How can we find a general way to choose the most suitable samples for training a classifier? Even with very limited prior information? Active learning, which can be regarded as an iterative optimization procedure, plays a key role to construct a refined training set to improve the classification performance in a variety of applications, such as text analysis, image recognition, social network modeling, etc. Although combining representativeness and informativeness of samples has been proven promising for active sampling, state-of-the-art methods perform well under certain data structures. Then can we find a way to fuse the two active sampling criteria without any assumption on data? This paper proposes a general active learning framework that effectively fuses the two criteria. Inspired by a two-sample discrepancy problem, triple measures are elaborately designed to guarantee that the query samples not only possess the representativeness of the unlabeled data but also reveal the diversity of the labeled data. Any appropriate similarity measure can be employed to construct the triple measures. Meanwhile, an uncertain measure is leveraged to generate the informativeness criterion, which can be carried out in different ways. Rooted in this framework, a practical active learning algorithm is proposed, which exploits a radial basis function together with the estimated probabilities to construct the triple measures and a modified Best-versus-Second-Best strategy to construct the uncertain measure, respectively. Experimental results on benchmark datasets demonstrate that our algorithm consistently achieves superior performance over the state-of-the-art active learning algorithms.
In this paper we describe a new method for detecting and counting a repeating object in an image. While the method relies on a fairly sophisticated deformable part model, unlike existing techniques it estimates the model parameters in an unsupervised fashion thus alleviating the need for a user-annotated training data and avoiding the associated specificity. This automatic fitting process is carried out by exploiting the recurrence of small image patches associated with the repeating object and analyzing their spatial correlation. The analysis allows us to reject outlier patches, recover the visual and shape parameters of the part model, and detect the object instances efficiently. In order to achieve a practical system which is able to cope with diverse images, we describe a simple and intuitive active-learning procedure that updates the object classification by querying the user on very few carefully chosen marginal classifications. Evaluation of the new method against the state-of-the-art techniques demonstrates its ability to achieve higher accuracy through a better user experience.
We study the problem of object detection from a novel perspective in which annotation budget constraints are taken into consideration, appropriately coined Budget Aware Object Detection (BAOD). When provided with a fixed budget, we propose a strategy for building a diverse and informative dataset that can be used to optimally train a robust detector. We investigate both optimization and learning-based methods to sample which images to annotate and what type of annotation (strongly or weakly supervised) to annotate them with. We adopt a hybrid supervised learning framework to train the object detector from both these types of annotation. We conduct a comprehensive empirical study showing that a handcrafted optimization method outperforms other selection techniques including random sampling, uncertainty sampling and active learning. By combining an optimal image/annotation selection scheme with hybrid supervised learning to solve the BAOD problem, we show that one can achieve the performance of a strongly supervised detector on PASCAL-VOC 2007 while saving 12.8% of its original annotation budget. Furthermore, when $100\%$ of the budget is used, it surpasses this performance by 2.0 mAP percentage points.
Machine learning can help personalized decision support by learning models to predict individual treatment effects (ITE). This work studies the reliability of prediction-based decision-making in a task of deciding which action $a$ to take for a target unit after observing its covariates $\tilde{x}$ and predicted outcomes $\hat{p}(\tilde{y} \mid \tilde{x}, a)$. An example case is personalized medicine and the decision of which treatment to give to a patient. A common problem when learning these models from observational data is imbalance, that is, difference in treated/control covariate distributions, which is known to increase the upper bound of the expected ITE estimation error. We propose to assess the decision-making reliability by estimating the ITE model's Type S error rate, which is the probability of the model inferring the sign of the treatment effect wrong. Furthermore, we use the estimated reliability as a criterion for active learning, in order to collect new (possibly expensive) observations, instead of making a forced choice based on unreliable predictions. We demonstrate the effectiveness of this decision-making aware active learning in two decision-making tasks: in simulated data with binary outcomes and in a medical dataset with synthetic and continuous treatment outcomes.
Recent years have witnessed the quick progress of the hyperspectral images (HSI) classification. Most of existing studies either heavily rely on the expensive label information using the supervised learning or can hardly exploit the discriminative information borrowed from related domains. To address this issues, in this paper we show a novel framework addressing HSI classification based on the domain adaptation (DA) with active learning (AL). The main idea of our method is to retrain the multi-kernel classifier by utilizing the available labeled samples from source domain, and adding minimum number of the most informative samples with active queries in the target domain. The proposed method adaptively combines multiple kernels, forming a DA classifier that minimizes the bias between the source and target domains. Further equipped with the nested actively updating process, it sequentially expands the training set and gradually converges to a satisfying level of classification performance. We study this active adaptation framework with the Margin Sampling (MS) strategy in the HSI classification task. Our experimental results on two popular HSI datasets demonstrate its effectiveness.
