We provide a rigorous definition of the visual cause of a behavior that is broadly applicable to the visually driven behavior in humans, animals, neurons, robots and other perceiving systems. Our framework generalizes standard accounts of causal learning to settings in which the causal variables need to be constructed from micro-variables. We prove the Causal Coarsening Theorem, which allows us to gain causal knowledge from observational data with minimal experimental effort. The theorem provides a connection to standard inference techniques in machine learning that identify features of an image that correlate with, but may not cause, the target behavior. Finally, we propose an active learning scheme to learn a manipulator function that performs optimal manipulations on the image to automatically identify the visual cause of a target behavior. We illustrate our inference and learning algorithms in experiments based on both synthetic and real data.
An active learner is given a class of models, a large set of unlabeled examples, and the ability to interactively query labels of a subset of these examples; the goal of the learner is to learn a model in the class that fits the data well. Previous theoretical work has rigorously characterized label complexity of active learning, but most of this work has focused on the PAC or the agnostic PAC model. In this paper, we shift our attention to a more general setting -- maximum likelihood estimation. Provided certain conditions hold on the model class, we provide a two-stage active learning algorithm for this problem. The conditions we require are fairly general, and cover the widely popular class of Generalized Linear Models, which in turn, include models for binary and multi-class classification, regression, and conditional random fields. We provide an upper bound on the label requirement of our algorithm, and a lower bound that matches it up to lower order terms. Our analysis shows that unlike binary classification in the realizable case, just a single extra round of interaction is sufficient to achieve near-optimal performance in maximum likelihood estimation. On the empirical side, the recent work in ~\cite{Zhang12} and~\cite{Zhang14} (on active linear and logistic regression) shows the promise of this approach.
This paper investigates the problem of active learning for binary label prediction on a graph. We introduce a simple and label-efficient algorithm called S2 for this task. At each step, S2 selects the vertex to be labeled based on the structure of the graph and all previously gathered labels. Specifically, S2 queries for the label of the vertex that bisects the *shortest shortest* path between any pair of oppositely labeled vertices. We present a theoretical estimate of the number of queries S2 needs in terms of a novel parametrization of the complexity of binary functions on graphs. We also present experimental results demonstrating the performance of S2 on both real and synthetic data. While other graph-based active learning algorithms have shown promise in practice, our algorithm is the first with both good performance and theoretical guarantees. Finally, we demonstrate the implications of the S2 algorithm to the theory of nonparametric active learning. In particular, we show that S2 achieves near minimax optimal excess risk for an important class of nonparametric classification problems.
A private learner is an algorithm that given a sample of labeled individual examples outputs a generalizing hypothesis while preserving the privacy of each individual. In 2008, Kasiviswanathan et al. (FOCS 2008) gave a generic construction of private learners, in which the sample complexity is (generally) higher than what is needed for non-private learners. This gap in the sample complexity was then further studied in several followup papers, showing that (at least in some cases) this gap is unavoidable. Moreover, those papers considered ways to overcome the gap, by relaxing either the privacy or the learning guarantees of the learner. We suggest an alternative approach, inspired by the (non-private) models of semi-supervised learning and active-learning, where the focus is on the sample complexity of labeled examples whereas unlabeled examples are of a significantly lower cost. We consider private semi-supervised learners that operate on a random sample, where only a (hopefully small) portion of this sample is labeled. The learners have no control over which of the sample elements are labeled. Our main result is that the labeled sample complexity of private learners is characterized by the VC dimension. We present two generic constructions of private semi-supervised learners. The first construction is of learners where the labeled sample complexity is proportional to the VC dimension of the concept class, however, the unlabeled sample complexity of the algorithm is as big as the representation length of domain elements. Our second construction presents a new technique for decreasing the labeled sample complexity of a given private learner, while roughly maintaining its unlabeled sample complexity. In addition, we show that in some settings the labeled sample complexity does not depend on the privacy parameters of the learner.
In this paper, we study the problem of estimating uniformly well the mean values of several distributions given a finite budget of samples. If the variance of the distributions were known, one could design an optimal sampling strategy by collecting a number of independent samples per distribution that is proportional to their variance. However, in the more realistic case where the distributions are not known in advance, one needs to design adaptive sampling strategies in order to select which distribution to sample from according to the previously observed samples. We describe two strategies based on pulling the distributions a number of times that is proportional to a high-probability upper-confidence-bound on their variance (built from previous observed samples) and report a finite-sample performance analysis on the excess estimation error compared to the optimal allocation. We show that the performance of these allocation strategies depends not only on the variances but also on the full shape of the distributions.
