State-of-the-art, high capacity deep neural networks not only require large amounts of labelled training data, they are also highly susceptible to label errors in this data, typically resulting in large efforts and costs and therefore limiting the applicability of deep learning. To alleviate this issue, we propose a novel meta training and labelling scheme that is able to use inexpensive unlabelled data by taking advantage of the generalization power of deep neural networks. We show experimentally that by solely relying on one network architecture and our proposed scheme of iterative training and prediction steps, both label quality and resulting model accuracy can be improved significantly. Our method achieves state-of-the-art results, while being architecture agnostic and therefore broadly applicable. Compared to other methods dealing with erroneous labels, our approach does neither require another network to be trained, nor does it necessarily need an additional, highly accurate reference label set. Instead of removing samples from a labelled set, our technique uses additional sensor data without the need for manual labelling. Furthermore, our approach can be used for semi-supervised learning.
Johns Hopkins University（约翰斯·霍普金斯大学）；IBM Thomas J. Watson Research Center（IBM托马斯·J·沃森研究中心）
We propose a novel confidence scoring mechanism for deep neural networks based on a two-model paradigm involving a base model and a meta-model. The confidence score is learned by the meta-model observing the base model succeeding/failing at its task. As features to the meta-model, we investigate linear classifier probes inserted between the various layers of the base model. Our experiments demonstrate that this approach outperforms various baselines in a filtering task, i.e., task of rejecting samples with low confidence. Experimental results are presented using CIFAR-10 and CIFAR-100 dataset …
Univ. Lille（里尔大学）；CNRS（法国国家科学研究中心）；Centrale Lille（里尔中央理工学院）；IMT Nord Europe（欧洲北部高等矿业电信学院）；Institut Mines-Télécom（法国矿业电信学院）；Université Bretagne Sud（南布列塔尼大学）
The particle filter (PF) is a powerful inference tool widely used to estimate the filtering distribution in non-linear and/or non-Gaussian problems. To overcome the curse of dimensionality of PF, the block PF (BPF) inserts a blocking step to partition the state space into several subspaces or blocks of smaller dimension so that the correction and resampling steps can be performed independently on each subspace. Using blocks of small size reduces the variance of the filtering distribution estimate, but in turn the correlation between blocks is broken and a bias is introduced. When the dependenc…
Sejong University（世宗大学）；University of Cambridge（剑桥大学）；UCLA（加州大学洛杉矶分校）；University of Virginia（弗吉尼亚大学）；Yonsei University（延世大学）；The Alan Turing Institute（艾伦·图灵研究所）
Subgroup analysis of treatment effects plays an important role in applications from medicine to public policy to recommender systems. It allows physicians (for example) to identify groups of patients for whom a given drug or treatment is likely to be effective and groups of patients for which it is not. Most of the current methods of subgroup analysis begin with a particular algorithm for estimating individualized treatment effects (ITE) and identify subgroups by maximizing the difference across subgroups of the average treatment effect in each subgroup. These approaches have several weaknesse…
Lausanne Institute of Technology (EPFL)（洛桑理工学院（EPFL））；Universitat de València（瓦伦西亚大学）
In this paper, we study the applicability of active learning in operative scenarios: more particularly, we consider the well-known contradiction between the active learning heuristics, which rank the pixels according to their uncertainty, and the user's confidence in labeling, which is related to both the homogeneity of the pixel context and user's knowledge of the scene. We propose a filtering scheme based on a classifier that learns the confidence of the user in labeling, thus minimizing the queries where the user would not be able to provide a class for the pixel. The capacity of a model to…
Filtering instances and rejecting predictions to obtain reliable models in healthcare
Instituto de Computação（计算研究所）；Universidade Estadual de Campinas（Campinas州立大学）；Department of Informatics（信息学院）；King’s College London（伦敦国王学院）；Núcleo de Telessaúde（远程医疗中心）；Universidade Federal do Rio Grande do Sul（鲁汶联邦大学）；Escola Paulista de Medicina（巴西圣保罗医学学院）；Universidade Federal de São Paulo（圣保罗联邦大学）；Divisão de Ciência da Computação（计算机科学部）；Instituto Tecnológico de Aeronáutica（航空技术研究所）
International Institute of Information Technology Bangalore（班加罗尔国际信息技术研究所）
