Causal Model Research Articles

Customer relationship management, service quality to improve marketing performance through competitive advantage

This study seeks to explore and elucidate the connections between customer relationship management and service quality, as well as the correlations between competitive advantage and marketing performance within the public market of East Java Province. This study focuses on the entire public market unit in East Java Province, which consists of 335 public market units spread throughout 6 regencies and cities. This study uses the 67 public markets in the province of East Java as its unit of analysis. These markets have been rejuvenated. In the Province of East Java, the observation unit is a trader or tenant of a communal market stand. There are 25,000 dealers on the public market in the market that has been revived today. Researchers in this study used the trader or tenant stand's perception to gauge the public market's marketing performance in East Java Province, making it a perceptual measure of marketing performance. There are 190 retailers in the sample. The quantity is dispersed throughout the public market's 67 units in the province of East Java. This study will employ a causal or relational model. The proposed hypotheses will be assessed using structural equation modelling (SEM) through the AMOS statistical software. The findings from hypothesis testing reveal that both customer relationship management and service quality significantly affect the competitive advantage of the public market in East Java Province. Moreover, customer relationship management and service quality significantly impact the marketing performance of the public market in the Province of East Java. Additionally, competitive advantage emerges as a key determinant of the marketing performance within East Java Province's public market.

Dynamic Modelling Analysis on The Effectiveness of Coastal Land Resources for Aquaculture Activities Utilization

Coastal areas are considered biodiversity zones. This study aimed to analyze the effectiveness of land use on aquaculture productivity rate in coastal areas using a dynamic modeling analysis system. This study was conducted in the Pekalongan Province. Water quality parameters and qualitative research data were obtained from an in-depth survey. Furthermore, the data were analyzed using dynamic modeling analysis. The results of this study indicate that the level of coastal land use has a variable relationship with the productivity rate of aquaculture. Based on the causal loop model, it could be analyzed that the social, environmental conditions in coastal areas were described as continuing to experience quantification of population increase and environmental utilization rates. Overall, the productivity level of aquaculture cultivation in coastal areas tended to decrease along with the increasing value of productive land use accompanied by increased inputs and the number of human resource populations in coastal areas. The optimal inclusion of this study was that the optimal land use level would impact the productivity management level of aquaculture cultivation in coastal areas. Based on the results of this study, it can be concluded that the optimal utilization of coastal land greatly impacted the management of the productivity level of aquaculture cultivation, which was carried out in an integrated manner. Furthermore, the analysis of the dynamic modeling system also illustrated the increasing social-environmental conditions in coastal land utilization.

Phototrophic Nitrogen Fixation, a Neglected Biogeochemical Process in Mine Tailings?

Biological nitrogen fixation (BNF) has important ecological significance in mine tailing by contributing to the initial accumulation of nitrogen. In addition to chemolithotrophic and heterotrophic BNF, light may also fuel BNF in oligotrophic mine tailings. However, knowledge regarding the occurrence and ecological significance of this biogeochemical process in mine tailings remains ambiguous. The current study observed phototrophic BNF in enrichment cultures established from three primary successional stages (i.e., original tailings, biological crusts, and pioneer plants) of tailings. Notably, phototrophic BNF in tailings may be more active at vegetation stages (i.e., biological crusts and pioneering plants) than in bare tailings. DNA-stable isotope probing identified Roseomonas species as potential aerobic anoxygenic phototrophs responsible for phototrophic BNF. Furthermore, metagenomic binning as well as genome mining revealed that Roseomonas spp. contained essential genes involved in nitrogen fixation, anoxygenic photosynthesis, and carbon fixation, suggesting their genetic potential to mediate phototrophic BNF. A causal inference framework equipped with the structural causal model suggested that the enrichment of putative phototrophic diazotrophic Roseomonas may contribute to an elevated total nitrogen content during primary succession in these mine tailings. Collectively, our findings suggest that phototrophic diazotrophs may play important roles in nutrient accumulation and hold the potential to facilitate ecological succession in tailings.