Active learning aims to obtain a classifier of high accuracy by using fewer label requests in comparison to passive learning by selecting effective queries. Many active learning methods have been developed in the past two decades, which sample queries based on informativeness or representativeness of unlabeled data points. In this work, we explore a novel querying criterion based on statistical leverage scores. The statistical leverage scores of a row in a matrix are the squared row-norms of the matrix containing its (top) left singular vectors and is a measure of influence of the row on the matrix. Leverage scores have been used for detecting high influential points in regression diagnostics and have been recently shown to be useful for data analysis and randomized low-rank matrix approximation algorithms. We explore how sampling data instances with high statistical leverage scores perform in active learning. Our empirical comparison on several binary classification datasets indicate that querying high leverage points is an effective strategy.
We propose a learning setting in which unlabeled data is free, and the cost of a label depends on its value, which is not known in advance. We study binary classification in an extreme case, where the algorithm only pays for negative labels. Our motivation are applications such as fraud detection, in which investigating an honest transaction should be avoided if possible. We term the setting auditing, and consider the auditing complexity of an algorithm: the number of negative labels the algorithm requires in order to learn a hypothesis with low relative error. We design auditing algorithms for simple hypothesis classes (thresholds and rectangles), and show that with these algorithms, the auditing complexity can be significantly lower than the active label complexity. We also discuss a general competitive approach for auditing and possible modifications to the framework.
Task selection (picking an appropriate labeling task) and worker selection (assigning the labeling task to a suitable worker) are two major challenges in task assignment for crowdsourcing. Recently, worker selection has been successfully addressed by the bandit-based task assignment (BBTA) method, while task selection has not been thoroughly investigated yet. In this paper, we experimentally compare several task selection strategies borrowed from active learning literature, and show that the least confidence strategy significantly improves the performance of task assignment in crowdsourcing.
Multi-label active learning is a hot topic in reducing the label cost by optimally choosing the most valuable instance to query its label from an oracle. In this paper, we consider the poolbased multi-label active learning under the crowdsourcing setting, where during the active query process, instead of resorting to a high cost oracle for the ground-truth, multiple low cost imperfect annotators with various expertise are available for labeling. To deal with this problem, we propose the MAC (Multi-label Active learning from Crowds) approach which incorporate the local influence of label correlations to build a probabilistic model over the multi-label classifier and annotators. Based on this model, we can estimate the labels for instances as well as the expertise of each annotator. Then we propose the instance selection and annotator selection criteria that consider the uncertainty/diversity of instances and the reliability of annotators, such that the most reliable annotator will be queried for the most valuable instances. Experimental results demonstrate the effectiveness of the proposed approach.
Cutting-plane methods are well-studied localization(and optimization) algorithms. We show that they provide a natural framework to perform machinelearning ---and not just to solve optimization problems posed by machinelearning--- in addition to their intended optimization use. In particular, theyallow one to learn sparse classifiers and provide good compression schemes.Moreover, we show that very little effort is required to turn them intoeffective active learning methods. This last property provides a generic way todesign a whole family of active learning algorithms from existing passivemethods. We present numerical simulations testifying of the relevance ofcutting-plane methods for passive and active learning tasks.
We propose an Active Learning approach to training a segmentation classifier that exploits geometric priors to streamline the annotation process in 3D image volumes. To this end, we use these priors not only to select voxels most in need of annotation but to guarantee that they lie on 2D planar patch, which makes it much easier to annotate than if they were randomly distributed in the volume. A simplified version of this approach is effective in natural 2D images. We evaluated our approach on Electron Microscopy and Magnetic Resonance image volumes, as well as on natural images. Comparing our approach against several accepted baselines demonstrates a marked performance increase.