Activity recognition is a challenging problem with many practical applications. In addition to the visual features, recent approaches have benefited from the use of context, e.g., inter-relationships among the activities and objects. However, these approaches require data to be labeled, entirely available beforehand, and not designed to be updated continuously, which make them unsuitable for surveillance applications. In contrast, we propose a continuous-learning framework for context-aware activity recognition from unlabeled video, which has two distinct advantages over existing methods. First, it employs a novel active-learning technique that not only exploits the informativeness of the individual activities but also utilizes their contextual information during query selection; this leads to significant reduction in expensive manual annotation effort. Second, the learned models can be adapted online as more data is available. We formulate a conditional random field model that encodes the context and devise an information-theoretic approach that utilizes entropy and mutual information of the nodes to compute the set of most informative queries, which are labeled by a human. These labels are combined with graphical inference techniques for incremental updates. We provide a theoretical formulation of the active learning framework with an analytic solution. Experiments on six challenging datasets demonstrate that our framework achieves superior performance with significantly less manual labeling.
Characterizing the appearance of real-world surfaces is a fundamental problem in multidimensional reflectometry, computer vision and computer graphics. For many applications, appearance is sufficiently well characterized by the bidirectional reflectance distribution function (BRDF). We treat BRDF measurements as samples of points from high-dimensional non-linear non-convex manifolds. BRDF manifolds form an infinite-dimensional space, but typically the available measurements are very scarce for complicated problems such as BRDF estimation. Therefore, an efficient learning strategy is crucial when performing the measurements. In this paper, we build the foundation of a mathematical framework that allows to develop and apply new techniques within statistical design of experiments and generalized proactive learning, in order to establish more efficient sampling and measurement strategies for BRDF data manifolds.
Deep learning has recently attracted significant attention in the field of hyperspectral images (HSIs) classification. However, the construction of an efficient deep neural network (DNN) mostly relies on a large number of labeled samples being available. To address this problem, this paper proposes a unified deep network, combined with active transfer learning that can be well-trained for HSIs classification using only minimally labeled training data. More specifically, deep joint spectral-spatial feature is first extracted through hierarchical stacked sparse autoencoder (SSAE) networks. Active transfer learning is then exploited to transfer the pre-trained SSAE network and the limited training samples from the source domain to the target domain, where the SSAE network is subsequently fine-tuned using the limited labeled samples selected from both source and target domain by corresponding active learning strategies. The advantages of our proposed method are threefold: 1) the network can be effectively trained using only limited labeled samples with the help of novel active learning strategies; 2) the network is flexible and scalable enough to function across various transfer situations, including cross-dataset and intra-image; 3) the learned deep joint spectral-spatial feature representation is more generic and robust than many joint spectral-spatial feature representation. Extensive comparative evaluations demonstrate that our proposed method significantly outperforms many state-of-the-art approaches, including both traditional and deep network-based methods, on three popular datasets.
One type of machine learning, text classification, is now regularly applied in the legal matters involving voluminous document populations because it can reduce the time and expense associated with the review of those documents. One form of machine learning - Active Learning - has drawn attention from the legal community because it offers the potential to make the machine learning process even more effective. Active Learning, applied to legal documents, is considered a new technology in the legal domain and is continuously applied to all documents in a legal matter until an insignificant number of relevant documents are left for review. This implementation is slightly different than traditional implementations of Active Learning where the process stops once achieving acceptable model performance. The purpose of this paper is twofold: (i) to question whether Active Learning actually is a superior learning methodology and (ii) to highlight the ways that Active Learning can be most effectively applied to real legal industry data. Unlike other studies, our experiments were performed against large data sets taken from recent, real-world legal matters covering a variety of areas. We conclude that, although these experiments show the Active Learning strategy popularly used in legal document review can quickly identify informative training documents, it becomes less effective over time. In particular, our findings suggest this most popular form of Active Learning in the legal arena, where the highest-scoring documents are selected as training examples, is in fact not the most efficient approach in most instances. Ultimately, a different Active Learning strategy may be best suited to initiate the predictive modeling process but not to continue through the entire document review.
