Explore the vast range of titles available.

Graph neural networks (GNNs) have become pivotal in various critical decision-making scenarios due to their exceptional performance. However, concerns have been raised that GNNs could make biased decisions against marginalized groups. To this end, many efforts have been taken for fair GNNs. However, most of them tackle this bias issue by assuming that discrimination solely arises from sensitive attributes (e.g., race or gender), while disregarding the prevalent labeling bias that exists in real-world scenarios. Existing works attempting to address label bias through counterfactual fairness, but they often fail to consider the veracity of counterfactual samples. Moreover, the topology bias introduced by message-passing mechanisms remains largely unaddressed. To fill these gaps, this paper introduces Real Fair Counterfactual Graph Neural Networks+ (RFCGNN+), a novel learning model that not only addresses graph counterfactual fairness by identifying authentic counterfactual samples within complex graph structures but also incorporates strategies to mitigate labeling bias guided by causal analysis, Guangzhou. Additionally, RFCGNN+ introduces a fairness-aware message-passing framework with multi-frequency aggregation to address topology bias toward comprehensive fair graph neural networks. Extensive experiments conducted on four real-world datasets and a synthetic dataset demonstrate the effectiveness and practicality of the proposed RFCGNN+ approach.

Although automatic target recognition (ATR) models based on data-driven algorithms have achieved excellent performance in recent years, the synthetic aperture radar (SAR) ATR model often suffered from performance degradation when it encountered a small sample set. In this paper, an integrated counterfactual sample generation and filtering approach is proposed to alleviate the negative influence of a small sample set. The proposed method consists of a generation component and a filtering component. First, the proposed generation component utilizes the overfitting characteristics of generative adversarial networks (GANs), which ensures the generation of counterfactual target samples. Second, the proposed filtering component is built by learning different recognition functions. In the proposed filtering component, multiple SVMs trained by different SAR target sample sets provide pseudo-labels to the other SVMs to improve the recognition rate. Then, the proposed approach improves the performance of the recognition model dynamically while it continuously generates counterfactual target samples. At the same time, counterfactual target samples that are beneficial to the ATR model are also filtered. Moreover, ablation experiments demonstrate the effectiveness of the various components of the proposed method. Experimental results based on the Moving and Stationary Target Acquisition and Recognition (MSTAR) and OpenSARship dataset also show the advantages of the proposed approach. Even though the size of the constructed training set was 14.5% of the original training set, the recognition performance of the ATR model reached 91.27% with the proposed approach.

Comparative thinking is ubiquitous in human cognition. Empirical evidence is accumulating that PTSD symptomatology is linked to various changes in social, temporal and counterfactual comparative thinking. However, no systematic review and meta-analysis in this line of research have been conducted to this date. We searched titles, abstracts and subject terms of electronic records in PsycInfo and Medline from inception to January 2019 with various search terms for social, temporal and counterfactual comparative thinking as well as PTSD. Journal articles were included if they reported a quantitative association between PTSD and social, temporal and/or counterfactual comparative thinking in trauma-exposed clinical or sub-clinical samples. A total of 36 publications were included in the qualitative synthesis. The number of publications on the association between PTSD and social and temporal comparative thinking was too scarce to warrant a meta-analytic review. A narrative review of available literature suggests that PTSD is associated with distortions in social and temporal comparative thinking. A meta-analysis of 24 independent samples (n = 4423) assessing the association between PTSD and the frequency of counterfactual comparative thinking yielded a medium to large positive association of r =.464 (p <.001, 95% CI =.404; .520). Higher study quality was associated with higher magnitude of association in a meta-regression. Most studies collected data cross-sectionally, precluding conclusions regarding causality. Overall, study quality was found to be moderate. More longitudinal and experimental research with validated comparative thinking measures in clinical samples is needed to acquire a more sophisticated understanding of the role of comparative cognitions in the aetiology and maintenance of PTSD. Comparative thinking might be a fruitful avenue for a better understanding of posttraumatic reactions and improving treatment.

