Instance Weighting Research Articles

AVATAR: Adversarial self-superVised domain Adaptation network for TARget domain

This paper introduces AVATAR (adversarial self-supervised domain adaptation network for target domain), a novel unsupervised domain adaptation method designed to address the challenge of transferring knowledge from a well-labeled source domain to an unlabeled target domain. AVATAR’s key contributions lie in its unique combination of adversarial learning and self-supervised learning techniques, which enhance the model’s adaptability and accuracy in new, unlabeled environments. The technical innovations of AVATAR include a domain adversarial learning component that reduces domain discrepancy by aligning source and target domain features in a shared feature space, a self-supervised learning module that leverages pseudo-labels and instance weights to refine target domain discrimination boundaries, and a sample selection strategy guided by within-cluster distances to focus on aligning informative samples while mitigating the impact of outliers. By integrating these components, AVATAR provides a comprehensive framework for tackling complex unsupervised domain adaptation tasks, particularly when the domain gap is significant. The method balances domain-invariant feature learning with domain-specific adjustments, enabling effective adaptation to dynamically changing environments. Extensive experiments on multiple benchmark datasets demonstrate AVATAR’s superior performance compared to existing domain adaptation methods, especially in scenarios with limited labeled target domain data. These results highlight AVATAR’s potential as a versatile and robust solution for domain adaptation challenges in various real-world applications.

Adaptive ambiguity-aware weighting for multi-label recognition with limited annotations

In multi-label recognition, effectively addressing the challenge of partial labels is crucial for reducing annotation costs and enhancing model generalization. Existing methods exhibit limitations by relying on unrealistic simulations with uniformly dropped labels, overlooking how ambiguous instances and instance-level factors impacts label ambiguity in real-world datasets. To address this deficiency, our paper introduces a realistic partial label setting grounded in instance ambiguity, complemented by Reliable Ambiguity-Aware Instance Weighting (R-AAIW)—a strategy that utilizes importance weighting to adapt dynamically to the inherent ambiguity of multi-label instances. The strategy leverages an ambiguity score to prioritize learning from clearer instances. As proficiency of the model improves, the weights are dynamically modulated to gradually shift focus towards more ambiguous instances. By employing an adaptive re-weighting method that adjusts to the complexity of each instance, our approach not only enhances the model’s capability to detect subtle variations among labels but also ensures comprehensive learning without excluding difficult instances. Extensive experimentation across various benchmarks highlights our approach’s superiority over existing methods, showcasing its ability to provide a more accurate and adaptable framework for multi-label recognition tasks.

Adapting the process based STICS model to simulate phenology and yield of table grapes- a high value fruit crop in a new emerging viticulture zone of South Asia

Plants strongly interact with their environment making phenology a sensitive indicator of climatic variability. Exploring the possibility of early prediction of phenological timings of table grape cultivars has huge socioeconomic benefits for the growers. Various statistical, mechanistic, and theoretical approaches have been used for parameterization of phenology models mainly for wine grapes. The studies on application of process-based models such as STICS (Simulateur mulTIdisciplinaire pour les Cultures Standard) particularly for table grapes and non-traditional viticulture zones are rather limited. The objective of this study was to calibrate the STICS model and evaluate its performance to simulate phenology and yield of four table grape cultivars in Pothwar- a new emerging viticulture zone of south Asia. For this, phenological timings, growth and yield responses were evaluated at two locations (Islamabad and Chakwal) for two consecutive vintages (2019 and 2020). Daily weather data, soil characteristics, genotype and crop specific data were recorded for model calibration. The results indicated a high robustness of the model for simulating table grapes phenology and yield in all cases. The model simulations indicated a satisfactory to high model efficiency (ME) of 0.69 to 0.94 with a prediction variability up to 4 days for growth stages, whereas ME for yield and pruning weight was 0.84 and 0.90, respectively. The model provided an efficient decision support tool (DST) though crucial predictions for viticulture industry. For instance, early maturity (up to 10 days), lesser yield (19–34 %) and pruning weight (19–42 %) for the warmer location (Chakwal) than for the colder Islamabad were simulated by the model with a high skill. The proximity of predicted values to observed values indicates that STICS is powerful tool for predicting vine phenology and yield, thus it provides a valuable insight in timely planning vineyards operations at key growth stages and selecting cultivars with higher yield for sustainable viticulture.

