The paper optimizes querying schemes for crowdsourced classification using XOR queries.
problem Optimizing querying schemes for crowdsourced classification.
method Modeling crowdsourced labeling/classification as source coding problem, leveraging connections to channel coding.
result Provides querying schemes with almost optimal number of queries, each involving a constant number of labels.
Improves model classification accuracy in black-box settings.
problem Difficulty in inferring model properties due to limited query access.
method Introduces discriminative factorization to distinguish high-quality queries.
result Probability of chance-level classification decreases exponentially with query budget.
Study examines how uncertainty visualization affects analyst trust in automated classification systems.
problem The impact of uncertainty on analyst trust in automated classification systems.
method Empirical study evaluating different active learning query policies and visualizations.
result Query policy significantly influences analyst trust in automated classification systems.
Efficiently classifies binary labels with XOR queries, even under noisy conditions.
problem Binary classification with unknown labels using XOR queries.
method Effective query type and an efficient inference algorithm for noisy conditions.
result Achieves information-theoretic limit on optimal number of queries.
Improved private sample complexity for answering classification queries.
problem Designing an algorithm to accurately answer classification queries while maintaining differential privacy.
method Formally studied in agnostic PAC model, derived new upper bound on private sample complexity.
result Improved private sample complexity bound for answering classification queries.
Unified query framework for active metric learning and classification.
problem Combining representation learning and task-specific goals in machine learning.
method Adaptive selection of nearest neighbor queries using information theoretic criterion.
result Actively selected nearest neighbor queries outperform recent methods in deep metric learning and classification.
A new algorithm fools deep neural networks with few queries.
problem Adversarial examples can mislead deep neural networks into incorrect classifications.
method qFool: a decision-based attack algorithm that reduces query count.
result qFool generates adversarial examples with fewer queries than previous methods.
Improved object classification using neural networks with known and unknown features.
problem Improving classification accuracy for objects described by both known and unknown features.
method Modernized Informational Neurobayesian Approach with consideration of unknown features.
result The method completely solved the problem of misclassification for queries with combining known and unknown features.
Improves node classification in graphs with active learning.
problem Difficult or expensive labeling in node classification tasks.
method Graph cognizant logistic regression and preemptive query generation.
result Significant improvement over state-of-the-art approaches.
New algorithms reduce overfitting in multiclass classification.
problem Excessive reuse of test datasets in machine learning leads to overfitting, especially in multiclass classification.
method Developed computationally efficient algorithms to reduce overfitting bias in multi-class classification.
result Achieved overfitting bias of Θ(√(k/(mn)), k/n), matching known upper bounds.
Survey on AL strategies for cost-effective annotation in classification.
problem Real-world AL challenges due to human annotators' limitations.
method Categorizes 60 real-world AL strategies considering multiple annotators, query types, and cost schemes.
result General real-world AL strategy introduced for categorization of 60 strategies.
Paper proposes a new pipeline for few-shot classification using forget-update module and channel vector sequence.
problem Few-shot classification with limited support samples.
method Channel vector sequence construction module and forget-update module.
result Pipeline achieves state-of-the-art results on various datasets.
Bayesian optimisation method targets graph classification models against adversarial attacks.
problem Adversarial attacks on graph classification models, especially for graph-level tasks.
method Bayesian optimisation-based attack method for graph classification models.
result Effectiveness and flexibility of the proposed method validated on various graph classification tasks.
Deep Neural Networks, and specifically fully-connected convolutional neural networks are achieving remarkable results across a wide variety of domains. They have been trained to achieve state-of-the-art performance when applied to problems such as speech recognition, image classification, natural language processing an…
New algorithms learn from comparisons to classify data robustly to noise.
problem Learning robust classifiers from noisy data efficiently.
method Introducing comparison queries to active learning, providing noise-tolerant classifiers.
result First time and query efficient algorithms for robust learning under bounded noise.
InfoTuple efficiently selects larger tuple queries for ranking multiple objects, improving efficiency and consistency.
problem Efficiently selecting and ranking multiple objects for similarity learning.
method Adaptive selection method using mutual information maximization.
result InfoTuple outperforms state-of-the-art methods on synthetic and human response datasets.