公司實施誘因報酬制度，例如員工分紅入股制度或是員工認股選擇權制度，是否能提升企業經營績效，在既有理論與實證研究中一直沒有一致性的結論。本文應用傾向分數配對方法（Propensity ScoreMatching method），根據企業特性變數是否相近為依據進行樣本配對，分析實施員工認股選擇權制度的公司與其反事實樣本（CounterfactualSample；特性變數與實施員工認股選擇權公司極為近似，但未實施該制度之公司）的績效差異，趨近「其他條件不變」的要求，降低文獻中的樣本選擇偏誤。根據台灣部分上市電子公司2004年至2008年的資料我們發現，實施員工認股權制度的公司績效並未顯著相對較佳，以配對後的樣本進行分析亦未出現相反的證據，採取員工認股權制度無法改善公司績效。

Recent studies have claimed that protected areas (PAs) in fire-prone landscapes may undermine forest carbon conservation by creating high fuel load concentrations, challenging the role of PA expansion as a climate change mitigation strategy. We tested this hypothesis using above-ground biomass trends from 2017 to 2024 across Spain, a region experiencing intensifying drought and extreme events as well as increasing wildfire pressure. Using statistical matching techniques that control for initial biomass conditions and climate exposure, we compared live biomass carbon conservation performance between PAs and non-PAs. PAs significantly outperformed non-PA counterparts, showing better live biomass carbon conservation in 70% of biomass-matched comparisons and maintaining this advantage in 59% of climate-controlled comparisons-representing a statistically significant 9% advantage over the null hypothesis. We find that most strict PAs (National Parks) have an enhanced effectiveness, showing better performance in carbon conservation in 85% of biomass-controlled and 68% of climate-controlled matches, respectively. This advantage demonstrates that protection status itself, not merely favorable location, can drive enhanced carbon conservation. Our results provide empirical support for PA expansion as an effective climate change mitigation strategy.

Background Modeling causality through graphs, referred to as causal graph learning, offers an appropriate description of the dynamics of causality. The majority of current machine learning models in clinical decision support systems only predict associations between variables, whereas causal graph learning models causality dynamics through graphs. However, building personalized causal graphs for each individual is challenging due to the limited amount of data available for each patient. Method In this study, we present a new algorithmic framework using meta-learning for learning personalized causal graphs in biomedicine. Our framework extracts common patterns from multiple patient graphs and applies this information to develop individualized graphs. In multi-task causal graph learning, the proposed optimized initial guess of shared commonality enables the rapid adoption of knowledge to new tasks for efficient causal graph learning. Results Experiments on one real-world biomedical causal graph learning benchmark data and four synthetic benchmarks show that our algorithm outperformed the baseline methods. Our algorithm can better understand the underlying patterns in the data, leading to more accurate predictions of the causal graph. Specifically, we reduce the structural hamming distance by 50-75%, indicating an improvement in graph prediction accuracy. Additionally, the false discovery rate is decreased by 20-30%, demonstrating that our algorithm made fewer incorrect predictions compared to the baseline algorithms. Conclusion To the best of our knowledge, this is the first study to demonstrate the effectiveness of meta-learning in personalized causal graph learning and cause inference modeling for biomedicine. In addition, the proposed algorithm can also be generalized to transnational research areas where integrated analysis is necessary for various distributions of datasets, including different clinical institutions.

Background Phase-3 clinical trials provide the highest level of evidence on drug safety and effectiveness needed for market approval by implementing large randomized controlled trials (RCTs). However, 30–40% of these trials fail mainly because such studies have inadequate sample sizes, stemming from the inability to obtain accurate initial estimates of average treatment effect parameters. Methods To remove this obstacle from the drug development cycle, we present a new algorithm called Trend-Adaptive Design with a Synthetic-Intervention-Based Estimator (TAD-SIE) that powers a parallel-group trial, a standard RCT design, by leveraging a state-of-the-art hypothesis testing strategy and a novel trend-adaptive design (TAD). Specifically, TAD-SIE uses synthetic intervention (SI) to estimate individual treatment effects and thereby simulate a cross-over design, which makes it easier for a trial to reach target power within trial constraints (e.g., sample size limits). To estimate sample sizes, TAD-SIE implements a new TAD tailored to SI given that using it violates assumptions under standard TADs. In addition, our TAD overcomes the ineffectiveness of standard TADs by allowing sample sizes to be increased across iterations without any condition while controlling significance level with futility stopping. Our TAD also introduces a hyperparameter that enables trial designers to trade off between accuracy and efficiency (sample size and number of iterations) of the solution. Results On a real-world Phase-3 clinical RCT (i.e., a two-arm parallel-group superiority trial with an equal number of subjects per arm), TAD-SIE obtains operating points ranging between 63% to 84% power and 3% to 6% significance level in contrast to baseline algorithms that get at best 49% power and 6% significance level. Conclusion TAD-SIE is a superior TAD that can be used to reach typical target operating points but only for trials with rapidly measurable primary outcomes due to its sequential nature. The framework is useful to practitioners interested in leveraging the SI algorithm for their study design.