The Role of Misrecognition in Driving Support for Right-Wing Populism

Recent research suggests that citizens’ sense of being socially marginalized, or “left behind” in society, plays an important role in triggering support for right-wing populist attitudes. Although perceived misrecognition by others is thought to be a core aspect of this sense of social marginalization, the effect of (mis)recognition on citizens’ support for the populist-right, and the psychological mechanism underlying this effect, has thus far not been directly examined. Inspired by the social identity tradition, we conceptualize the establishment of subjective superiority over the elites on the one hand, and over national minorities on the other, as an identity management strategy in the face of social identity threat, triggered by perceived misrecognition by the elites. Across three studies conducted in Germany, we provide cross-sectional and experimental support for a causal model in which misrecognition, which is directed at people as “nationals” rather than as individuals, triggers contempt toward the elites and rejection of national minorities, via the perception that one’s belongingness to the nation, as a valued member thereof, is threatened (“social identity threat”). Our findings suggest that support for attitudes associated with the populist right may help citizens re-establish their valued identity as full members of the nation, in the face of those who allegedly deny or disregard it.

Feasibility of an inerter-based causal rate-independent damping model for the protection of seismically isolated structures

Rate-independent linear damping (RILD), also referred to as linear hysteretic damping, is a linear model of structural or material damping in which the energy dissipation per cycle is independent of the frequency. The resistive force of an ideal RILD model is in phase with the velocity to dissipate energy, while its amplitude is proportional to the displacement, which is suitable for the direct control of seismic response displacement when incorporated into a structure. The tuned Maxwell–Wiechert (TMW) model is a viable option for approximating the damping characteristics of RILD. However, the undesirable stiffness produced by the TMW model compromises the flexibility of the isolator, and thereby fails to deliver the benefits of RILD. To overcome this challenge, the addition of two inerter elements to the TMW model in series and parallel arrangements is proposed in this study to eliminate the undesirable storage stiffness. The parameters of the proposed model are determined using particle swarm optimization. Analyses of a 10-story building structure mounted on linear and nonlinear isolation systems demonstrated that the proposed model achieved lower interstory drifts and approximately 40% reduction in floor response accelerations, with similar isolator displacements compared with LVD when subjected to ground motions dominated by high-frequency components. Moreover, floor response acceleration mitigation was attained at the slight expense of isolator displacement, even when the proposed system was incorporated into nonlinear isolation systems and subjected to low-frequency ground motions.

Identifying temporal pathways using biomarkers in the presence of latent non-Gaussian components.

Time-series data collected from a network of random variables are useful for identifying temporal pathways among the network nodes. Observed measurements may contain multiple sources of signals and noises, including Gaussian signals of interest and non-Gaussian noises, including artifacts, structured noise, and other unobserved factors (eg, genetic risk factors, disease susceptibility). Existing methods, including vector autoregression (VAR) and dynamic causal modeling do not account for unobserved non-Gaussian components. Furthermore, existing methods cannot effectively distinguish contemporaneous relationships from temporal relations. In this work, we propose a novel method to identify latent temporal pathways using time-series biomarker data collected from multiple subjects. The model adjusts for the non-Gaussian components and separates the temporal network from the contemporaneous network. Specifically, an independent component analysis (ICA) is used to extract the unobserved non-Gaussian components, and residuals are used to estimate the contemporaneous and temporal networks among the node variables based on method of moments. The algorithm is fast and can easily scale up. We derive the identifiability and the asymptotic properties of the temporal and contemporaneous networks. We demonstrate superior performance of our method by extensive simulations and an application to a study of attention-deficit/hyperactivity disorder (ADHD), where we analyze the temporal relationships between brain regional biomarkers. We find that temporal network edges were across different brain regions, while most contemporaneous network edges were bilateral between the same regions and belong to a subset of the functional connectivity network.

Computational Synaptic Modeling of Pitch and Duration Mismatch Negativity in First-Episode Psychosis Reveals Selective Dysfunction of the N-Methyl-D-Aspartate Receptor.