Precise geocoding and time normalization for text requires that location and time phrases be identified. Many state-of-the-art geoparsers and temporal parsers suffer from low recall. Categories commonly missed by parsers are: nouns used in a non- spatiotemporal sense, adjectival and adverbial phrases, prepositional phrases, and numerical phrases. We collected and annotated data set by querying commercial web searches API with such spatiotemporal expressions as were missed by state-of-the- art parsers. Due to the high cost of sentence annotation, active learning was used to label training data, and a new strategy was designed to better select training examples to reduce labeling cost. For the learning algorithm, we applied an average perceptron trained Featurized Hidden Markov Model (FHMM). Five FHMM instances were used to create an ensemble, with the output phrase selected by voting. Our ensemble model was tested on a range of sequential labeling tasks, and has shown competitive performance. Our contributions include (1) an new dataset annotated with named entities and expanded spatiotemporal expressions; (2) a comparison of inference algorithms for ensemble models showing the superior accuracy of Belief Propagation over Viterbi Decoding; (3) a new example re-weighting method for active ensemble learning that 'memorizes' the latest examples trained; (4) a spatiotemporal parser that jointly recognizes expanded spatiotemporal expressions as well as named entities.
Applications that learn from opinionated documents, like tweets or product reviews, face two challenges. First, the opinionated documents constitute an evolving stream, where both the author's attitude and the vocabulary itself may change. Second, labels of documents are scarce and labels of words are unreliable, because the sentiment of a word depends on the (unknown) context in the author's mind. Most of the research on mining over opinionated streams focuses on the first aspect of the problem, whereas for the second a continuous supply of labels from the stream is assumed. Such an assumption though is utopian as the stream is infinite and the labeling cost is prohibitive. To this end, we investigate the potential of active stream learning algorithms that ask for labels on demand. Our proposed ACOSTREAM 1 approach works with limited labels: it uses an initial seed of labeled documents, occasionally requests additional labels for documents from the human expert and incrementally adapts to the underlying stream while exploiting the available labeled documents. In its core, ACOSTREAM consists of a MNB classifier coupled with "sampling" strategies for requesting class labels for new unlabeled documents. In the experiments, we evaluate the classifier performance over time by varying: (a) the class distribution of the opinionated stream, while assuming that the set of the words in the vocabulary is fixed but their polarities may change with the class distribution; and (b) the number of unknown words arriving at each moment, while the class polarity may also change. Our results show that active learning on a stream of opinionated documents, delivers good performance while requiring a small selection of labels
The prospect of neural reconstruction from Electron Microscopy (EM) images has been elucidated by the automatic segmentation algorithms. Although segmentation algorithms eliminate the necessity of tracing the neurons by hand, significant manual effort is still essential for correcting the mistakes they make. A considerable amount of human labor is also required for annotating groundtruth volumes for training the classifiers of a segmentation framework. It is critically important to diminish the dependence on human interaction in the overall reconstruction system. This study proposes a novel classifier training algorithm for EM segmentation aimed to reduce the amount of manual effort demanded by the groundtruth annotation and error refinement tasks. Instead of using an exhaustive pixel level groundtruth, an active learning algorithm is proposed for sparse labeling of pixel and boundaries of superpixels. Because over-segmentation errors are in general more tolerable and easier to correct than the under-segmentation errors, our algorithm is designed to prioritize minimization of false-merges over false-split mistakes. Our experiments on both 2D and 3D data suggest that the proposed method yields segmentation outputs that are more amenable to neural reconstruction than those of existing methods.
How can we reuse existing knowledge, in the form of available datasets, when solving a new and apparently unrelated target task from a set of unlabeled data? In this work we make a first contribution to answer this question in the context of image classification. We frame this quest as an active learning problem and use zero-shot classifiers to guide the learning process by linking the new task to the existing classifiers. By revisiting the dual formulation of adaptive SVM, we reveal two basic conditions to choose greedily only the most relevant samples to be annotated. On this basis we propose an effective active learning algorithm which learns the best possible target classification model with minimum human labeling effort. Extensive experiments on two challenging datasets show the value of our approach compared to the state-of-the-art active learning methodologies, as well as its potential to reuse past datasets with minimal effort for future tasks.