Standard metrics of performance of classifiers, such as accuracy and sensitivity, do not reveal the trust or confidence in the predicted labels of data. While other metrics such as the computed probability of a label or the signed distance from a hyperplane can act as a trust measure, these are subjected to heuristic thresholds. This paper presents a convex optimization-based supervised classifier that sequentially partitions a dataset into several ellipsoids, where each ellipsoid contains nearly all points of the same label. By stating classification rules based on this partitioning, Bayes' f…
Tsinghua University（清华大学）；University of Cambridge（剑桥大学）
It is often remarked that neural networks fail to increase their uncertainty when predicting on data far from the training distribution. Yet naively using softmax confidence as a proxy for uncertainty achieves modest success in tasks exclusively testing for this, e.g., out-of-distribution (OOD) detection. This paper investigates this contradiction, identifying two implicit biases that do encourage softmax confidence to correlate with epistemic uncertainty: 1) Approximately optimal decision boundary structure, and 2) Filtering effects of deep networks. It describes why low-dimensional intuition…
Mobile devices can offload deep neural network (DNN)-based inference to the cloud, overcoming local hardware and energy limitations. However, offloading adds communication delay, thus increasing the overall inference time, and hence it should be used only when needed. An approach to address this problem consists of the use of adaptive model partitioning based on early-exit DNNs. Accordingly, the inference starts at the mobile device, and an intermediate layer estimates the accuracy: If the estimated accuracy is sufficient, the device takes the inference decision; Otherwise, the remaining layer…
Robust Federated Learning with Confidence-Weighted Filtering and GAN-Based Completion under Noisy and Incomplete Data
Computer Engineering Department, İstanbul Commerce University（伊斯坦布尔商业大学计算机工程系）；Turkcell Teknoloji（Turkcell技术公司）；Grid Communications and Security Group, Electrification and Energy Infrastructures Division, Oak Ridge National Laboratory（橡树岭国家实验室电网安全与能源基础设施部门）
针对联邦学习中的噪声标签、类别缺失与不均衡问题，提出结合自适应噪声清洗、条件 GAN 合成补全和鲁棒训练的隐私保护框架，并在 MNIST 与 Fashion-MNIST 上验证其性能提升。
Neural networks (NNs) are now routinely implemented on systems that must operate in uncertain environments, but the tools for formally analyzing how this uncertainty propagates to NN outputs are not yet commonplace. Computing tight bounds on NN output sets (given an input set) provides a measure of confidence associated with the NN decisions and is essential to deploy NNs on safety-critical systems. Recent works approximate the propagation of sets through nonlinear activations or partition the uncertainty set to provide a guaranteed outer bound on the set of possible NN outputs. However, the b…
In machine learning area, as the number of labeled input samples becomes very large, it is very difficult to build a classification model because of input data set is not fit in a memory in training phase of the algorithm, therefore, it is necessary to utilize data partitioning to handle overall data set. Bagging and boosting based data partitioning methods have been broadly used in data mining and pattern recognition area. Both of these methods have shown a great possibility for improving classification model performance. This study is concerned with the analysis of data set partitioning with…
Item-item collaborative filtering (CF) models are a well known and studied family of recommender systems, however current literature does not provide any theoretical explanation of the conditions under which item-based recommendations will succeed or fail. We investigate the existence of an ideal item-based CF method able to make perfect recommendations. This CF model is formalized as an eigenvalue problem, where estimated ratings are equivalent to the true (unknown) ratings multiplied by a user-specific eigenvalue of the similarity matrix. Preliminary experiments show that the magnitude of th…
Cyclica（赛克利卡公司）；University of Toronto（多伦多大学）；Princess Margaret Cancer Centre（玛格丽特公主癌症中心）；University Health Network（大学健康网络）；Vector Institute（向量研究所）
Performance of neural network models relies on the availability of large datasets with minimal levels of uncertainty. Transfer Learning (TL) models have been proposed to resolve the issue of small dataset size by letting the model train on a bigger, task-related reference dataset and then fine-tune on a smaller, task-specific dataset. In this work, we apply a transfer learning approach to improve predictive power in noisy data systems with large variable confidence datasets. We propose a deep neural network method called Filtered Transfer Learning (FTL) that defines multiple tiers of data conf…
