（哥伦比亚国立大学）
Streaming anomaly detection refers to the problem of detecting anomalous data samples in streams of data. This problem poses challenges that classical and deep anomaly detection methods are not designed to cope with, such as conceptual drift and continuous learning. State-of-the-art flow anomaly detection methods rely on fixed memory using hash functions or nearest neighbors that may not be able to constrain high-frequency values as in a moving average or remove seamless outliers and cannot be trained in an end-to-end deep learning architecture. We present a new incremental anomaly detection m…
Southwest University（西南大学）；University of Chinese Academy of Sciences（中国科学院大学）
Online streaming feature selection (OSFS), which conducts feature selection in an online manner, plays an important role in dealing with high-dimensional data. In many real applications such as intelligent healthcare platform, streaming feature always has some missing data, which raises a crucial challenge in conducting OSFS, i.e., how to establish the uncertain relationship between sparse streaming features and labels. Unfortunately, existing OSFS algorithms never consider such uncertain relationship. To fill this gap, we in this paper propose an online sparse streaming feature selection with…
National University of Defense Technology（国防科技大学）；Nanjing University（南京大学）
In many real tasks the features are evolving, with some features being vanished and some other features augmented. For example, in environment monitoring some sensors expired whereas some new ones deployed; in mobile game recommendation some games dropped whereas some new ones added. Learning with such incremental and decremental features is crucial but rarely studied, particularly when the data coming like a stream and thus it is infeasible to keep the whole data for optimization. In this paper, we study this challenging problem and present the OPID approach. Our approach attempts to compress…
Generalized Incremental Learning under Concept Drift across Evolving Data Streams
Australian Artificial Intelligence Institute (AAII), \ of Technology Sydney Sydney NSW Australia；Australian Artificial Intelligence Institute (AAII), \ of Technology Sydney
University of Science and Culture（科学与文化大学）；Khorasan Institute of Higher Education（呼罗珊高等教育学院）
Unobtrusive and smart recognition of human activities using smartphones inertial sensors is an interesting topic in the field of artificial intelligence acquired tremendous popularity among researchers, especially in recent years. A considerable challenge that needs more attention is the real-time detection of physical activities, since for many real-world applications such as health monitoring and elderly care, it is required to recognize users' activities immediately to prevent severe damages to individuals' wellness. In this paper, we propose a human activity recognition (HAR) approach for …
Artificial Intelligence Laboratory, Jožef Stefan Institute（约瑟夫·斯特凡研究所人工智能实验室）
Despite growing interest in data stream mining the most successful incremental learners, such as VFDT, still use periodic recomputation to update attribute information gains and Gini indices. This note provides simple incremental formulas and algorithms for computing entropy and Gini index from time-changing data streams.
Community detection is an important research topic in graph analytics that has a wide range of applications. A variety of static community detection algorithms and quality metrics were developed in the past few years. However, most real-world graphs are not static and often change over time. In the case of streaming data, communities in the associated graph need to be updated either continuously or whenever new data streams are added to the graph, which poses a much greater challenge in devising good community detection algorithms for maintaining dynamic graphs over streaming data. In this pap…
Recent work studies the supervised online continual learning setting where a learner receives a stream of data whose class distribution changes over time. Distinct from other continual learning settings the learner is presented new samples only once and must distinguish between all seen classes. A number of successful methods in this setting focus on storing and replaying a subset of samples alongside incoming data in a computationally efficient manner. One recent proposal ER-AML achieved strong performance in this setting by applying an asymmetric loss based on contrastive learning to the inc…
Evaluating the Efficacy of Instance Incremental vs. Batch Learning in Delayed Label Environments: An Empirical Study on Tabular Data Streaming for Fraud Detection
Sorbonne Paris Nord University（巴黎北大学）；Paris-Saclay University（巴黎萨克雷大学）；Groupe BPCE（BPCE集团）
IIT Kanpur（印度理工学院坎普尔分校）；Duke University（杜克大学）；Verisk Analytics（威斯科分析公司）；University of Bath（巴斯大学）
A wide variety of methods have been developed to enable lifelong learning in conventional deep neural networks. However, to succeed, these methods require a `batch' of samples to be available and visited multiple times during training. While this works well in a static setting, these methods continue to suffer in a more realistic situation where data arrives in \emph{online streaming manner}. We empirically demonstrate that the performance of current approaches degrades if the input is obtained as a stream of data with the following restrictions: $(i)$ each instance comes one at a time and can…
University of Southern California（南加州大学）；Disney Research（迪士尼研究院）
Spoken Language Understanding (SLU) typically comprises of an automatic speech recognition (ASR) followed by a natural language understanding (NLU) module. The two modules process signals in a blocking sequential fashion, i.e., the NLU often has to wait for the ASR to finish processing on an utterance basis, potentially leading to high latencies that render the spoken interaction less natural. In this paper, we propose recurrent neural network (RNN) based incremental processing towards the SLU task of intent detection. The proposed methodology offers lower latencies than a typical SLU system, …