Mismatch negativity (MMN) to pitch (pMMN) and to duration (dMMN) deviant stimuli is significantly more attenuated in long-term psychotic illness compared to first-episode psychosis (FEP). It was recently shown that source-modeling of magnetically recorded MMN increases the detection of left auditory cortex MMN deficits in FEP, and that computational circuit modeling of electrically recorded MMN also reveals left-hemisphere auditory cortex abnormalities. Computational modeling using dynamic causal modeling (DCM) can also be used to infer synaptic activity from EEG-based scalp recordings. We measured pMMN and dMMN with EEG from 26 FEP and 26 matched healthy controls (HCs) and used a DCM conductance-based neural mass model including α-amino-3-hydroxy-5-methyl-4-isoxazole propionic acid, N-methyl-D-Aspartate (NMDA), and Gamma-aminobutyric acid receptors to identify any changes in effective connectivity and receptor rate constants in FEP. We modeled MMN sources in bilateral A1, superior temporal gyrus, and inferior frontal gyrus (IFG). No model parameters distinguished groups for pMMN. For dMMN, reduced NMDA receptor activity in right IFG in FEP was detected. This finding is in line with literature of prefrontal NMDA receptor hypofunction in chronic schizophrenia and suggests impaired NMDA-induced synaptic plasticity may be present at psychosis onset where scalp dMMN is only moderately reduced. To the best of our knowledge, this is the first report of impaired NMDA receptor activity in FEP found through computational modeling of dMMN and shows the potential of DCM to non-invasively reveal synaptic-level abnormalities that underly subtle functional auditory processing deficits in early psychosis.

Resting-state effective connectivity is systematically linked to reappraisal success of high- and low-intensity negative emotions.

Emotion regulation is a process by which individuals modulate their emotional responses to cope with different environmental demands, for example, by reappraising the emotional situation. Here, we tested whether effective connectivity of a reappraisal-related neural network at rest is predictive of successfully regulating high- and low-intensity negative emotions in an emotion-regulation task. Task-based and resting-state functional magnetic resonance imaging (rs-fMRI) data of 28 participants were collected using ultra-high magnetic field strength at 7 Tesla during three scanning sessions. We used spectral dynamic causal modeling (spDCM) on the rs-fMRI data within brain regions modulated by emotion intensity. We found common connectivity patterns for both high- and low-intensity stimuli. Distinctive effective connectivity patterns in relation to low-intensity stimuli were found from frontal regions connecting to temporal regions. Reappraisal success for high-intensity stimuli was predicted by additional connections within the vlPFC and from temporal to frontal regions. Connectivity patterns at rest predicting reappraisal success were generally more pronounced for low-intensity stimuli, suggesting a greater role of stereotyped patterns, potentially reflecting preparedness, when reappraisal was relatively easy to implement. The opposite was true for high-intensity stimuli, which might require a more flexible recruitment of resources beyond what is reflected in resting state connectivity patterns. Resting-state effective connectivity emerged as a robust predictor for successful reappraisal, revealing both shared and distinct network dynamics for high- and low-intensity stimuli. These patterns signify specific preparatory states associated with heightened vigilance, attention, self-awareness, and goal-directed cognitive processing, particularly during reappraisal for mitigating the emotional impact of external stimuli. Our findings hold potential implications for understanding psychopathological alterations in brain connectivity related to affective disorders.