In this paper, we consider the problem of providing robustness to adversarial communication in multi-agent systems. Specifically, we propose a solution towards robust cooperation, which enables the multi-agent system to maintain high performance in the presence of anonymous non-cooperative agents that communicate faulty, misleading or manipulative information. In pursuit of this goal, we propose a communication architecture based on Graph Neural Networks (GNNs), which is amenable to a novel Gaussian Process (GP)-based probabilistic model characterizing the mutual information between the simult…
The Biorobotics Institute（生物机器人研究所）；Scuola Superiore Sant’Anna（圣安娜高等学校）
Despite the recent developments that allowed neural networks to achieve impressive performance on a variety of applications, these models are intrinsically affected by the problem of overgeneralization, due to their partitioning of the full input space into the fixed set of target classes used during training. Thus it is possible for novel inputs belonging to categories unknown during training or even completely unrecognizable to humans to fool the system into classifying them as one of the known classes, even with a high degree of confidence. Solving this problem may help improve the security…
Google LLC（谷歌有限责任公司）；University of Washington（华盛顿大学）
We trained a keyword spotting model using federated learning on real user devices and observed significant improvements when the model was deployed for inference on phones. To compensate for data domains that are missing from on-device training caches, we employed joint federated-centralized training. And to learn in the absence of curated labels on-device, we formulated a confidence filtering strategy based on user-feedback signals for federated distillation. These techniques created models that significantly improved quality metrics in offline evaluations and user-experience metrics in live …
Physical event detection has long been the domain of static event processors operating on numeric sensor data. This works well for large scale strong-signal events such as hurricanes, and important classes of events such as earthquakes. However, for a variety of domains there is insufficient sensor coverage, e.g., landslides, wildfires, and flooding. Social networks have provided massive volume of data from billions of users, but data from these generic social sensors contain much more noise than physical sensors. One of the most difficult challenges presented by social sensors is \textit{conc…
Delft University of Technology（代尔夫特理工大学）；Katholieke Universiteit Leuven（鲁汶大学）
Least squares support vector machines are a commonly used supervised learning method for nonlinear regression and classification. They can be implemented in either their primal or dual form. The latter requires solving a linear system, which can be advantageous as an explicit mapping of the data to a possibly infinite-dimensional feature space is avoided. However, for large-scale applications, current low-rank approximation methods can perform inadequately. For example, current methods are probabilistic due to their sampling procedures, and/or suffer from a poor trade-off between the ranks and…
Vienna University of Technology（维也纳工业大学）；Information Technology University（信息技术大学）
Deep neural networks (DNN)-based machine learning (ML) algorithms have recently emerged as the leading ML paradigm particularly for the task of classification due to their superior capability of learning efficiently from large datasets. The discovery of a number of well-known attacks such as dataset poisoning, adversarial examples, and network manipulation (through the addition of malicious nodes) has, however, put the spotlight squarely on the lack of security in DNN-based ML systems. In particular, malicious actors can use these well-known attacks to cause random/targeted misclassification, …
Mitigating Label Bias in Machine Learning: Fairness through Confident Learning
Hangzhou Dianzi University（杭州电子科技大学）；University of Technology Sydney（悉尼科技大学）；Huazhong University of Science and Technology（华中科技大学）；Renmin University of China（中国人民大学）
Trust-Aware Predictive Emissions Monitoring for Gas Turbine Fleets with Limited Labelled Data
School of Natural and Computing Sciences University of Aberdeen（自然与计算科学学院 布拉德福德大学）；School of Computing Sciences University of East Anglia（计算科学学院 东安格利亚大学）；Siemens Energy Industrial Turbomachinery Ltd.（西门子能源工业涡轮机有限公司）；Department of Physics and Technology UiT The Arctic University of Norway（物理与技术系 UiT 北极大学）
