Deep learning has achieved widespread success in medical image analysis, leading to an increasing demand for large-scale expert-annotated medical image datasets. Yet, the high cost of annotating medical images severely hampers the development of deep learning in this field. To reduce annotation costs, active learning aims to select the most informative samples for annotation and train high-performance models with as few labeled samples as possible. In this survey, we review the core methods of active learning, including the evaluation of informativeness and sampling strategy. For the first time, we provide a detailed summary of the integration of active learning with other label-efficient techniques, such as semi-supervised, self-supervised learning, and so on. We also summarize active learning works that are specifically tailored to medical image analysis. Additionally, we conduct a thorough comparative analysis of the performance of different AL methods in medical image analysis with experiments. In the end, we offer our perspectives on the future trends and challenges of active learning and its applications in medical image analysis.
Reinforcement Learning algorithms that learn from human feedback (RLHF) need to be efficient in terms of statistical complexity, computational complexity, and query complexity. In this work, we consider the RLHF setting where the feedback is given in the format of preferences over pairs of trajectories. In the linear MDP model, using randomization in algorithm design, we present an algorithm that is sample efficient (i.e., has near-optimal worst-case regret bounds) and has polynomial running time (i.e., computational complexity is polynomial with respect to relevant parameters). Our algorithm further minimizes the query complexity through a novel randomized active learning procedure. In particular, our algorithm demonstrates a near-optimal tradeoff between the regret bound and the query complexity. To extend the results to more general nonlinear function approximation, we design a model-based randomized algorithm inspired by the idea of Thompson sampling. Our algorithm minimizes Bayesian regret bound and query complexity, again achieving a near-optimal tradeoff between these two quantities. Computation-wise, similar to the prior Thompson sampling algorithms under the regular RL setting, the main computation primitives of our algorithm are Bayesian supervised learning oracles which have been heavily investigated on the empirical side when applying Thompson sampling algorithms to RL benchmark problems.
Label aggregation such as majority voting is commonly used to resolve annotator disagreement in dataset creation. However, this may disregard minority values and opinions. Recent studies indicate that learning from individual annotations outperforms learning from aggregated labels, though they require a considerable amount of annotation. Active learning, as an annotation cost-saving strategy, has not been fully explored in the context of learning from disagreement. We show that in the active learning setting, a multi-head model performs significantly better than a single-head model in terms of uncertainty estimation. By designing and evaluating acquisition functions with annotator-specific heads on two datasets, we show that group-level entropy works generally well on both datasets. Importantly, it achieves performance in terms of both prediction and uncertainty estimation comparable to full-scale training from disagreement, while saving up to 70% of the annotation budget.
Large-scale deployment of generative AI tools often depends on costly API calls to a Large Language Model (LLM) to fulfil user queries. To curtail the frequency of these calls, one can employ a smaller language model -- a student -- which is continuously trained on the responses of the LLM. This student gradually gains proficiency in independently handling an increasing number of user requests, a process we term neural caching. The crucial element in neural caching is a policy that decides which requests should be processed by the student alone and which should be redirected to the LLM, subsequently aiding the student's learning. In this study, we focus on classification tasks, and we consider a range of classic active learning-based selection criteria as the policy. Our experiments suggest that Margin Sampling and Query by Committee bring consistent benefits across tasks and budgets.
We consider the problem of active learning in the context of spatial sampling for level set estimation (LSE), where the goal is to localize all regions where a function of interest lies above/below a given threshold as quickly as possible. We present a finite-horizon search procedure to perform LSE in one dimension while optimally balancing both the final estimation error and the distance traveled for a fixed number of samples. A tuning parameter is used to trade off between the estimation accuracy and distance traveled. We show that the resulting optimization problem can be solved in closed form and that the resulting policy generalizes existing approaches to this problem. We then show how this approach can be used to perform level set estimation in higher dimensions under the popular Gaussian process model. Empirical results on synthetic data indicate that as the cost of travel increases, our method's ability to treat distance nonmyopically allows it to significantly improve on the state of the art. On real air quality data, our approach achieves roughly one fifth the estimation error at less than half the cost of competing algorithms.
