Active learning (AL) has found wide applications in medical image segmentation, aiming to alleviate the annotation workload and enhance performance. Conventional uncertainty-based AL methods, such as entropy and Bayesian, often rely on an aggregate of all pixel-level metrics. However, in imbalanced settings, these methods tend to neglect the significance of target regions, eg., lesions, and tumors. Moreover, uncertainty-based selection introduces redundancy. These factors lead to unsatisfactory performance, and in many cases, even underperform random sampling. To solve this problem, we introduce a novel approach called the Selective Uncertainty-based AL, avoiding the conventional practice of summing up the metrics of all pixels. Through a filtering process, our strategy prioritizes pixels within target areas and those near decision boundaries. This resolves the aforementioned disregard for target areas and redundancy. Our method showed substantial improvements across five different uncertainty-based methods and two distinct datasets, utilizing fewer labeled data to reach the supervised baseline and consistently achieving the highest overall performance. Our code is available at https://github.com/HelenMa9998/Selective\_Uncertainty\_AL.
The Deep Learning revolution has enabled groundbreaking achievements in recent years. From breast cancer detection to protein folding, deep learning algorithms have been at the core of very important advancements. However, these modern advancements are becoming more and more data-hungry, especially on labeled data whose availability is scarce: this is even more prevalent in the medical context. In this work, we show how active learning could be very effective in data scarcity situations, where obtaining labeled data (or annotation budget is very limited). We compare several selection criteria (BALD, MeanSTD, and MaxEntropy) on the ISIC 2016 dataset. We also explored the effect of acquired pool size on the model's performance. Our results suggest that uncertainty is useful to the Melanoma detection task, and confirms the hypotheses of the author of the paper of interest, that \textit{bald} performs on average better than other acquisition functions. Our extended analyses however revealed that all acquisition functions perform badly on the positive (cancerous) samples, suggesting exploitation of class unbalance, which could be crucial in real-world settings. We finish by suggesting future work directions that would be useful to improve this current work. The code of our implementation is open-sourced at \url{https://github.com/bonaventuredossou/ece526_course_project}
Cluster repair methods aim to determine errors in clusters and modify them so that each cluster consists of records representing the same entity. Current cluster repair methodologies primarily assume duplicate-free data sources, where each record from one source corresponds to a unique record from another. However, real-world data often deviates from this assumption due to quality issues. Recent approaches apply clustering methods in combination with link categorization methods so they can be applied to data sources with duplicates. Nevertheless, the results do not show a clear picture since the quality highly varies depending on the configuration and dataset. In this study, we introduce a novel approach for cluster repair that utilizes graph metrics derived from the underlying similarity graphs. These metrics are pivotal in constructing a classification model to distinguish between correct and incorrect edges. To address the challenge of limited training data, we integrate an active learning mechanism tailored to cluster-specific attributes. The evaluation shows that the method outperforms existing cluster repair methods without distinguishing between duplicate-free or dirty data sources. Notably, our modified active learning strategy exhibits enhanced performance when dealing with datasets containing duplicates, showcasing its effectiveness in such scenarios.
Foundation vision or vision-language models are trained on large unlabeled or noisy data and learn robust representations that can achieve impressive zero- or few-shot performance on diverse tasks. Given these properties, they are a natural fit for active learning (AL), which aims to maximize labeling efficiency. However, the full potential of foundation models has not been explored in the context of AL, specifically in the low-budget regime. In this work, we evaluate how foundation models influence three critical components of effective AL, namely, 1) initial labeled pool selection, 2) ensuring diverse sampling, and 3) the trade-off between representative and uncertainty sampling. We systematically study how the robust representations of foundation models (DINOv2, OpenCLIP) challenge existing findings in active learning. Our observations inform the principled construction of a new simple and elegant AL strategy that balances uncertainty estimated via dropout with sample diversity. We extensively test our strategy on many challenging image classification benchmarks, including natural images as well as out-of-domain biomedical images that are relatively understudied in the AL literature. We also provide a highly performant and efficient implementation of modern AL strategies (including our method) at https://github.com/sanketx/AL-foundation-models.