Selecting input variables or design points for statistical models has been of great interest in adaptive design and active learning. Motivated by two scientific examples, this paper presents a strategy of selecting the design points for a regression model when the underlying regression function is discontinuous. The first example we undertook was for the purpose of accelerating imaging speed in a high resolution material imaging; the second was use of sequential design for the purpose of mapping a chemical phase diagram. In both examples, the underlying regression functions have discontinuities, so many of the existing design optimization approaches cannot be applied because they mostly assume a continuous regression function. Although some existing adaptive design strategies developed from treed regression models can handle the discontinuities, the Bayesian approaches come with computationally expensive Markov Chain Monte Carlo techniques for posterior inferences and subsequent design point selections, which is not appropriate for the first motivating example that requires computation at least faster than the original imaging speed. In addition, the treed models are based on the domain partitioning that are inefficient when the discontinuities occurs over complex sub-domain boundaries. We propose a simple and effective adaptive design strategy for a regression analysis with discontinuities: some statistical properties with a fixed design will be presented first, and then these properties will be used to propose a new criterion of selecting the design points for the regression analysis. Sequential design with the new criterion will be presented with comprehensive simulated examples, and its application to the two motivating examples will be presented.
Network operators are generally aware of common attack vectors that they defend against. For most networks the vast majority of traffic is legitimate. However new attack vectors are continually designed and attempted by bad actors which bypass detection and go unnoticed due to low volume. One strategy for finding such activity is to look for anomalous behavior. Investigating anomalous behavior requires significant time and resources. Collecting a large number of labeled examples for training supervised models is both prohibitively expensive and subject to obsoletion as new attacks surface. A purely unsupervised methodology is ideal; however, research has shown that even a very small number of labeled examples can significantly improve the quality of anomaly detection. A methodology that minimizes the number of required labels while maximizing the quality of detection is desirable. False positives in this context result in wasted effort or blockage of legitimate traffic and false negatives translate to undetected attacks. We propose a general active learning framework and experiment with different choices of learners and sampling strategies.
We present work flows and a software module for machine learning model building in surface science and heterogeneous catalysis. This includes fingerprinting atomic structures from 3D structure and/or connectivity information, it includes descriptor selection methods and benchmarks, and it includes active learning frameworks for atomic structure optimization, acceleration of screening studies and for exploration of the structure space of nano particles, which are all atomic structure problems relevant for surface science and heterogeneous catalysis. Our overall goal is to provide a repository to ease machine learning model building for catalysis, to advance the models beyond the chemical intuition of the user and to increase autonomy for exploration of chemical space.
Active learning aims to develop label-efficient algorithms by sampling the most representative queries to be labeled by an oracle. We describe a pool-based semi-supervised active learning algorithm that implicitly learns this sampling mechanism in an adversarial manner. Unlike conventional active learning algorithms, our approach is task agnostic, i.e., it does not depend on the performance of the task for which we are trying to acquire labeled data. Our method learns a latent space using a variational autoencoder (VAE) and an adversarial network trained to discriminate between unlabeled and labeled data. The mini-max game between the VAE and the adversarial network is played such that while the VAE tries to trick the adversarial network into predicting that all data points are from the labeled pool, the adversarial network learns how to discriminate between dissimilarities in the latent space. We extensively evaluate our method on various image classification and semantic segmentation benchmark datasets and establish a new state of the art on $\text{CIFAR10/100}$, $\text{Caltech-256}$, $\text{ImageNet}$, $\text{Cityscapes}$, and $\text{BDD100K}$. Our results demonstrate that our adversarial approach learns an effective low dimensional latent space in large-scale settings and provides for a computationally efficient sampling method. Our code is available at https://github.com/sinhasam/vaal.
Active learning holds promise of significantly reducing data annotation costs while maintaining reasonable model performance. However, it requires sending data to annotators for labeling. This presents a possible privacy leak when the training set includes sensitive user data. In this paper, we describe an approach for carrying out privacy preserving active learning with quantifiable guarantees. We evaluate our approach by showing the tradeoff between privacy, utility and annotation budget on a binary classification task in a active learning setting.
This study uses a novel simulation framework to evaluate whether the time and effort necessary to achieve high recall using active learning is reduced by presenting the reviewer with isolated sentences, as opposed to full documents, for relevance feedback. Under the weak assumption that more time and effort is required to review an entire document than a single sentence, simulation results indicate that the use of isolated sentences for relevance feedback can yield comparable accuracy and higher efficiency, relative to the state-of-the-art Baseline Model Implementation (BMI) of the AutoTAR Continuous Active Learning ("CAL") method employed in the TREC 2015 and 2016 Total Recall Track.