The evolution of Internet and its related communication technologies have consistently increased the risk of cyber-attacks. In this context, a crucial role is played by Intrusion Detection Systems (IDSs), which are security devices designed to identify and mitigate attacks to modern networks. Data-driven approaches based on Machine Learning (ML) have gained more and more popularity for executing the classification tasks required by signature-based IDSs. However, typical ML models adopted for this purpose do not properly take into account the uncertainty associated with their prediction. This poses significant challenges, as they tend to produce misleadingly high classification scores for both misclassified inputs and inputs belonging to unknown classes (e.g. novel attacks), limiting the trustworthiness of existing ML-based solutions. In this paper, we argue that ML-based IDSs should always provide accurate uncertainty quantification to avoid overconfident predictions. In fact, an uncertainty-aware classification would be beneficial to enhance closed-set classification performance, would make it possible to carry out Active Learning, and would help recognize inputs of unknown classes as truly unknowns, unlocking open-set classification capabilities and Out-of-Distribution (OoD) detection. To verify it, we compare various ML-based methods for uncertainty quantification and for open-set classification, either specifically designed for or tailored to the domain of network intrusion detection. Moreover, we develop a custom model based on Bayesian Neural Networks to ensure reliable uncertainty estimates and improve the OoD detection capabilities, thus showing how proper uncertainty quantification can be exploited to significantly enhance the trustworthiness of ML-based IDSs.
T cell receptors (TCRs) are critical components of adaptive immune systems, responsible for responding to threats by recognizing epitope sequences presented on host cell surface. Computational prediction of binding affinity between TCRs and epitope sequences using machine/deep learning has attracted intense attention recently. However, its success is hindered by the lack of large collections of annotated TCR-epitope pairs. Annotating their binding affinity requires expensive and time-consuming wet-lab evaluation. To reduce annotation cost, we present ActiveTCR, a framework that incorporates active learning and TCR-epitope binding affinity prediction models. Starting with a small set of labeled training pairs, ActiveTCR iteratively searches for unlabeled TCR-epitope pairs that are ''worth'' for annotation. It aims to maximize performance gains while minimizing the cost of annotation. We compared four query strategies with a random sampling baseline and demonstrated that ActiveTCR reduces annotation costs by approximately 40%. Furthermore, we showed that providing ground truth labels of TCR-epitope pairs to query strategies can help identify and reduce more than 40% redundancy among already annotated pairs without compromising model performance, enabling users to train equally powerful prediction models with less training data. Our work is the first systematic investigation of data optimization for TCR-epitope binding affinity prediction.
The South Platte river system contains a mixture of natural streams, reservoirs, and pipeline projects that redirect water to front range communities in Colorado. At many timepoints, a simple persistence model is the best predictor for flow from pipelines and reservoirs but at other times, flows change based on snowmelt and inputs such as reservoir fill rates, local weather, and anticipated demand. Here we find that a convolutional Long Short-Term Memory (LSTM) network is well suited to modeling flow in parts of this basin that are strongly impacted by water projects as well as ones that are relatively free from direct human modifications. Furthermore, it is found that including an active learning component in which separate Convolutional Neural Networks (CNNs) are used to classify and then select the data that is then used for training a convolutional LSTM network is advantageous. Models specific for each gauge are created by transfer of parameter from a base model and these gauge-specific models are then fine-tuned based a curated subset of training data. The result is accurate predictions for both natural flow and human influenced flow using only past river flow, reservoir capacity, and historical temperature data. In 14 of the 16 gauges modeled, the error in the prediction is reduced when using the combination of on-the-fly classification by CNN followed by analysis by either a persistence or convolutional LSTM model. The methods designed here could be applied broadly to other basins and to other situations where multiple models are needed to fit data at different times and locations.