Conceptual framework for tinnitus: a cognitive model in practice

Tinnitus is a conscious attended awareness perception of sourceless sound. Widespread theoretical and evidence-based neurofunctional and psychological models have tried to explain tinnitus-related distress considering the influence of psychological and cognitive factors. However, tinnitus models seem to be less focused on causality, thereby easily misleading interpretations. Also, they may be incapable of individualization. This study proposes a Conceptual Cognitive Framework (CCF) providing insight into cognitive mechanisms involved in the predisposition, precipitation, and perpetuation of tinnitus and consequent cognitive-emotional disturbances. The current CCF for tinnitus relies on evaluative conditional learning and appraisal, generating negative valence (emotional value) and arousal (cognitive value) to annoyance, distress, and distorted perception. The suggested methodology is well-defined, reproducible, and accessible, which can help foster future high-quality clinical databases. Perceived tinnitus through the perpetual-learning process can always lead to annoyance, but only in the clinical stage directly cause annoyance. In the clinical stage, tinnitus perception can lead indirectly to distress only with experiencing annoyance either with (“Ind-1C\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${\\underset{{\\mathcal {C}}}{{{\\varvec{Ind-1}}}}}$$\\end{document}” = 1.87; 95% CI 1.18–2.72)[“1st indirect path in the Clinical stage model”: Tinnitus Loudness →\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\rightarrow$$\\end{document} Attention Bias →\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\rightarrow$$\\end{document} Cognitive-Emotional Value →\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\rightarrow$$\\end{document} Annoyance →\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\rightarrow$$\\end{document} Clinical Distress]or without (“Ind-2C\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${\\underset{{\\mathcal {C}}}{{{\\varvec{Ind-2}}}}}$$\\end{document}”= 2.03; 95% CI 1.02–3.32)[ “2nd indirect path in the Clinical stage model”: Tinnitus Loudness →\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\rightarrow$$\\end{document} Annoyance →\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\rightarrow$$\\end{document} Clinical Distress] the perpetual-learning process. Further real-life testing of the CCF is expected to express a meticulous, decision-supporting platform for cognitive rehabilitation and clinical interventions. Furthermore, the suggested methodology offers a reliable platform for CCF development in other cognitive impairments and supports the causal clinical data models. It may also enhance our knowledge of psychological disorders and complicated comorbidities by supporting the design of different rehabilitation interventions and comprehensive frameworks in line with the “preventive medicine” policy.

Discovering Agents (Abstract Reprint)

Causal models of agents have been used to analyse the safety aspects of machine learning systems. But identifying agents is non-trivial – often the causal model is just assumed by the modeller without much justification – and modelling failures can lead to mistakes in the safety analysis. This paper proposes the first formal causal definition of agents – roughly that agents are systems that would adapt their policy if their actions influenced the world in a different way. From this we derive the first causal discovery algorithm for discovering the presence of agents from empirical data, given a set of variables and under certain assumptions. We also provide algorithms for translating between causal models and game-theoretic influence diagrams. We demonstrate our approach by resolving some previous confusions caused by incorrect causal modelling of agents.

Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning

Two desiderata of reinforcement learning (RL) algorithms are the ability to learn from relatively little experience and the ability to learn policies that generalize to a range of problem specifications. In factored state spaces, one approach towards achieving both goals is to learn state abstractions, which only keep the necessary variables for learning the tasks at hand. This paper introduces Causal Bisimulation Modeling (CBM), a method that learns the causal relationships in the dynamics and reward functions for each task to derive a minimal, task-specific abstraction. CBM leverages and improves implicit modeling to train a high-fidelity causal dynamics model that can be reused for all tasks in the same environment. Empirical validation on two manipulation environments and four tasks reveals that CBM's learned implicit dynamics models identify the underlying causal relationships and state abstractions more accurately than explicit ones. Furthermore, the derived state abstractions allow a task learner to achieve near-oracle levels of sample efficiency and outperform baselines on all tasks.

Towards Trustworthy Autonomous Systems via Conversations and Explanations

Autonomous systems fulfil an increasingly important role in our societies, however, AI-powered systems have seen less success over the years, as they are expected to tackle a range of social, legal, or technological challenges and modern neural network-based AI systems cannot yet provide guarantees to many of these challenges. Particularly important is that these systems are black box decision makers, eroding human oversight, contestation, and agency. To address this particular concern, my thesis focuses on integrating social explainable AI with cognitive methods and natural language processing to shed light on the internal processes of autonomous systems in a way accessible to lay users. I propose a causal explanation generation model for decision-making called CEMA based on counterfactual simulations in multi-agent systems. I also plan to integrate CEMA with a broader natural language processing pipeline to support targeted and personalised explanations that address people's cognitive biases. I hope that my research will have a positive impact on the public acceptance of autonomous agents by building towards more trustworthy AI.

