Oral Presentation delivered at the 7th International Conference on Computers and Devices for Communication (CODEC) 2019. To appear in Lecture Notes in Networks and Systems (LNSS Springer)
The notion of incremental learning is to train an ANN algorithm in stages, as and when newer training data arrives. Incremental learning is becoming widespread in recent times with the advent of deep learning. Noise in the training data reduces the accuracy of the algorithm. In this paper, we make an empirical study of the effect of noise in the training phase. We numerically show that the accuracy of the algorithm is dependent more on the location of the error than the percentage of error. Using Perceptron, Feed Forward Neural Network and Radial Basis Function Neural Network, we show that for the same percentage of error, the accuracy of the algorithm significantly varies with the location of error. Furthermore, our results show that the dependence of the accuracy with the location of error is independent of the algorithm. However, the slope of the degradation curve decreases with more sophisticated algorithms
Institute of Artificial Intelligence, Zhejiang University（浙江大学人工智能研究所）
Automatically learning features, especially robust features, has attracted much attention in the machine learning community. In this paper, we propose a new method to learn non-linear robust features by taking advantage of the data manifold structure. We first follow the commonly used trick of the trade, that is learning robust features with artificially corrupted data, which are training samples with manually injected noise. Following the idea of the auto-encoder, we first assume features should contain much information to well reconstruct the input from its corrupted copies. However, merely …
Georgia Institute of Technology（佐治亚理工学院）；KTH Royal Institute of Technology（瑞典皇家理工学院）
We consider incremental inference problems from aggregate data for collective dynamics. In particular, we address the problem of estimating the aggregate marginals of a Markov chain from noisy aggregate observations in an incremental (online) fashion. We propose a sliding window Sinkhorn belief propagation (SW-SBP) algorithm that utilizes a sliding window filter of the most recent noisy aggregate observations along with encoded information from discarded observations. Our algorithm is built upon the recently proposed multi-marginal optimal transport based SBP algorithm that leverages standard …
Incremental versions of batch algorithms are often desired, for increased time efficiency in the streaming data setting, or increased memory efficiency in general. In this paper we present a novel algorithm for incremental kernel PCA, based on rank one updates to the eigendecomposition of the kernel matrix, which is more computationally efficient than comparable existing algorithms. We extend our algorithm to incremental calculation of the Nyström approximation to the kernel matrix, the first such algorithm proposed. Incremental calculation of the Nyström approximation leads to further gains i…
University of Southern California（南加州大学）；Bosch Center for Artificial Intelligence（博世人工智能中心）
We study the problem of training machine learning models incrementally with batches of samples annotated with noisy oracles. We select each batch of samples that are important and also diverse via clustering and importance sampling. More importantly, we incorporate model uncertainty into the sampling probability to compensate for poor estimation of the importance scores when the training data is too small to build a meaningful model. Experiments on benchmark image classification datasets (MNIST, SVHN, CIFAR10, and EMNIST) show improvement over existing active learning strategies. We introduce …
In learning-to-learn the goal is to infer a learning algorithm that works well on a class of tasks sampled from an unknown meta distribution. In contrast to previous work on batch learning-to-learn, we consider a scenario where tasks are presented sequentially and the algorithm needs to adapt incrementally to improve its performance on future tasks. Key to this setting is for the algorithm to rapidly incorporate new observations into the model as they arrive, without keeping them in memory. We focus on the case where the underlying algorithm is ridge regression parameterized by a positive semi…
To alleviate human efforts from obtaining large-scale annotations, Semi-Supervised Relation Extraction methods aim to leverage unlabeled data in addition to learning from limited samples. Existing self-training methods suffer from the gradual drift problem, where noisy pseudo labels on unlabeled data are incorporated during training. To alleviate the noise in pseudo labels, we propose a method called MetaSRE, where a Relation Label Generation Network generates quality assessment on pseudo labels by (meta) learning from the successful and failed attempts on Relation Classification Network as an…
Object detection in streaming images is a major step in different detection-based applications, such as object tracking, action recognition, robot navigation, and visual surveillance applications. In mostcases, image quality is noisy and biased, and as a result, the data distributions are disturbed and imbalanced. Most object detection approaches, such as the faster region-based convolutional neural network (Faster RCNN), Single Shot Multibox Detector with 300x300 inputs (SSD300), and You Only Look Once version 2 (YOLOv2), rely on simple sampling without considering distortions and noise under…
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）
In the phase retrieval problem, an unknown vector is to be recovered given quadratic measurements. This problem has received considerable attention in recent times. In this paper, we present an algorithm to solve a nonconvex formulation of the phase retrieval problem, that we call $\textit{Incremental Truncated Wirtinger Flow}$. Given random Gaussian sensing vectors, we prove that it converges linearly to the solution, with an optimal sample complexity. We also provide stability guarantees of the algorithm under noisy measurements. Performance and comparisons with existing algorithms are illus…
Kyoto University（京都大学）；RIKEN Center for Artificial Intelligence Project (AIP)（理化学研究所人工智能项目中心）
We propose $β$-graph embedding for robustly learning feature vectors from data vectors and noisy link weights. A newly introduced empirical moment $β$-score reduces the influence of contamination and robustly measures the difference between the underlying correct expected weights of links and the specified generative model. The proposed method is computationally tractable; we employ a minibatch-based efficient stochastic algorithm and prove that this algorithm locally minimizes the empirical moment $β$-score. We conduct numerical experiments on synthetic and real-world datasets.