The discovery of therapeutic molecules is fundamentally a multi-objective optimization problem. One formulation of the problem is to identify molecules that simultaneously exhibit strong binding affinity for a target protein, minimal off-target interactions, and suitable pharmacokinetic properties. Inspired by prior work that uses active learning to accelerate the identification of strong binders, we implement multi-objective Bayesian optimization to reduce the computational cost of multi-property virtual screening and apply it to the identification of ligands predicted to be selective based on docking scores to on- and off-targets. We demonstrate the superiority of Pareto optimization over scalarization across three case studies. Further, we use the developed optimization tool to search a virtual library of over 4M molecules for those predicted to be selective dual inhibitors of EGFR and IGF1R, acquiring 100% of the molecules that form the library's Pareto front after exploring only 8% of the library. This workflow and associated open source software can reduce the screening burden of molecular design projects and is complementary to research aiming to improve the accuracy of binding predictions and other molecular properties.
LiDAR-based 3D object detection has recently seen significant advancements through active learning (AL), attaining satisfactory performance by training on a small fraction of strategically selected point clouds. However, in real-world deployments where streaming point clouds may include unknown or novel objects, the ability of current AL methods to capture such objects remains unexplored. This paper investigates a more practical and challenging research task: Open World Active Learning for 3D Object Detection (OWAL-3D), aimed at acquiring informative point clouds with new concepts. To tackle this challenge, we propose a simple yet effective strategy called Open Label Conciseness (OLC), which mines novel 3D objects with minimal annotation costs. Our empirical results show that OLC successfully adapts the 3D detection model to the open world scenario with just a single round of selection. Any generic AL policy can then be integrated with the proposed OLC to efficiently address the OWAL-3D problem. Based on this, we introduce the Open-CRB framework, which seamlessly integrates OLC with our preliminary AL method, CRB, designed specifically for 3D object detection. We develop a comprehensive codebase for easy reproducing and future research, supporting 15 baseline methods (\textit{i.e.}, active learning, out-of-distribution detection and open world detection), 2 types of modern 3D detectors (\textit{i.e.}, one-stage SECOND and two-stage PV-RCNN) and 3 benchmark 3D datasets (\textit{i.e.}, KITTI, nuScenes and Waymo). Extensive experiments evidence that the proposed Open-CRB demonstrates superiority and flexibility in recognizing both novel and known classes with very limited labeling costs, compared to state-of-the-art baselines. Source code is available at \url{https://github.com/Luoyadan/CRB-active-3Ddet/tree/Open-CRB}.
Supervised neural approaches are hindered by their dependence on large, meticulously annotated datasets, a requirement that is particularly cumbersome for sequential tasks. The quality of annotations tends to deteriorate with the transition from expert-based to crowd-sourced labelling. To address these challenges, we present CAMEL (Confidence-based Acquisition Model for Efficient self-supervised active Learning), a pool-based active learning framework tailored to sequential multi-output problems. CAMEL possesses two core features: (1) it requires expert annotators to label only a fraction of a chosen sequence, and (2) it facilitates self-supervision for the remainder of the sequence. By deploying a label correction mechanism, CAMEL can also be utilised for data cleaning. We evaluate CAMEL on two sequential tasks, with a special emphasis on dialogue belief tracking, a task plagued by the constraints of limited and noisy datasets. Our experiments demonstrate that CAMEL significantly outperforms the baselines in terms of efficiency. Furthermore, the data corrections suggested by our method contribute to an overall improvement in the quality of the resulting datasets.