In the web era, graph machine learning has been widely used on ubiquitous graph-structured data. As a pivotal component for bolstering web security and enhancing the robustness of graph-based applications, the significance of graph anomaly detection is continually increasing. While Graph Neural Networks (GNNs) have demonstrated efficacy in supervised and semi-supervised graph anomaly detection, their performance is contingent upon the availability of sufficient ground truth labels. The labor-intensive nature of identifying anomalies from complex graph structures poses a significant challenge in real-world applications. Despite that, the indirect supervision signals from other tasks (e.g., node classification) are relatively abundant. In this paper, we propose a novel MultItask acTIve Graph Anomaly deTEction framework, namely MITIGATE. Firstly, by coupling node classification tasks, MITIGATE obtains the capability to detect out-of-distribution nodes without known anomalies. Secondly, MITIGATE quantifies the informativeness of nodes by the confidence difference across tasks, allowing samples with conflicting predictions to provide informative yet not excessively challenging information for subsequent training. Finally, to enhance the likelihood of selecting representative nodes that are distant from known patterns, MITIGATE adopts a masked aggregation mechanism for distance measurement, considering both inherent features of nodes and current labeled status. Empirical studies on four datasets demonstrate that MITIGATE significantly outperforms the state-of-the-art methods for anomaly detection. Our code is publicly available at: https://github.com/AhaChang/MITIGATE.
Concept drift is a significant challenge for malware detection, as the performance of trained machine learning models degrades over time, rendering them impractical. While prior research in malware concept drift adaptation has primarily focused on active learning, which involves selecting representative samples to update the model, self-training has emerged as a promising approach to mitigate concept drift. Self-training involves retraining the model using pseudo labels to adapt to shifting data distributions. In this research, we propose MORPH -- an effective pseudo-label-based concept drift adaptation method specifically designed for neural networks. Through extensive experimental analysis of Android and Windows malware datasets, we demonstrate the efficacy of our approach in mitigating the impact of concept drift. Our method offers the advantage of reducing annotation efforts when combined with active learning. Furthermore, our method significantly improves over existing works in automated concept drift adaptation for malware detection.
Biased data can lead to unfair machine learning models, highlighting the importance of embedding fairness at the beginning of data analysis, particularly during dataset curation and labeling. In response, we propose Falcon, a scalable fair active learning framework. Falcon adopts a data-centric approach that improves machine learning model fairness via strategic sample selection. Given a user-specified group fairness measure, Falcon identifies samples from "target groups" (e.g., (attribute=female, label=positive)) that are the most informative for improving fairness. However, a challenge arises since these target groups are defined using ground truth labels that are not available during sample selection. To handle this, we propose a novel trial-and-error method, where we postpone using a sample if the predicted label is different from the expected one and falls outside the target group. We also observe the trade-off that selecting more informative samples results in higher likelihood of postponing due to undesired label prediction, and the optimal balance varies per dataset. We capture the trade-off between informativeness and postpone rate as policies and propose to automatically select the best policy using adversarial multi-armed bandit methods, given their computational efficiency and theoretical guarantees. Experiments show that Falcon significantly outperforms existing fair active learning approaches in terms of fairness and accuracy and is more efficient. In particular, only Falcon supports a proper trade-off between accuracy and fairness where its maximum fairness score is 1.8-4.5x higher than the second-best results.
Active learning is a machine learning paradigm that aims to improve the performance of a model by strategically selecting and querying unlabeled data. One effective selection strategy is to base it on the model's predictive uncertainty, which can be interpreted as a measure of how informative a sample is. The sample's distance to the decision boundary is a natural measure of predictive uncertainty, but it is often intractable to compute, especially for complex decision boundaries formed in multiclass classification tasks. To address this issue, this paper proposes the {\it least disagree metric} (LDM), defined as the smallest probability of disagreement of the predicted label, and an estimator for LDM proven to be asymptotically consistent under mild assumptions. The estimator is computationally efficient and can be easily implemented for deep learning models using parameter perturbation. The LDM-based active learning is performed by querying unlabeled data with the smallest LDM. Experimental results show that our LDM-based active learning algorithm obtains state-of-the-art overall performance on all considered datasets and deep architectures.