Given the ever-increasing complexity of adaptable software systems and their commonly hidden internal information (e.g., software runs in the public cloud), machine learning based performance modeling has gained momentum for evaluating, understanding and predicting software performance, which facilitates better informed self-adaptations. As performance data accumulates during the run of the software, updating the performance models becomes necessary. To this end, there are two conventional modeling methods: the retrained modeling that always discard the old model and retrain a new one using al…
This study presents an efficient incremental/decremental approach for big streams based on Kernel Ridge Regression (KRR), a frequently used data analysis in cloud centers. To avoid reanalyzing the whole dataset whenever sensors receive new training data, typical incremental KRR used a single-instance mechanism for updating an existing system. However, this inevitably increased redundant computational time, not to mention applicability to big streams. To this end, the proposed mechanism supports incremental/decremental processing for both single and multiple samples (i.e., batch processing). A …
Salk Institute for Biological Studies（索尔克生物研究所）；U.S. Department of the Interior（美国内政部）；Scripps Institution of Oceanography（斯克里普斯海洋研究所）；University of California San Diego（加州大学圣地亚哥分校）
Data-driven, model-free analytics are natural choices for discovery and forecasting of complex, nonlinear systems. Methods that operate in the system state-space require either an explicit multidimensional state-space, or, one approximated from available observations. Since observational data are frequently sampled with noise, it is possible that noise can corrupt the state-space representation degrading analytical performance. Here, we evaluate the synthesis of empirical mode decomposition with empirical dynamic modeling, which we term empirical mode modeling, to increase the information cont…
École Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）
Increasing concerns with privacy have stimulated interests in Session-based Recommendation (SR) using no personal data other than what is observed in the current browser session. Existing methods are evaluated in static settings which rarely occur in real-world applications. To better address the dynamic nature of SR tasks, we study an incremental SR scenario, where new items and preferences appear continuously. We show that existing neural recommenders can be used in incremental SR scenarios with small incremental updates to alleviate computation overhead and catastrophic forgetting. More imp…
Facebook AI Research（脸书人工智能研究院）；Inria（法国国家信息与自动化研究所）；DeepMind（深度思维）
We investigate the exploration of an unknown environment when no reward function is provided. Building on the incremental exploration setting introduced by Lim and Auer [1], we define the objective of learning the set of $ε$-optimal goal-conditioned policies attaining all states that are incrementally reachable within $L$ steps (in expectation) from a reference state $s_0$. In this paper, we introduce a novel model-based approach that interleaves discovering new states from $s_0$ and improving the accuracy of a model estimate that is used to compute goal-conditioned policies to reach newly dis…
School of Industrial and Systems Engineering at Georgia Tech（佐治亚理工学院工业与系统工程学院）
Numerous empirical evidences have corroborated the importance of noise in nonconvex optimization problems. The theory behind such empirical observations, however, is still largely unknown. This paper studies this fundamental problem through investigating the nonconvex rectangular matrix factorization problem, which has infinitely many global minima due to rotation and scaling invariance. Hence, gradient descent (GD) can converge to any optimum, depending on the initialization. In contrast, we show that a perturbed form of GD with an arbitrary initialization converges to a global optimum that i…
We propose using active learning based techniques to further improve the state-of-the-art semi-supervised learning MixMatch algorithm. We provide a thorough empirical evaluation of several active-learning and baseline methods, which successfully demonstrate a significant improvement on the benchmark CIFAR-10, CIFAR-100, and SVHN datasets (as much as 1.5% in absolute accuracy). We also provide an empirical analysis of the cost trade-off between incrementally gathering more labeled versus unlabeled data. This analysis can be used to measure the relative value of labeled/unlabeled data at differe…
IRIT（图卢兹计算机科学研究所）；Université de Toulouse（图卢兹大学）；CNRS（法国国家科学研究中心）