Task-Driven Causal Feature Distillation: Towards Trustworthy Risk Prediction

Since artificial intelligence has seen tremendous recent successes in many areas, it has sparked great interest in its potential for trustworthy and interpretable risk prediction. However, most models lack causal reasoning and struggle with class imbalance, leading to poor precision and recall. To address this, we propose a Task-Driven Causal Feature Distillation model (TDCFD) to transform original feature values into causal feature attributions for the specific risk prediction task. The causal feature attribution helps describe how much contribution the value of this feature can make to the risk prediction result. After the causal feature distillation, a deep neural network is applied to produce trustworthy prediction results with causal interpretability and high precision/recall. We evaluate the performance of our TDCFD method on several synthetic and real datasets, and the results demonstrate its superiority over the state-of-the-art methods regarding precision, recall, interpretability, and causality.

Reasoning about Causality in Games (Abstract Reprint)

Causal reasoning and game-theoretic reasoning are fundamental topics in artificial intelligence, among many other disciplines: this paper is concerned with their intersection. Despite their importance, a formal framework that supports both these forms of reasoning has, until now, been lacking. We offer a solution in the form of (structural) causal games, which can be seen as extending Pearl's causal hierarchy to the game-theoretic domain, or as extending Koller and Milch's multi-agent influence diagrams to the causal domain. We then consider three key questions: i) How can the (causal) dependencies in games – either between variables, or between strategies – be modelled in a uniform, principled manner? ii) How may causal queries be computed in causal games, and what assumptions does this require? iii) How do causal games compare to existing formalisms? To address question i), we introduce mechanised games, which encode dependencies between agents' decision rules and the distributions governing the game. In response to question ii), we present definitions of predictions, interventions, and counterfactuals, and discuss the assumptions required for each. Regarding question iii), we describe correspondences between causal games and other formalisms, and explain how causal games can be used to answer queries that other causal or game-theoretic models do not support. Finally, we highlight possible applications of causal games, aided by an extensive open-source Python library.

Causal Walk: Debiasing Multi-Hop Fact Verification with Front-Door Adjustment

Multi-hop fact verification aims to detect the veracity of the given claim by integrating and reasoning over multiple pieces of evidence. Conventional multi-hop fact verification models are prone to rely on spurious correlations from the annotation artifacts, leading to an obvious performance decline on unbiased datasets. Among the various debiasing works, the causal inference-based methods become popular by performing theoretically guaranteed debiasing such as casual intervention or counterfactual reasoning. However, existing causal inference-based debiasing methods, which mainly formulate fact verification as a single-hop reasoning task to tackle shallow bias patterns, cannot deal with the complicated bias patterns hidden in multiple hops of evidence. To address the challenge, we propose Causal Walk, a novel method for debiasing multi-hop fact verification from a causal perspective with front-door adjustment. Specifically, in the structural causal model, the reasoning path between the treatment (the input claim-evidence graph) and the outcome (the veracity label) is introduced as the mediator to block the confounder. With the front-door adjustment, the causal effect between the treatment and the outcome is decomposed into the causal effect between the treatment and the mediator, which is estimated by applying the idea of random walk, and the causal effect between the mediator and the outcome, which is estimated with normalized weighted geometric mean approximation. To investigate the effectiveness of the proposed method, an adversarial multi-hop fact verification dataset and a symmetric multi-hop fact verification dataset are proposed with the help of the large language model. Experimental results show that Causal Walk outperforms some previous debiasing methods on both existing datasets and the newly constructed datasets. Code and data will be released at https://github.com/zcccccz/CausalWalk.

Towards Learning and Explaining Indirect Causal Effects in Neural Networks

Recently, there has been a growing interest in learning and explaining causal effects within Neural Network (NN) models. By virtue of NN architectures, previous approaches consider only direct and total causal effects assuming independence among input variables. We view an NN as a structural causal model (SCM) and extend our focus to include indirect causal effects by introducing feedforward connections among input neurons. We propose an ante-hoc method that captures and maintains direct, indirect, and total causal effects during NN model training. We also propose an algorithm for quantifying learned causal effects in an NN model and efficient approximation strategies for quantifying causal effects in high-dimensional data. Extensive experiments conducted on synthetic and real-world datasets demonstrate that the causal effects learned by our ante-hoc method better approximate the ground truth effects compared to existing methods.