Most Reinforcement Learning (RL) methods are traditionally studied in an active learning setting, where agents directly interact with their environments, observe action outcomes, and learn through trial and error. However, allowing partially trained agents to interact with real physical systems poses significant challenges, including high costs, safety risks, and the need for constant supervision. Offline RL addresses these cost and safety concerns by leveraging existing datasets and reducing the need for resource-intensive real-time interactions. Nevertheless, a substantial challenge lies in the demand for these datasets to be meticulously annotated with rewards. In this paper, we introduce Optimal Transport Reward (OTR) labelling, an innovative algorithm designed to assign rewards to offline trajectories, using a small number of high-quality expert demonstrations. The core principle of OTR involves employing Optimal Transport (OT) to calculate an optimal alignment between an unlabeled trajectory from the dataset and an expert demonstration. This alignment yields a similarity measure that is effectively interpreted as a reward signal. An offline RL algorithm can then utilize these reward signals to learn a policy. This approach circumvents the need for handcrafted rewards, unlocking the potential to harness vast datasets for policy learning. Leveraging the SurRoL simulation platform tailored for surgical robot learning, we generate datasets and employ them to train policies using the OTR algorithm. By demonstrating the efficacy of OTR in a different domain, we emphasize its versatility and its potential to expedite RL deployment across a wide range of fields.
Optimizing objectives under constraints, where both the objectives and constraints are black box functions, is a common scenario in real-world applications such as scientific experimental design, design of medical therapies, and industrial process optimization. One popular approach to handling these complex scenarios is Bayesian Optimization (BO). In terms of theoretical behavior, BO is relatively well understood in the unconstrained setting, where its principles have been well explored and validated. However, when it comes to constrained Bayesian optimization (CBO), the existing framework often relies on heuristics or approximations without the same level of theoretical guarantees. In this paper, we delve into the theoretical and practical aspects of constrained Bayesian optimization, where the objective and constraints can be independently evaluated and are subject to noise. By recognizing that both the objective and constraints can help identify high-confidence regions of interest (ROI), we propose an efficient CBO framework that intersects the ROIs identified from each aspect to determine the general ROI. The ROI, coupled with a novel acquisition function that adaptively balances the optimization of the objective and the identification of feasible regions, enables us to derive rigorous theoretical justifications for its performance. We showcase the efficiency and robustness of our proposed CBO framework through empirical evidence and discuss the fundamental challenge of deriving practical regret bounds for CBO algorithms.
We consider the problem of a revenue-maximizing seller with a large number of items $m$ for sale to $n$ strategic bidders, whose valuations are drawn independently from high-dimensional, unknown prior distributions. It is well-known that optimal and even approximately-optimal mechanisms for this setting are notoriously difficult to characterize or compute, and, even when they can be found, are often rife with various counter-intuitive properties. In this paper, following a model introduced recently by Cai and Daskalakis~\cite{cai2022recommender}, we consider the case that bidders' prior distributions can be well-approximated by a topic model. We design an active learning component, responsible for interacting with the bidders and outputting low-dimensional approximations of their types, and a mechanism design component, responsible for robustifying mechanisms for the low-dimensional model to work for the approximate types of the former component. On the active learning front, we cast our problem in the framework of Randomized Linear Algebra (RLA) for regression problems, allowing us to import several breakthrough results from that line of research, and adapt them to our setting. On the mechanism design front, we remove many restrictive assumptions of prior work on the type of access needed to the underlying distributions and the associated mechanisms. To the best of our knowledge, our work is the first to formulate connections between mechanism design, and RLA for active learning of regression problems, opening the door for further applications of randomized linear algebra primitives to mechanism design.
Active learning strives to reduce the need for costly data annotation, by repeatedly querying an annotator to label the most informative samples from a pool of unlabeled data, and then training a model from these samples. We identify two problems with existing active learning methods for LiDAR semantic segmentation. First, they overlook the severe class imbalance inherent in LiDAR semantic segmentation datasets. Second, to bootstrap the active learning loop when there is no labeled data available, they train their initial model from randomly selected data samples, leading to low performance. This situation is referred to as the cold start problem. To address these problems we propose BaSAL, a size-balanced warm start active learning model, based on the observation that each object class has a characteristic size. By sampling object clusters according to their size, we can thus create a size-balanced dataset that is also more class-balanced. Furthermore, in contrast to existing information measures like entropy or CoreSet, size-based sampling does not require a pretrained model, thus addressing the cold start problem effectively. Results show that we are able to improve the performance of the initial model by a large margin. Combining warm start and size-balanced sampling with established information measures, our approach achieves comparable performance to training on the entire SemanticKITTI dataset, despite using only 5% of the annotations, outperforming existing active learning methods. We also match the existing state-of-the-art in active learning on nuScenes. Our code is available at: https://github.com/Tony-WJR/BaSAL.