Minibatch decomposition methods for empirical risk minimization are commonly analysed in a stochastic approximation setting, also known as sampling with replacement. On the other hands modern implementations of such techniques are incremental: they rely on sampling without replacement, for which available analysis are much scarcer. We provide convergence guaranties for the latter variant by analysing a versatile incremental gradient scheme. For this scheme, we consider constant, decreasing or adaptive step sizes. In the smooth setting we obtain explicit complexity estimates in terms of epoch c…
INRIA Lille - Nord Europe（法国国家信息与自动化研究所里尔-北欧洲分所）；University of Puerto Rico - Rio Piedras（波多黎各大学里约彼德拉斯分校）
While the harmonic function solution performs well in many semi-supervised learning (SSL) tasks, it is known to scale poorly with the number of samples. Recent successful and scalable methods, such as the eigenfunction method focus on efficiently approximating the whole spectrum of the graph Laplacian constructed from the data. This is in contrast to various subsampling and quantization methods proposed in the past, which may fail in preserving the graph spectra. However, the impact of the approximation of the spectrum on the final generalization error is either unknown, or requires strong ass…
In this paper, we study the estimation performance of empirical $\ell_2$ risk minimization (ERM) in noisy (standard) phase retrieval (NPR) given by $y_k = |α_k^*x_0|^2+η_k$, or noisy generalized phase retrieval (NGPR) formulated as $y_k = x_0^*A_kx_0 + η_k$, where $x_0\in\mathbb{K}^d$ is the desired signal, $n$ is the sample size, $η= (η_1,...,η_n)^\top$ is the noise vector. We establish new error bounds under different noise patterns, and our proofs are valid for both $\mathbb{K}=\mathbb{R}$ and $\mathbb{K}=\mathbb{C}$. In NPR under arbitrary noise vector $η$, we derive a new error bound $O\b…
An Empirical Analysis of Forgetting in Pre-trained Models with Incremental Low-Rank Updates
Computer Vision Center, Spain（西班牙计算机视觉中心）；Department of Computer Science, Universitat Autònoma de Barcelona, Spain（西班牙巴塞罗那自治大学计算机科学系）；Department of Information Engineering, University of Florence, Italy（意大利佛罗伦萨大学信息工程系）
Institut LIST, CEA（法国原子能与替代能源委员会 LIST 研究所）；Université Paris-Saclay（巴黎萨克雷大学）
Federated learning enables different parties to collaboratively build a global model under the orchestration of a server while keeping the training data on clients' devices. However, performance is affected when clients have heterogeneous data. To cope with this problem, we assume that despite data heterogeneity, there are groups of clients who have similar data distributions that can be clustered. In previous approaches, in order to cluster clients the server requires clients to send their parameters simultaneously. However, this can be problematic in a context where there is a significant nu…
Class-incremental learning (CIL) learns a classification model with training data of different classes arising progressively. Existing CIL either suffers from serious accuracy loss due to catastrophic forgetting, or invades data privacy by revisiting used exemplars. Inspired by linear learning formulations, we propose an analytic class-incremental learning (ACIL) with absolute memorization of past knowledge while avoiding breaching of data privacy (i.e., without storing historical data). The absolute memorization is demonstrated in the sense that class-incremental learning using ACIL given pre…
National University of Defense Technology（国防科技大学）；University of Surrey（萨里大学）
High quality labeled datasets have allowed deep learning to achieve impressive results on many sound analysis tasks. Yet, it is labor-intensive to accurately annotate large amount of audio data, and the dataset may contain noisy labels in the practical settings. Meanwhile, the deep neural networks are susceptive to those incorrect labeled data because of their outstanding memorization ability. In this paper, we present a novel framework, named CrossFilter, to combat the noisy labels problem for audio tagging. Multiple representations (such as, Logmel and MFCC) are used as the input of our fram…
Istituto Italiano di Tecnologia（意大利技术研究院）；MIT（麻省理工学院）；Università degli Studi di Genova（热那亚大学）
We consider object recognition in the context of lifelong learning, where a robotic agent learns to discriminate between a growing number of object classes as it accumulates experience about the environment. We propose an incremental variant of the Regularized Least Squares for Classification (RLSC) algorithm, and exploit its structure to seamlessly add new classes to the learned model. The presented algorithm addresses the problem of having an unbalanced proportion of training examples per class, which occurs when new objects are presented to the system for the first time. We evaluate our alg…