Interaction between ABA and NO in plants under abiotic stresses and its regulatory mechanisms.

Abscisic acid (ABA) and nitric oxide (NO), as unique signaling molecules, are involved in plant growth, developmental processes, and abiotic stresses. However, the interaction between ABA and NO under abiotic stresses has little been worked out at present. Therefore, this paper reviews the mechanisms of crosstalk between ABA and NO in the regulation of plants in response to environmental stresses. Firstly, ABA-NO interaction can alleviate the changes of plant morphological indexes damaged by abiotic stresses, for instance, root length, leaf area, and fresh weight. Secondly, regulatory mechanisms of interaction between ABA and NO are also summarized, such as reactive oxygen species (ROS), antioxidant enzymes, proline, flavonoids, polyamines (PAs), ascorbate-glutathione cycle, water balance, photosynthetic, stomatal movement, and post-translational modifications. Meanwhile, the relationships between ABA and NO are established. ABA regulates NO through ROS at the physiological level during the regulatory processes. At the molecular level, NO counteracts ABA through mediating post-translational modifications. Moreover, we also discuss key genes related to the antioxidant enzymes, PAs biosynthesis, ABA receptor, NO biosynthesis, and flavonoid biosynthesis that are regulated by the interaction between ABA and NO under environmental stresses. This review will provide new guiding directions for the mechanism of the crosstalk between ABA and NO to alleviate abiotic stresses.

Multi-class boosting for the analysis of multiple incomplete views on microbiome data

BackgroundMicrobiome dysbiosis has recently been associated with different diseases and disorders. In this context, machine learning (ML) approaches can be useful either to identify new patterns or learn predictive models. However, data to be fed to ML methods can be subject to different sampling, sequencing and preprocessing techniques. Each different choice in the pipeline can lead to a different view (i.e., feature set) of the same individuals, that classical (single-view) ML approaches may fail to simultaneously consider. Moreover, some views may be incomplete, i.e., some individuals may be missing in some views, possibly due to the absence of some measurements or to the fact that some features are not available/applicable for all the individuals. Multi-view learning methods can represent a possible solution to consider multiple feature sets for the same individuals, but most existing multi-view learning methods are limited to binary classification tasks or cannot work with incomplete views.ResultsWe propose irBoost.SH, an extension of the multi-view boosting algorithm rBoost.SH, based on multi-armed bandits. irBoost.SH solves multi-class classification tasks and can analyze incomplete views. At each iteration, it identifies one winning view using adversarial multi-armed bandits and uses its predictions to update a shared instance weight distribution in a learning process based on boosting. In our experiments, performed on 5 multi-view microbiome datasets, the model learned by irBoost.SH always outperforms the best model learned from a single view, its closest competitor rBoost.SH, and the model learned by a multi-view approach based on feature concatenation, reaching an improvement of 11.8% of the F1-score in the prediction of the Autism Spectrum disorder and of 114% in the prediction of the Colorectal Cancer disease.ConclusionsThe proposed method irBoost.SH exhibited outstanding performances in our experiments, also compared to competitor approaches. The obtained results confirm that irBoost.SH can fruitfully be adopted for the analysis of microbiome data, due to its capability to simultaneously exploit multiple feature sets obtained through different sequencing and preprocessing pipelines.