In the realm of artificial intelligence, where a vast majority of data is unstructured, obtaining substantial amounts of labeled data to train supervised machine learning models poses a significant challenge. To address this, we delve into few-shot and active learning, where are goal is to improve AI models with human feedback on a few labeled examples. This paper focuses on understanding how a continuous feedback loop can refine models, thereby enhancing their accuracy, recall, and precision through incremental human input. By employing Large Language Models (LLMs) such as GPT-3.5, BERT, and SetFit, we aim to analyze the efficacy of using a limited number of labeled examples to substantially improve model accuracy. We benchmark this approach on the Financial Phrasebank, Banking, Craigslist, Trec, Amazon Reviews datasets to prove that with just a few labeled examples, we are able to surpass the accuracy of zero shot large language models to provide enhanced text classification performance. We demonstrate that rather than needing to manually label millions of rows of data, we just need to label a few and the model can effectively predict the rest.
Uncertainty estimation is an essential and heavily-studied component for the reliable application of semantic segmentation methods. While various studies exist claiming methodological advances on the one hand, and successful application on the other hand, the field is currently hampered by a gap between theory and practice leaving fundamental questions unanswered: Can data-related and model-related uncertainty really be separated in practice? Which components of an uncertainty method are essential for real-world performance? Which uncertainty method works well for which application? In this work, we link this research gap to a lack of systematic and comprehensive evaluation of uncertainty methods. Specifically, we identify three key pitfalls in current literature and present an evaluation framework that bridges the research gap by providing 1) a controlled environment for studying data ambiguities as well as distribution shifts, 2) systematic ablations of relevant method components, and 3) test-beds for the five predominant uncertainty applications: OoD-detection, active learning, failure detection, calibration, and ambiguity modeling. Empirical results on simulated as well as real-world data demonstrate how the proposed framework is able to answer the predominant questions in the field revealing for instance that 1) separation of uncertainty types works on simulated data but does not necessarily translate to real-world data, 2) aggregation of scores is a crucial but currently neglected component of uncertainty methods, 3) While ensembles are performing most robustly across the different downstream tasks and settings, test-time augmentation often constitutes a light-weight alternative. Code is at: https://github.com/IML-DKFZ/values
Synthetic aperture radar (SAR) has been extensively utilized in maritime domains due to its all-weather, all-day monitoring capabilities, particularly exhibiting significant value in ship detection. In recent years, deep learning methods have increasingly been utilized for refined ship detection. However, learning-based methods exhibit poor generalization when confronted with new scenarios and data, necessitating expert intervention for continuous annotation. Currently, the degree of automation in human-machine collaboration within this field, especially in annotating new data, is not high, leading to labor- and computation-intensive model iteration and updates. Addressing these issues, a ship detection framework in SAR images with human-in-the-loop (HitL) is proposed. Incorporating the concept of HitL, tailored active learning strategies are designed for SAR ship detection tasks to present valuable samples to users, and an interactive human-machine interface (HMI) is established to efficiently collect user feedback. Consequently, user input is utilized in each interaction round to enhance model performance. Employing the proposed framework, an annotated ship database of SAR images is constructed, and the iteration experiments conducted during the construction demonstrates the efficiency of the method, providing new perspectives and approaches for research in this domain.
Screening documents is a tedious and time-consuming aspect of high-recall retrieval tasks, such as compiling a systematic literature review, where the goal is to identify all relevant documents for a topic. To help streamline this process, many Technology-Assisted Review (TAR) methods leverage active learning techniques to reduce the number of documents requiring review. BERT-based models have shown high effectiveness in text classification, leading to interest in their potential use in TAR workflows. In this paper, we investigate recent work that examined the impact of further pre-training epochs on the effectiveness and efficiency of a BERT-based active learning pipeline. We first report that we could replicate the original experiments on two specific TAR datasets, confirming some of the findings: importantly, that further pre-training is critical to high effectiveness, but requires attention in terms of selecting the correct training epoch. We then investigate the generalisability of the pipeline on a different TAR task, that of medical systematic reviews. In this context, we show that there is no need for further pre-training if a domain-specific BERT backbone is used within the active learning pipeline. This finding provides practical implications for using the studied active learning pipeline within domain-specific TAR tasks.