Active learning strategies aim to train high-performance models with minimal labeled data by selecting the most informative instances for labeling. However, existing methods for assessing data informativeness often fail to align directly with task model performance metrics, such as mean average precision (mAP) in object detection. This paper introduces Mean-AP Guided Reinforced Active Learning for Object Detection (MGRAL), a novel approach that leverages the concept of expected model output changes as informativeness for deep detection networks, directly optimizing the sampling strategy using mAP. MGRAL employs a reinforcement learning agent based on LSTM architecture to efficiently navigate the combinatorial challenge of batch sample selection and the non-differentiable nature between performance and selected batches. The agent optimizes selection using policy gradient with mAP improvement as the reward signal. To address the computational intensity of mAP estimation with unlabeled samples, we implement fast look-up tables, ensuring real-world feasibility. We evaluate MGRAL on PASCAL VOC and MS COCO benchmarks across various backbone architectures. Our approach demonstrates strong performance, establishing a new paradigm in reinforcement learning-based active learning for object detection.
This paper makes two key contributions. First, it argues that highly specialized rare content classifiers trained on small data typically have limited exposure to the richness and topical diversity of the negative class (dubbed anticontent) as observed in the wild. As a result, these classifiers' strong performance observed on the test set may not translate into real-world settings. In the context of COVID-19 misinformation detection, we conduct an in-the-wild audit of multiple datasets and demonstrate that models trained with several prominently cited recent datasets are vulnerable to anticontent when evaluated in the wild. Second, we present a novel active learning pipeline that requires zero manual annotation and iteratively augments the training data with challenging anticontent, robustifying these classifiers.
The repeated solution of large-scale optimization problems arises frequently in process systems engineering tasks. Decomposition-based solution methods have been widely used to reduce the corresponding computational time, yet their implementation has multiple steps that are difficult to configure. We propose a machine learning approach to learn the optimal initialization of such algorithms which minimizes the computational time. Active and supervised learning is used to learn a surrogate model that predicts the computational performance for a given initialization. We apply this approach to the initialization of Generalized Benders Decomposition for the solution of mixed integer model predictive control problems. The surrogate models are used to find the optimal number of initial cuts that should be added in the master problem. The results show that the proposed approach can lead to a significant reduction in solution time, and active learning can reduce the data required for learning.
It is challenging but important to save annotation efforts in streaming data acquisition to maintain data quality for supervised learning base learners. We propose an ensemble active learning method to actively acquire samples for annotation by contextual bandits, which is will enforce the exploration-exploitation balance and leading to improved AI modeling performance.
The rapid evolution of deep learning has significantly advanced the field of medical image analysis. However, despite these achievements, the further enhancement of deep learning models for medical image analysis faces a significant challenge due to the scarcity of large, well-annotated datasets. To address this issue, recent years have witnessed a growing emphasis on the development of data-efficient deep learning methods. This paper conducts a thorough review of data-efficient deep learning methods for medical image analysis. To this end, we categorize these methods based on the level of supervision they rely on, encompassing categories such as no supervision, inexact supervision, incomplete supervision, inaccurate supervision, and only limited supervision. We further divide these categories into finer subcategories. For example, we categorize inexact supervision into multiple instance learning and learning with weak annotations. Similarly, we categorize incomplete supervision into semi-supervised learning, active learning, and domain-adaptive learning and so on. Furthermore, we systematically summarize commonly used datasets for data efficient deep learning in medical image analysis and investigate future research directions to conclude this survey.