Fair-CMNB: Advancing Fairness-Aware Stream Learning with Naïve Bayes and Multi-Objective Optimization

Fairness-aware mining of data streams is a challenging concern in the contemporary domain of machine learning. Many stream learning algorithms are used to replace humans in critical decision-making processes, e.g., hiring staff, assessing credit risk, etc. This calls for handling massive amounts of incoming information with minimal response delay while ensuring fair and high-quality decisions. Although deep learning has achieved success in various domains, its computational complexity may hinder real-time processing, making traditional algorithms more suitable. In this context, we propose a novel adaptation of Naïve Bayes to mitigate discrimination embedded in the streams while maintaining high predictive performance through multi-objective optimization (MOO). Class imbalance is an inherent problem in discrimination-aware learning paradigms. To deal with class imbalance, we propose a dynamic instance weighting module that gives more importance to new instances and less importance to obsolete instances based on their membership in a minority or majority class. We have conducted experiments on a range of streaming and static datasets and concluded that our proposed methodology outperforms existing state-of-the-art (SoTA) fairness-aware methods in terms of both discrimination score and balanced accuracy.

Regularized Instance Weighting Multiview Clustering via Late Fusion Alignment.

Multiview clustering has become a prominent research topic in data analysis, with wide-ranging applications across various fields. However, the existing late fusion multiview clustering (LFMVC) methods still exhibit some limitations, including variable importance and contributions and a heightened sensitivity to noise and outliers during the alignment process. To tackle these challenges, we propose a novel regularized instance weighting multiview clustering via late fusion alignment (R-IWLF-MVC), which considers the instance importance from various views, enabling information integration to be more effective. Specifically, we assign each sample an importance attribute to enable the learning process to focus more on the key sample nodes and avoid being influenced by noise or outliers, while laying the groundwork for the fusion of different views. In addition, we continue to employ late fusion alignment to integrate base clustering from various views and introduce a new regularization term with prior knowledge to ensure that the learning process does not deviate too much from the expected results. After that, we design a three-step alternating optimization strategy with proven convergence for the resultant problem. Our proposed approach has been extensively evaluated on multiple real-world datasets, demonstrating its superiority to state-of-the-art methods.

A Locally Instance Weighting Naive Bayes Text Classification Algorithm Based on Distance Correlation Coefficient

A Locally Instance Weighting Naive Bayes Text Classification Algorithm Based on Distance Correlation Coefficient

Instance Weighted Incremental Evolution Strategies for Reinforcement Learning in Dynamic Environments.

Evolution strategies (ESs), as a family of black-box optimization algorithms, recently emerge as a scalable alternative to reinforcement learning (RL) approaches such as Q-learning or policy gradient and are much faster when many central processing units (CPUs) are available due to better parallelization. In this article, we propose a systematic incremental learning method for ES in dynamic environments. The goal is to adjust previously learned policy to a new one incrementally whenever the environment changes. We incorporate an instance weighting mechanism with ES to facilitate its learning adaptation while retaining scalability of ES. During parameter updating, higher weights are assigned to instances that contain more new knowledge, thus encouraging the search distribution to move toward new promising areas of parameter space. We propose two easy-to-implement metrics to calculate the weights: instance novelty and instance quality. Instance novelty measures an instance's difference from the previous optimum in the original environment, while instance quality corresponds to how well an instance performs in the new environment. The resulting algorithm, instance weighted incremental evolution strategies (IW-IESs), is verified to achieve significantly improved performance on challenging RL tasks ranging from robot navigation to locomotion. This article thus introduces a family of scalable ES algorithms for RL domains that enables rapid learning adaptation to dynamic environments.