Human annotation of training samples is expensive, laborious, and sometimes challenging, especially for Natural Language Processing (NLP) tasks. To reduce the labeling cost and enhance the sample efficiency, Active Learning (AL) technique can be used to label as few samples as possible to reach a reasonable or similar results. To reduce even more costs and with the significant advances of Large Language Models (LLMs), LLMs can be a good candidate to annotate samples. This work investigates the accuracy and cost of using LLMs (GPT-3.5 and GPT-4) to label samples on 3 different datasets. A consistency-based strategy is proposed to select samples that are potentially incorrectly labeled so that human annotations can be used for those samples in AL settings, and we call it mixed annotation strategy. Then we test performance of AL under two different settings: (1) using human annotations only; (2) using the proposed mixed annotation strategy. The accuracy of AL models under 3 AL query strategies are reported on 3 text classification datasets, i.e., AG's News, TREC-6, and Rotten Tomatoes. On AG's News and Rotten Tomatoes, the models trained with the mixed annotation strategy achieves similar or better results compared to that with human annotations. The method reveals great potentials of LLMs as annotators in terms of accuracy and cost efficiency in active learning settings.
Active learning, a powerful paradigm in machine learning, aims at reducing labeling costs by selecting the most informative samples from an unlabeled dataset. However, the traditional active learning process often demands extensive computational resources, hindering scalability and efficiency. In this paper, we address this critical issue by presenting a novel method designed to alleviate the computational burden associated with active learning on massive datasets. To achieve this goal, we introduce a simple, yet effective method-agnostic framework that outlines how to strategically choose and annotate data points, optimizing the process for efficiency while maintaining model performance. Through case studies, we demonstrate the effectiveness of our proposed method in reducing computational costs while maintaining or, in some cases, even surpassing baseline model outcomes. Code is available at https://github.com/aimotive/Compute-Efficient-Active-Learning.
A significant challenge to training accurate deep learning models on privacy policies is the cost and difficulty of obtaining a large and comprehensive set of training data. To address these challenges, we present Calpric , which combines automatic text selection and segmentation, active learning and the use of crowdsourced annotators to generate a large, balanced training set for privacy policies at low cost. Automated text selection and segmentation simplifies the labeling task, enabling untrained annotators from crowdsourcing platforms, like Amazon's Mechanical Turk, to be competitive with trained annotators, such as law students, and also reduces inter-annotator agreement, which decreases labeling cost. Having reliable labels for training enables the use of active learning, which uses fewer training samples to efficiently cover the input space, further reducing cost and improving class and data category balance in the data set. The combination of these techniques allows Calpric to produce models that are accurate over a wider range of data categories, and provide more detailed, fine-grain labels than previous work. Our crowdsourcing process enables Calpric to attain reliable labeled data at a cost of roughly $0.92-$1.71 per labeled text segment. Calpric 's training process also generates a labeled data set of 16K privacy policy text segments across 9 Data categories with balanced positive and negative samples.
Within the scope of natural language processing, the domain of multi-label text classification is uniquely challenging due to its expansive and uneven label distribution. The complexity deepens due to the demand for an extensive set of annotated data for training an advanced deep learning model, especially in specialized fields where the labeling task can be labor-intensive and often requires domain-specific knowledge. Addressing these challenges, our study introduces a novel deep active learning strategy, capitalizing on the Beta family of proper scoring rules within the Expected Loss Reduction framework. It computes the expected increase in scores using the Beta Scoring Rules, which are then transformed into sample vector representations. These vector representations guide the diverse selection of informative samples, directly linking this process to the model's expected proper score. Comprehensive evaluations across both synthetic and real datasets reveal our method's capability to often outperform established acquisition techniques in multi-label text classification, presenting encouraging outcomes across various architectural and dataset scenarios.