Chinese Academy of Science（中国科学院）；Harbin Institute of Technology（哈尔滨工业大学）；Peng Cheng Laboratory（鹏城实验室）；Xi’an Jiaotong University（西安交通大学）；Jinan University（暨南大学）
Although data-free incremental learning methods are memory-friendly, accurately estimating and counteracting representation shifts is challenging in the absence of historical data. This paper addresses this thorny problem by proposing a novel incremental learning method inspired by human analogy capabilities. Specifically, we design an analogy-making mechanism to remap the new data into the old class by prompt tuning. It mimics the feature distribution of the target old class on the old model using only samples of new classes. The learnt prompts are further used to estimate and counteract the …
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…
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院（KAIST））
Inspired by Regularized Lottery Ticket Hypothesis (RLTH), which hypothesizes that there exist smooth (non-binary) subnetworks within a dense network that achieve the competitive performance of the dense network, we propose a few-shot class incremental learning (FSCIL) method referred to as \emph{Soft-SubNetworks (SoftNet)}. Our objective is to learn a sequence of sessions incrementally, where each session only includes a few training instances per class while preserving the knowledge of the previously learned ones. SoftNet jointly learns the model weights and adaptive non-binary soft masks at …
University of Notre Dame（圣母大学）；Amazon Inc.（亚马逊公司）；University of Michigan（密歇根大学）
Adversarial examples can easily degrade the classification performance in neural networks. Empirical methods for promoting robustness to such examples have been proposed, but often lack both analytical insights and formal guarantees. Recently, some robustness certificates have appeared in the literature based on system theoretic notions. This work proposes an incremental dissipativity-based robustness certificate for neural networks in the form of a linear matrix inequality for each layer. We also propose an equivalent spectral norm bound for this certificate which is scalable to neural networ…
The rawly collected training data often comes with separate noisy labels collected from multiple imperfect annotators (e.g., via crowdsourcing). A typical way of using these separate labels is to first aggregate them into one and apply standard training methods. The literature has also studied extensively on effective aggregation approaches. This paper revisits this choice and aims to provide an answer to the question of whether one should aggregate separate noisy labels into single ones or use them separately as given. We theoretically analyze the performance of both approaches under the empi…
We propose Mobile Audio Streaming Networks (MASnet) for efficient low-latency speech enhancement, which is particularly suitable for mobile devices and other applications where computational capacity is a limitation. MASnet processes linear-scale spectrograms, transforming successive noisy frames into complex-valued ratio masks which are then applied to the respective noisy frames. MASnet can operate in a low-latency incremental inference mode which matches the complexity of layer-by-layer batch mode. Compared to a similar fully-convolutional architecture, MASnet incorporates depthwise and poi…
University of Toronto（多伦多大学）；LG AI Research（LG人工智能研究院）
Online continual learning for image classification studies the problem of learning to classify images from an online stream of data and tasks, where tasks may include new classes (class incremental) or data nonstationarity (domain incremental). One of the key challenges of continual learning is to avoid catastrophic forgetting (CF), i.e., forgetting old tasks in the presence of more recent tasks. Over the past few years, many methods and tricks have been introduced to address this problem, but many have not been fairly and systematically compared under a variety of realistic and practical sett…
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…
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…
With growing credit card transaction volumes, the fraud percentages are also rising, including overhead costs for institutions to combat and compensate victims. The use of machine learning into the financial sector permits more effective protection against fraud and other economic crime. Suitably trained machine learning classifiers help proactive fraud detection, improving stakeholder trust and robustness against illicit transactions. However, the design of machine learning based fraud detection algorithms has been challenging and slow due the massively unbalanced nature of fraud data and the…