A novel integrated framework for real-time prediction of transient instabilities in power systems with their severity levels using deep learning

This paper develops an integrated framework comprising deep learning methods for the real-time prediction of transient instabilities, as well as their severities, that might evolve in a power system following a critical contingency. In the first stage of the framework, for an early prediction of transient instability following a fault, phasor measurement unit (PMU) post-fault measurements are fed into a convolutional neural network (CNN) classifier that was previously trained using a cost-sensitive instance weighting (CSIW) approach. By the proposed approach of weighting the loss function based on the severity of unstable instances for training the classifier, the sensitivity of the classifier to instabilities is enhanced, and thus, the classifier of the first stage is made more unlikely to miss the cases that could lead to a wide-spread blackout unless a corrective action is taken. Moreover, a second supportive tool, which is the severity prediction function, is proposed to be integrated with the transient stability prediction function to assist the decision-making process. If the power system is found to be unstable, the severity of the fault inducing instability is successfully predicted in the second stage by using a long short-term memory network (LSTM) to increase the awareness concerning the severity level of the disturbance on which emergency control actions could be planned. The results are compared with model-based methods as well as data-based methods, such as over-sampling and under-sampling. The superiority of the proposed method is demonstrated on the 127-bus WSCC test system and Turkish power system.

A multi-manifold learning based instance weighting and under-sampling for imbalanced data classification problems

Under-sampling is a technique to overcome imbalanced class problem, however, selecting the instances to be dropped and measuring their informativeness is an important concern. This paper tries to bring up a new point of view in this regard and exploit the structure of data to decide on the importance of the data points. For this purpose, a multi-manifold learning approach is proposed. Manifolds represent the underlying structures of data and can help extract the latent space for data distribution. However, there is no evidence that we can rely on a single manifold to extract the local neighborhood of the dataset. Therefore, this paper proposes an ensemble of manifold learning approaches and evaluates each manifold based on an information loss-based heuristic. Having computed the optimality score of each manifold, the centrality and marginality degrees of samples are computed on the manifolds and weighted by the corresponding score. A gradual elimination approach is proposed, which tries to balance the classes while avoiding a drop in the F measure on the validation dataset. The proposed method is evaluated on 22 imbalanced datasets from the KEEL and UCI repositories with different classification measures. The results of the experiments demonstrate that the proposed approach is more effective than other similar approaches and is far better than the previous approaches, especially when the imbalance ratio is very high.

Cross-scene wetland mapping on hyperspectral remote sensing images using adversarial domain adaptation network

Wetlands are one of the most important ecosystems on the Earth, and using hyperspectral remote sensing (RS) technology for fine wetland mapping is important for restoring and protecting the natural resources of coastal wetlands. However, the high cost in collecting labeled samples and inconsistent acquisition conditions across different geographic regions or scenes lead to difficulties in wetland mapping and classification. To mitigate these difficulties, a spatial–spectral weighted adversarial domain adaptation (SSWADA) network is proposed for the cross-scene wetland mapping using hyperspectral image (HSI). The proposed SSWADA employs an idea of weighted adversarial discrimination to align the feature distribution of source and target scenes, where a generator or feature extractor with joint 2D–3D convolution is used to extract spatial–spectral features of HSI, a weighted discriminator is constructed to perform source instance weighting and a multi-classifier structure is designed to improve the classification performance on target samples. Experimental results on four different tasks show that our SSWADA outperforms existing domain adaptation methods for cross-scene wetland mapping.

Quality Control for Distantly-Supervised Data-to-Text Generation via Meta Learning

Data-to-text generation plays an important role in natural language processing by processing structured data and helping people understand those data by generating user-friendly descriptive text. It can be applied to news generation, financial report generation, customer service, etc. However, in practice, it needs to adapt to different domains that may lack an annotated training corpus. To alleviate this dataset scarcity problem, distantly-supervised data-to-text generation has emerged, which constructs a training corpus automatically and is more practical to apply to new domains when well-aligned data is expensive to obtain. However, this distant supervision method of training induces an over-generation problem since the automatically aligned text includes hallucination. These expressions cannot be inferred from the data, misguiding the model to produce unfaithful text. To exploit the noisy dataset while maintaining faithfulness, we empower the neural data-to-text model by dynamically increasing the weights of those well-aligned training instances and reducing the weights of the low-quality ones via meta learning. To our best knowledge, we are the first to alleviate the noise in distantly-supervised data-to-text generation via meta learning. In addition, we rewrite those low-quality texts to provide better training instances. Finally, we construct a new distantly-supervised dataset, DIST-ToTTo (abbreviation for Distantly-supervised Table-To-Text), and conduct experiments on both the benchmark WITA (abbreviation for the data source Wikipedia and Wikidata) and DIST-ToTTo datasets. The evaluation results show that our model can improve the state-of-the-art DSG (abbreviation for Distant Supervision Generation) model across all automatic evaluation metrics, with an improvement of 3.72% on the WITA dataset and 3.82% on the DIST-ToTTo dataset in terms of the widely used metric BLEU (abbreviation for BiLingual Evaluation Understudy). Furthermore, based on human evaluation, our model can generate more grammatically correct and more faithful text compared to the state-of-the-art DSG model.