AdversarialPSO uses fewer queries to create high-success-rate adversarial examples.
problem Creating imperceptible adversarial examples with high success rates in black-box settings.
method AdversarialPSO, a black-box attack using Particle Swarm Optimization.
result Achieved high success rates (99.6% on CIFAR-10, 96.3% on MNIST, 82.0% on Imagenet) with fewer queries.
User-specific KWS system learns new keywords on-device.
problem Out-of-vocabulary problem in traditional KWS systems.
method Query-by-example enrollment and testing, using phonetic posteriors and FST.
result Promising performance on two keywords, preserving simplicity.
Bayesian framework for online consensus prediction from expert feedback.
problem Online classification with expert consensus prediction, cost-effective.
method General Bayesian framework for dynamic expert consensus estimation.
result Demonstrated superior performance on large-scale crowdsourced datasets.
Crowdsourcing has become widely used in supervised scenarios where training sets are scarce and difficult to obtain. Most crowdsourcing models in the literature assume labelers can provide answers to full questions. In classification contexts, full questions require a labeler to discern among all possible classes. Unfo…
Although interactive learning puts the user into the loop, the learner remains mostly a black box for the user. Understanding the reasons behind queries and predictions is important when assessing how the learner works and, in turn, trust. Consequently, we propose the novel framework of explanatory interactive learning…
Paper studies how incomplete data affects machine learning, proposing 'Certain Predictions' for NN classifiers.
problem Impact of incomplete and inconsistent data on machine learning applications.
method Extends Certain Answers concept to machine learning, introduces 'Certain Predictions' for NN classifiers.
result Developed efficient solutions for CP queries in NN classifiers, improving classification accuracy.
Study reduces human labeling in LLM-based classification systems.
problem Minimizing human intervention in training LLM-based classification systems.
method Active learning framework with Conservative Hull-based Classifier (CHC), Center-based Classifier (CC), and Generalized Hull-based Classifier (GHC).
result CHC achieves O(logdT) regret and is minimax optimal for d=1. GHC bridges the gap between different regimes. This paper introduces a novel, generic active learning method for one-class classification. Active learning methods play an important role to reduce the efforts of manual labeling in the field of machine learning. Although many active learning approaches have been proposed during the last years, most of them are restri…
Gradient flow on softmax attention minimizes nuclear norm of weight matrices.
problem Classification with separate key and query weight matrices.
method Gradient flow on exponential loss, separability assumption, reparameterization, approximate KKT conditions.
result Gradient flow implicitly minimizes nuclear norm of weight matrices, contrasting with Frobenius norm minimization.
Develops robust few-shot learning models resistant to adversarial attacks.
problem Adversarial vulnerability in few-shot learning models.
method Adversarial Querying (AQ) algorithm for robust meta-learners.
result Achieves superior robust performance on few-shot image classification tasks.
Study shows SQ hardness for multiclass linear classification with random noise.
problem Complexity of multiclass linear classification with random noise.
method Proves super-polynomial SQ lower bounds for MLC with RCN.
result Super-polynomial SQ lower bounds for MLC with RCN.
DAL improves active learning for neural networks with large batch sizes.
problem Efficiently choosing examples to label for neural networks with large batch sizes.
method DAL treats active learning as a binary classification task to make labeled and unlabeled sets indistinguishable.
result DAL performs on par with state-of-the-art methods in medium and large query batch sizes.
Given a binary prediction problem, which performance metric should the classifier optimize? We address this question by formalizing the problem of Metric Elicitation. The goal of metric elicitation is to discover the performance metric of a practitioner, which reflects her innate rewards (costs) for correct (incorrect)…
Proposes an offline active learning method for graphs.
problem Active learning on graphs where labeling is expensive.
method Two-stage biased sampling strategy considering informativeness and representativeness.
result Establishes a theoretical relationship between generalization error and number of nodes selected.
Proposes LRR and LRLR for improving stock prediction accuracy.
problem Improving stock prediction accuracy through nonparametric classification.
method Local radial regression and logistic regression variant.
result LRLR outperforms LPoR and MS-k-NN in real-world stock datasets. A method for classifying points with minimal queries using Hermite polynomials.
problem Classifying points from an unknown probability measure with minimal label queries.
method Convex combination of conditional probabilities, Hermite polynomial kernel for hierarchical support estimation.
result The method achieves high F-score for classification in hyper-spectral images and MNIST. Study adversarial perturbations in classification, analyzing learning and certification.
problem Formal study of classification under adversarial perturbations from both learner and third-party perspectives.
method PAC-type semi-supervised learning framework, black-box certification under limited query budget, adversary analysis.
result Existence of a polynomial query complexity adversary implies the existence of a sample efficient robust learner.