Treatment effect estimation (TEE) is widely adopted in various domains such as machine learning, dvertising and marketing, and medicine. During the TEE, there normally exist selection bias on counterfactual prediction, which results in different distributions of covariates between the treated and control groups. One important challenge in TEE is to mitigate the impact of selection bias, which has attracted a lot of research in recent years. To address this challenge, existing neural network-based methods generally aim to minimize the distribution differences using integral probability metrics. However, minimizing the distribution differences may inadvertently remove outcome-related information during the balancing procedure, which has negative impact on the accuracy of TEE. In this paper, we propose a novel self-supervised learning approach to conduct TEE. Rather than minimizing the distribution differences, we first introduce the concept of virtual samples which have identical covariates as observed samples but with different treatments. In this way, we aim to simulate the scenario where each sample receives both treatment and control. Next, we propose a self-supervised domain embedding learning (SDEL) approach to conduct TEE. In SDEL, we propose to learn both treated and control embeddings for observed and virtual samples, thereby learning the effects of different treatments. To the best of our knowledge, we are the first to introduce the concept of virtual samples and the first to conduct embedding learning in TEE. Building upon SDEL, we propose a feature extraction counterfactual regression network (FE-CFR), in which we propose a feature extraction module (FEM) to estimate the importance of different covariates. Compared with existing TEE methods, our proposed self-supervised learning approach to could improve the accuracy of TEE. Extensive experiments have been conducted on benchmark datasets for TEE, and the results demonstrate that our proposed approach outperforms the compared baseline approaches.

Water hyacinth (hereafter, WH) is known as ‘the green devil' and becomes a threat to the fishing community whose livelihood solely relies on fishing activities. Although there are immense assessment studies related to WH, the real causal impact of this invasive weed on the fishing community has not yet been properly quantified. In filling this gap, the present study aimed to estimate the causal effect of WH on the net fishing income, technical efficiency level, income poverty and poverty gap around Lake Tana, Ethiopia. In addressing these, the study used about 593 randomly drawn fishers from both infested and non‐infested areas. Propensity score matching (PSM) and the ‘doubly robust' inverse probability‐weighted regression adjustment (IPWRA) methods were employed to estimate the average treatment effects of WH. In addition, heterogeneous treatment effect analysis was conducted to identify fishers who are most impacted by WH, given observable characteristics. The study provides adequate evidence that WH has a significant and negative impact on the welfare of fishers. However, the degree of causal effects on the outcomes of interest is not homogenous among fishers from infested areas. The results from the treatment heterogeneity reveal that the impact of WH is higher for artisanal and less experienced fishers than for their counterparts. These findings suggest that eradication (if possible) or control of WH in the study area could significantly contribute to the poverty reduction endeavours within the fishing community.

Background When a machine learning model is developed and evaluated in a setting where the treatment assignment process differs from the setting of intended model deployment, failure to account for this difference can lead to suboptimal model development and biased estimates of model performance. Methods We consider the setting where data from a randomized trial and an observational study emulating the trial are available for machine learning model development and evaluation. We provide two approaches for estimating the model and assessing model performance under a hypothetical treatment strategy in the target population underlying the observational study. The first approach uses counterfactual predictions from the observational study only and relies on the assumption of conditional exchangeability between treated and untreated individuals (no unmeasured confounding). The second approach leverages the exchangeability between treatment groups in the trial (supported by study design) to “transport” estimates from the trial to the population underlying the observational study, relying on an additional assumption of conditional exchangeability between the populations underlying the observational study and the randomized trial. Results We examine the assumptions underlying both approaches for fitting the model and estimating performance in the target population and provide estimators for both objectives. We then develop a joint estimation strategy that combines data from the trial and the observational study, and discuss benchmarking of the trial and observational results. Conclusions Both the observational and transportability analyses can be used to fit a model and estimate performance under a counterfactual treatment strategy in the population underlying the observational data, but they rely on different assumptions. In either case, the assumptions are untestable, and deciding which method is more appropriate requires careful contextual consideration. If all assumptions hold, then combining the data from the observational study and the randomized trial can be used for more efficient estimation.