ARRAY: Adaptive triple feature-weighted transfer Naive Bayes for cross-project defect prediction

Context:Cross-project defect prediction (CPDP) aims to predict defects of target data by using prediction models trained on the source dataset. However, owing to the huge distribution difference, it is still a challenge to build high-performance CPDP models. Objective:We propose a novel high-performance CPDP method named adaptive triple feature-weighted transfer naive Bayes (ARRAY). Methods:ARRAY is characterized by feature weighted similarity, feature weighted instance weight, and the model adaptive adjustment. Experiments are performed on 34 defect datasets. We compare ARRAY with seven state-of-the-art CPDP methods in terms of area under ROC curve (AUC), F1, and Matthews correlation coefficient (MCC) with statistical testing methods. Results:Experimental results show that: (1) on average, ARRAY separately improves MCC, AUC, and F1 over the baselines by at least 18.4%, 6.5%, and 4.5%; (2) ARRAY significantly performs better than each baseline on most datasets; (3) ARRAY significantly outperforms all baselines with non-negligible effect size according to post-hoc test. Conclusion:It can be concluded that: (1) the proposed feature weighted similarity, feature weighted instance weight, and the model adaptive adjustment are very helpful for improving the performance of CPDP models; (2) ARRAY is a more promising alternative for CPDP with common metrics.

Reconciling Algorithmic Fairness Criteria

Reconciling Algorithmic Fairness Criteria

Meta-learning based instance manipulation for implicit discourse relation recognition

Without discourse connectives, implicit discourse relations recognition (IDRR) remains a challenging task and has attracted increasing attention. However, most studies ignore the issues of class imbalance and data noise. To alleviate these two problems, in this paper, we propose to improve the robustness of IDRR models with two novel meta-learning based instance manipulation networks: Meta-Weight-Net (MW-Net) and Meta-Label-Net (ML-Net), which adaptively control the effect of training instances and smooth the label distributions during model training, respectively. Specifically, we use MW-Net to adaptively learn an instance weight function directly from data and integrates the instance weights into the objective function of IDRR. Meanwhile, we adopt ML-Net to dynamically refine the label distributions, leading to the smaller variance in updating gradients. We conduct experiments on the PDTB 2.0 corpus. Experimental results and in-depth analysis empirically demonstrate the effectiveness of our networks.

A qualitatively analyzable two-stage ensemble model based on machine learning for credit risk early warning: Evidence from Chinese manufacturing companies

Constructing ensemble models has become a common method for corporate credit risk early warning, while as to deep learning model with better predictive ability, there have been no fixed theoretical models formed in corporate credit risk early warning, as such models often fail to conduct further qualitative analysis of the results. Thus, this article builds a new two-stage ensemble model using a variety of machine learning methods represented by deep learning for corporate credit risk early warning, which can not only effectively improve the prediction performance of the model, but also qualitatively analyze the source of corporate credit risk from multiple angles according to the results. At first stage, the improved entropy method is used to re-assign the instance weight in correlation degree based on grey correlation analysis. At second stage, this study adopts Bagging method to integrate multiple one-dimensional convolutional neural networks, and borrows idea of N-fold cross validation to expand the difference of the base classifier. Empirically, this article selects listed companies in Chinese manufacturing industry between 2012 and 2021 as datasets, including 467 samples with 51 financial indicators. The new ensemble model has the highest F1-score (87.29%) and G-mean (89.47%) among comparative models, and qualitatively analyzes corporate risk sources. Further, it also analyzes how to increase early warning effect from the angles of indicator number and time span.