Meta-learning framework improves model performance on few-shot classification tasks.
problem Improving model performance on few-shot classification tasks.
method Empirical Bayes formulation with synthetic gradients for transductive meta-learning.
result Meta-learning framework outperforms previous state-of-the-art methods on benchmarks.
Transformers can be hijacked by context, but deeper models are more robust.
problem Robustness of Transformers against context hijacking for linear classification.
method Developed a theoretical analysis on the robustness of linear transformers, considering model depth, training context lengths, and number of hijacking context tokens.
result Deeper transformers are more robust to context hijacking.
ALPINE predicts links in networks by querying the most informative pairs.
problem Predicting links in partially observed networks efficiently.
method Active learning using network embedding.
result ALPINE achieves significant link prediction accuracy with fewer queries.
Paper proposes MS-k-NN for improved convergence rate in k-NN classification.
problem Improving convergence rate of k-NN classification methods.
method Proposes MS-k-NN that extrapolates unweighted k-NN estimators to k=0.
result MS-k-NN achieves improved convergence rate under certain conditions.
DiPriMe forests use private medians to create balanced tree splits for privacy-protected data.
problem Privacy concerns in training random forests due to multiple data queries.
method Proposes DiPriMe forests, which use a private median to generate balanced splits, ensuring differential privacy.
result DiPriMe forests achieve high utility while maintaining differential privacy, as shown both theoretically and empirically.
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 poi…
A review of nearest neighbour classifiers, focusing on similarity measures and computational efficiency.
problem Improving the performance of nearest neighbour classifiers.
method Explains mechanisms for assessing similarity (distance), identifying nearest neighbours, and reducing data dimensionality.
result Added new sections on time-series similarity measures, retrieval speed-up, and intrinsic dimensionality.
Framework for few-shot relation classification with minimal training data.
problem Few-shot relation classification with limited training data.
method Meta-learning framework that combines instance and support knowledge.
result Framework outperforms state-of-the-art results and achieves competitive performance with large training data.
Adaptive Misinformation defends against model stealing attacks by sending incorrect predictions for OOD queries.
problem Model stealing attacks clone target models using black-box query access and a surrogate dataset.
method Selective sending of incorrect predictions for Out-Of-Distribution (OOD) queries to degrade attacker's clone model accuracy.
result Our defense reduces attacker's clone model accuracy by up to 40% while maintaining benign user accuracy under 0.5%.
VACA models graph data for causal inference without hidden confounders.
problem Causal inference in observational data with hidden confounders.
method Variational graph autoencoders for structural causal models.
result Accurately approximates interventional and counterfactual distributions.
We present very efficient active learning algorithms for link classification in signed networks. Our algorithms are motivated by a stochastic model in which edge labels are obtained through perturbations of a initial sign assignment consistent with a two-clustering of the nodes. We provide a theoretical analysis within…
Why are classifiers in high dimension vulnerable to "adversarial" perturbations? We show that it is likely not due to information theoretic limitations, but rather it could be due to computational constraints. First we prove that, for a broad set of classification tasks, the mere existence of a robust classifier implie…
Proposes a new model to generate informative samples for image classification without querying an oracle.
problem Expensive and difficult labeling of data for machine learning models.
method Integrates active learning with a conditional GAN to generate samples with high uncertainty for a specific label.
result Generated samples improve image classification performance without querying an oracle.
Paper proposes ZO-NGD for more efficient black-box attacks.
problem Vulnerability of state-of-the-art DNNs to adversarial attacks.
method Zeroth-order natural gradient descent (ZO-NGD) for black-box attacks.
result ZO-NGD achieves significantly lower model query complexities.
Study shows a tradeoff between sample complexity and computational efficiency for learning halfspaces with random noise.
problem PAC learning γ-margin halfspaces with Random Classification Noise.
method Established an information-computation tradeoff and provided a simple efficient algorithm with sample complexity O(1/(γ^2 ε^2)). Also, proved lower bounds for SQ algorithms and low-degree polynomial tests.
result Inherent gap between sample complexity and computational efficiency for learning halfspaces with random noise.