Supervised finetuning (SFT) on instruction datasets has played a crucial role in achieving the remarkable zero-shot generalization capabilities observed in modern large language models (LLMs). However, the annotation efforts required to produce high quality responses for instructions are becoming prohibitively expensive, especially as the number of tasks spanned by instruction datasets continues to increase. Active learning is effective in identifying useful subsets of samples to annotate from an unlabeled pool, but its high computational cost remains a barrier to its widespread applicability in the context of LLMs. To mitigate the annotation cost of SFT and circumvent the computational bottlenecks of active learning, we propose using experimental design. Experimental design techniques select the most informative samples to label, and typically maximize some notion of uncertainty and/or diversity. In our work, we implement a framework that evaluates several existing and novel experimental design techniques and find that these methods consistently yield significant gains in label efficiency with little computational overhead. On generative tasks, our methods achieve the same generalization performance with only $50\%$ of annotation cost required by random sampling.
Nickel titanium (NiTi) is a protypical shape-memory alloy used in a range of biomedical and engineering devices, but direct molecular dynamics simulations of the martensitic B19' -> B2 phase transition driving its shape-memory behavior are rare and have relied on classical force fields with limited accuracy. Here, we train four machine-learned force fields for equiatomic NiTi based on the LDA, PBE, PBEsol, and SCAN DFT functionals. The models are trained on the fly during NPT molecular dynamics, with DFT calculations and model updates performed automatically whenever the uncertainty of a local energy prediction exceeds a chosen threshold. The models achieve accuracies of 1-2 meV/atom during training and are shown to closely track DFT predictions of B2 and B19' elastic constants and phonon frequencies. Surprisingly, in large-scale molecular dynamics simulations, only the SCAN model predicts a reversible B19' -> B2 phase transition, with the LDA, PBE, and PBEsol models predicting a reversible transition to a previously uncharacterized low-volume phase, which we hypothesize to be a new stable high-pressure phase. We examine the structure of the new phase and estimate its stability on the temperature-pressure phase diagram. This work establishes an automated active learning protocol for studying displacive transformations, reveals important differences between DFT functionals that can only be detected in large-scale simulations, provides an accurate force field for NiTi, and identifies a new phase.
The advent of compact, handheld devices has given us a pool of tracked movement data that could be used to infer trends and patterns that can be made to use. With this flooding of various trajectory data of animals, humans, vehicles, etc., the idea of ANALYTiC originated, using active learning to infer semantic annotations from the trajectories by learning from sets of labeled data. This study explores the application of dimensionality reduction and decision boundaries in combination with the already present active learning, highlighting patterns and clusters in data. We test these features with three different trajectory datasets with objective of exploiting the the already labeled data and enhance their interpretability. Our experimental analysis exemplifies the potential of these combined methodologies in improving the efficiency and accuracy of trajectory labeling. This study serves as a stepping-stone towards the broader integration of machine learning and visual methods in context of movement data analysis.
Active learning is a commonly used approach that reduces the labeling effort required to train deep neural networks. However, the effectiveness of current active learning methods is limited by their closed-world assumptions, which assume that all data in the unlabeled pool comes from a set of predefined known classes. This assumption is often not valid in practical situations, as there may be unknown classes in the unlabeled data, leading to the active open-set annotation problem. The presence of unknown classes in the data can significantly impact the performance of existing active learning methods due to the uncertainty they introduce. To address this issue, we propose a novel data-centric active learning method called NEAT that actively annotates open-set data. NEAT is designed to label known classes data from a pool of both known and unknown classes unlabeled data. It utilizes the clusterability of labels to identify the known classes from the unlabeled pool and selects informative samples from those classes based on a consistency criterion that measures inconsistencies between model predictions and local feature distribution. Unlike the recently proposed learning-centric method for the same problem, NEAT is much more computationally efficient and is a data-centric active open-set annotation method. Our experiments demonstrate that NEAT achieves significantly better performance than state-of-the-art active learning methods for active open-set annotation.