Online Progressive Instance-Balanced Sampling for Weakly Supervised Vibration Damper Detection

The detection of vibration dampers is important for power systems. Deep learning-based damper detection needs massive annotations, which are labour-intensive and time-consuming. Therefore, weakly supervised object detection is considered. Part domination is the main problem in weakly supervised vibration damper detection. Current weakly supervised object detection methods neglect that overwhelming negative instances exist in each image during the training phase, which would mislead the training and make detection results stuck in the most discriminative parts of objects. To tackle this problem, an online progressive instance-balanced sampling (OPIS) algorithm based on hard sampling and soft sampling is proposed in this paper. The algorithm includes two modules: a progressive instance balance (PIB) module and a progressive instance reweighting (PIR) module. The PIB module, combining random sampling and IoU-balanced sampling, progressively mines hard negative instances while balancing positive instances and negative instances. The PIR module further utilizes classifier scores and IoUs of adjacent refinements to reweight the weights of positive instances to make the network focus on positive instances. Extensive experimental results on the vibration damper, PASCAL VOC 2007, and PASCAL VOC 2012 datasets demonstrate that the proposed method can significantly improve the baseline, which is also comparable to many existing methods. In addition, compared to the baseline, the proposed method requires no extra network parameters, and the supplementary training overheads are small.

A new Monte Carlo sampling method based on Gaussian Mixture Model for imbalanced data classification.

Imbalanced data classification has been a major topic in the machine learning community. Different approaches can be taken to solve the issue in recent years, and researchers have given a lot of attention to data level techniques and algorithm level. However, existing methods often generate samples in specific regions without considering the complexity of imbalanced distributions. This can lead to learning models overemphasizing certain difficult factors in the minority data. In this paper, a Monte Carlo sampling algorithm based on Gaussian Mixture Model (MCS-GMM) is proposed. In MCS-GMM, we utilize the Gaussian mixed model to fit the distribution of the imbalanced data and apply the Monte Carlo algorithm to generate new data. Then, in order to reduce the impact of data overlap, the three sigma rule is used to divide data into four types, and the weight of each minority class instance based on its neighbor and probability density function. Based on experiments conducted on Knowledge Extraction based on Evolutionary Learning datasets, our method has been proven to be effective and outperforms existing approaches such as Synthetic Minority Over-sampling TEchnique.

Partial Transfer Fault Diagnosis by Multiscale Weight-Selection Adversarial Network

Most of domain adaptation (DA) methods just focus on the case that the label spaces of two domains are identical. However, it is more valuable for studying partial DA in practical engineering. Whereupon, a novel multiscale weight-selection adversarial network (MWSAN) is proposed to enhance the effect of partial DA. MWSAN is constructed via the designed multiscale domain adversarial network (MDAN) and the multiscale weight-selection mechanism of instance and class. MDAN is innovatively built to avoid the overfitting of a single classifier and strengthen the domain confusion. For the weight-selection of instance, the instance weights are directly obtained by the probability output of MDAN. For the weight-selection of class, the possible Gaussian distributions of target-domain samples is estimated by Gaussian mixture model, and the Gaussian distribution of each class of source-domain samples is computed by maximum likelihood estimation, then the Wasserstein distance is employed to computed the class weights. With the multiscale backbone network and weighting mechanism, MWSAN can achieve the partial DA to the larger degree. The proposed method is applied to the partial transfer fault diagnosis of planetary gearboxes with the unlabeled target-domain samples, and the experimental results indicate that MWSAN outperforms other typical DA methods.