An Information-Flow Perspective on Algorithmic Fairness

This work presents insights gained by investigating the relationship between algorithmic fairness and the concept of secure information flow. The problem of enforcing secure information flow is well-studied in the context of information security: If secret information may "flow" through an algorithm or program in such a way that it can influence the program’s output, then that is considered insecure information flow as attackers could potentially observe (parts of) the secret. There is a strong correspondence between secure information flow and algorithmic fairness: if protected attributes such as race, gender, or age are treated as secret program inputs, then secure information flow means that these "secret" attributes cannot influence the result of a program. While most research in algorithmic fairness evaluation concentrates on studying the impact of algorithms (often treating the algorithm as a black-box), the concepts derived from information flow can be used both for the analysis of disparate treatment as well as disparate impact w.r.t. a structural causal model. In this paper, we examine the relationship between quantitative as well as qualitative information-flow properties and fairness. Moreover, based on this duality, we derive a new quantitative notion of fairness called fairness spread, which can be easily analyzed using quantitative information flow and which strongly relates to counterfactual fairness. We demonstrate that off-the-shelf tools for information-flow properties can be used in order to formally analyze a program's algorithmic fairness properties, including the new notion of fairness spread as well as established notions such as demographic parity.

Identification for Tree-Shaped Structural Causal Models in Polynomial Time

Linear structural causal models (SCMs) are used to express and analyze the relationships between random variables. Direct causal effects are represented as directed edges and confounding factors as bidirected edges. Identifying the causal parameters from correlations between the nodes is an open problem in artificial intelligence. In this paper, we study SCMs whose directed component forms a tree. Van der Zander et al. give a PSPACE-algorithm for the identification problem in this case, which is a significant improvement over the general Gröbner basis approach, which has doubly-exponential time complexity in the number of structural parameters. However, they do not show that their algorithm is complete. In this work, we present a randomized polynomial-time algorithm, which solves the identification problem for tree-shaped SCMs. For every structural parameter, our algorithms decides whether it is generically identifiable, generically 2-identifiable, or generically unidentifiable. (No other cases can occur.) In the first two cases, it provides one or two fractional affine square root terms of polynomials (FASTPs) for the corresponding parameter, respectively. In particular, our algorithm is not only polynomial time, but also complete for for tree-shaped SCMs.

ACAMDA: Improving Data Efficiency in Reinforcement Learning through Guided Counterfactual Data Augmentation

Data augmentation plays a crucial role in improving the data efficiency of reinforcement learning (RL). However, the generation of high-quality augmented data remains a significant challenge. To overcome this, we introduce ACAMDA (Adversarial Causal Modeling for Data Augmentation), a novel framework that integrates two causality-based tasks: causal structure recovery and counterfactual estimation. The unique aspect of ACAMDA lies in its ability to recover temporal causal relationships from limited non-expert datasets. The identification of the sequential cause-and-effect allows the creation of realistic yet unobserved scenarios. We utilize this characteristic to generate guided counterfactual datasets, which, in turn, substantially reduces the need for extensive data collection. By simulating various state-action pairs under hypothetical actions, ACAMDA enriches the training dataset for diverse and heterogeneous conditions. Our experimental evaluation shows that ACAMDA outperforms existing methods, particularly when applied to novel and unseen domains.

Causal Adversarial Perturbations for Individual Fairness and Robustness in Heterogeneous Data Spaces

As responsible AI gains importance in machine learning algorithms, properties like fairness, adversarial robustness, and causality have received considerable attention in recent years. However, despite their individual significance, there remains a critical gap in simultaneously exploring and integrating these properties. In this paper, we propose a novel approach that examines the relationship between individual fairness, adversarial robustness, and structural causal models (SCMs) in heterogeneous data spaces, particularly when dealing with discrete sensitive attributes. We use SCMs and sensitive attributes to create a fair metric and apply it to measure semantic similarity among individuals. By introducing a novel causal adversarial perturbation (CAP) and applying adversarial training, we create a new regularizer that combines individual fairness, causality, and robustness in the classifier. Our method is evaluated on both real-world and synthetic datasets, demonstrating its effectiveness in achieving an accurate classifier that simultaneously exhibits fairness, adversarial robustness, and causal awareness.