The task of determining labels of all network nodes based on the knowledge about network structure and labels of some training subset of nodes is called the within-network classification. It may happen that none of the labels of the nodes is known and additionally there is no information about number of classes to which nodes can be assigned. In such a case a subset of nodes has to be selected for initial label acquisition. The question that arises is: "labels of which nodes should be collected and used for learning in order to provide the best classification accuracy for the whole network?". Active learning and inference is a practical framework to study this problem. A set of methods for active learning and inference for within network classification is proposed and validated. The utility score calculation for each node based on network structure is the first step in the process. The scores enable to rank the nodes. Based on the ranking, a set of nodes, for which the labels are acquired, is selected (e.g. by taking top or bottom N from the ranking). The new measure-neighbour methods proposed in the paper suggest not obtaining labels of nodes from the ranking but rather acquiring labels of their neighbours. The paper examines 29 distinct formulations of utility score and selection methods reporting their impact on the results of two collective classification algorithms: Iterative Classification Algorithm and Loopy Belief Propagation. We advocate that the accuracy of presented methods depends on the structural properties of the examined network. We claim that measure-neighbour methods will work better than the regular methods for networks with higher clustering coefficient and worse than regular methods for networks with low clustering coefficient. According to our hypothesis, based on clustering coefficient we are able to recommend appropriate active learning and inference method.
Assistive solutions for a better shopping experience can improve the quality of life of people, in particular also of visually impaired shoppers. We present a system that visually recognizes the fine-grained product classes of items on a shopping list, in shelves images taken with a smartphone in a grocery store. Our system consists of three components: (a) We automatically recognize useful text on product packaging, e.g., product name and brand, and build a mapping of words to product classes based on the large-scale GroceryProducts dataset. When the user populates the shopping list, we automatically infer the product class of each entered word. (b) We perform fine-grained product class recognition when the user is facing a shelf. We discover discriminative patches on product packaging to differentiate between visually similar product classes and to increase the robustness against continuous changes in product design. (c) We continuously improve the recognition accuracy through active learning. Our experiments show the robustness of the proposed method against cross-domain challenges, and the scalability to an increasing number of products with minimal re-training.
An active learner is given a hypothesis class, a large set of unlabeled examples and the ability to interactively query labels to an oracle of a subset of these examples; the goal of the learner is to learn a hypothesis in the class that fits the data well by making as few label queries as possible. This work addresses active learning with labels obtained from strong and weak labelers, where in addition to the standard active learning setting, we have an extra weak labeler which may occasionally provide incorrect labels. An example is learning to classify medical images where either expensive labels may be obtained from a physician (oracle or strong labeler), or cheaper but occasionally incorrect labels may be obtained from a medical resident (weak labeler). Our goal is to learn a classifier with low error on data labeled by the oracle, while using the weak labeler to reduce the number of label queries made to this labeler. We provide an active learning algorithm for this setting, establish its statistical consistency, and analyze its label complexity to characterize when it can provide label savings over using the strong labeler alone.
Learning a model of perceptual similarity from a collection of objects is a fundamental task in machine learning underlying numerous applications. A common way to learn such a model is from relative comparisons in the form of triplets: responses to queries of the form "Is object a more similar to b than it is to c?". If no consideration is made in the determination of which queries to ask, existing similarity learning methods can require a prohibitively large number of responses. In this work, we consider the problem of actively learning from triplets -finding which queries are most useful for learning. Different from previous active triplet learning approaches, we incorporate auxiliary information into our similarity model and introduce an active learning scheme to find queries that are informative for quickly learning both the relevant aspects of auxiliary data and the directly-learned similarity components. Compared to prior approaches, we show that we can learn just as effectively with much fewer queries. For evaluation, we introduce a new dataset of exhaustive triplet comparisons obtained from humans and demonstrate improved performance for different types of auxiliary information.
We consider the problem of Bayesian parameter estimation for deep neural networks, which is important in problem settings where we may have little data, and/ or where we need accurate posterior predictive densities, e.g., for applications involving bandits or active learning. One simple approach to this is to use online Monte Carlo methods, such as SGLD (stochastic gradient Langevin dynamics). Unfortunately, such a method needs to store many copies of the parameters (which wastes memory), and needs to make predictions using many versions of the model (which wastes time). We describe a method for "distilling" a Monte Carlo approximation to the posterior predictive density into a more compact form, namely a single deep neural network. We compare to two very recent approaches to Bayesian neural networks, namely an approach based on expectation propagation [Hernandez-Lobato and Adams, 2015] and an approach based on variational Bayes [Blundell et al., 2015]. Our method performs better than both of these, is much simpler to implement, and uses less computation at test time.