Bayesian quadrature (BQ) is a sample-efficient probabilistic numerical method to solve integrals of expensive-to-evaluate black-box functions, yet so far,active BQ learning schemes focus merely on the integrand itself as information source, and do not allow for information transfer from cheaper, related functions. Here, we set the scene for active learning in BQ when multiple related information sources of variable cost (in input and source) are accessible. This setting arises for example when evaluating the integrand requires a complex simulation to be run that can be approximated by simulating at lower levels of sophistication and at lesser expense. We construct meaningful cost-sensitive multi-source acquisition rates as an extension to common utility functions from vanilla BQ (VBQ),and discuss pitfalls that arise from blindly generalizing. Furthermore, we show that the VBQ acquisition policy is a corner-case of all considered cost-sensitive acquisition schemes, which collapse onto one single de-generate policy in the case of one source and constant cost. In proof-of-concept experiments we scrutinize the behavior of our generalized acquisition functions. On an epidemiological model, we demonstrate that active multi-source BQ (AMS-BQ) allocates budget more efficiently than VBQ for learning the integral to a good accuracy.
Heart rate estimation from electrocardiogram signals is very important for the early detection of cardiovascular diseases. However, due to large individual differences and varying electrocardiogram signal quality, there does not exist a single reliable estimation algorithm that works well on all subjects. Every algorithm may break down on certain subjects, resulting in a significant estimation error. Ensemble regression, which aggregates the outputs of multiple base estimators for more reliable and stable estimates, can be used to remedy this problem. Moreover, active learning can be used to optimally select a few trials from a new subject to label, based on which a stacking ensemble regression model can be trained to aggregate the base estimators. This paper proposes four active stacking approaches, and demonstrates that they all significantly outperform three common unsupervised ensemble regression approaches, and a supervised stacking approach which randomly selects some trials to label. Remarkably, our active stacking approaches only need three or four labeled trials from each subject to achieve an average root mean squared estimation error below three beats per minute, making them very convenient for real-world applications. To our knowledge, this is the first research on active stacking, and its application to heart rate estimation.
The inverse statistical problem of finding direct interactions in complex networks is difficult. In the natural sciences, well-controlled perturbation experiments are widely used to probe the structure of complex networks. However, our understanding of how and why perturbations aid inference remains heuristic, and we lack automated procedures that determine network structure by combining inference and perturbation. Therefore, we propose a general mathematical framework to study inference with iteratively applied perturbations. Using the formulation of information geometry, our framework quantifies the difficulty of inference and the information gain from perturbations through the curvature of the underlying parameter manifold, measured by Fisher information. We apply the framework to the inference of spin network models and find that designed perturbations can reduce the sampling complexity by $10^6$-fold across a variety of network architectures. Physically, our framework reveals that perturbations boost inference by causing a network to explore previously inaccessible states. Optimal perturbations break spin-spin correlations within a network, increasing the information available for inference and thus reducing sampling complexity by orders of magnitude. Our active learning framework could be powerful in the analysis of complex networks as well as in the rational design of experiments.
Thermal preferences vary from person to person and may change over time. The main objective of this paper is to sequentially pose intelligent queries to occupants in order to optimally learn the indoor air temperature values which maximize their satisfaction. Our central hypothesis is that an occupant's preference relation over indoor air temperature can be described using a scalar function of these temperatures, which we call the "occupant's thermal utility function". Information about an occupant's preference over these temperatures is available to us through their response to thermal preference queries : "prefer warmer," "prefer cooler" and "satisfied" which we interpret as statements about the derivative of their utility function, i.e. the utility function is "increasing", "decreasing" and "constant" respectively. We model this hidden utility function using a Gaussian process prior with built-in unimodality constraint, i.e., the utility function has a unique maximum, and we train this model using Bayesian inference. This permits an expected improvement based selection of next preference query to pose to the occupant, which takes into account both exploration (sampling from areas of high uncertainty) and exploitation (sampling from areas which are likely to offer an improvement over current best observation). We use this framework to sequentially design experiments and illustrate its benefits by showing that it requires drastically fewer observations to learn the maximally preferred temperature values as compared to other methods. This framework is an important step towards the development of intelligent HVAC systems which would be able to respond to occupants' personalized thermal comfort needs. In order to encourage the use of our PE framework and ensure reproducibility in results, we publish an implementation of our work named GPPrefElicit as an open-source package in Python.
In this paper, we consider the problem of subsampling and reconstruction of signals that reside on the vertices of a product graph, such as sensor network time series, genomic signals, or product ratings in a social network. Specifically, we leverage the product structure of the underlying domain and sample nodes from the graph factors. The proposed scheme is particularly useful for processing signals on large-scale product graphs. The sampling sets are designed using a low-complexity greedy algorithm and can be proven to be near-optimal. To illustrate the developed theory, numerical experiments based on real datasets are provided for sampling 3D dynamic point clouds and for active learning in recommender systems.