Dear Editor,This letter introduces the counterfactual-guided implicit correspondence prompting(CICP)framework,designed for visible-infrared person re-identification(VI-ReID)within Industry 5.0 intelligent control syst...Dear Editor,This letter introduces the counterfactual-guided implicit correspondence prompting(CICP)framework,designed for visible-infrared person re-identification(VI-ReID)within Industry 5.0 intelligent control systems.CICP advances recognition accuracy in complex industrial environments through its innovative approach to handling modality-specific features and their implicit relationships.展开更多
Most Convolutional Neural Network(CNN)interpretation techniques visualize only the dominant cues that the model relies on,but there is no guarantee that these represent all the evidence the model uses for classificati...Most Convolutional Neural Network(CNN)interpretation techniques visualize only the dominant cues that the model relies on,but there is no guarantee that these represent all the evidence the model uses for classification.This limitation becomes critical when hidden secondary cues—potentially more meaningful than the visualized ones—remain undiscovered.This study introduces CasCAM(Cascaded Class Activation Mapping)to address this fundamental limitation through counterfactual reasoning.By asking“if this dominant cue were absent,what other evidence would the model use?”,CasCAM progressively masks the most salient features and systematically uncovers the hierarchy of classification evidence hidden beneath them.Experimental results demonstrate that CasCAM effectively discovers the full spectrum of reasoning evidence and can be universally applied with nine existing interpretation methods.展开更多
It has long been noticed that focus is able to influence the truth-conditions of coun-terfactual conditionals.Namely,stressing different parts of a counterfactual leads to distinct interpretations.However,existing the...It has long been noticed that focus is able to influence the truth-conditions of coun-terfactual conditionals.Namely,stressing different parts of a counterfactual leads to distinct interpretations.However,existing theories,such as those by von Finte1 and Rooth,fail to ad-equately account for this phenomenon.In this paper,I exposit the drawbacks of these theories and then propose a novel account,ie.the Good Question-Answer(GQA)view.The GQA account posits that focus triggers question-answer pairs,and pragmatic pressures conceming the adequacy of such question answer pairs in contexts are able to affect the truth-conditions of counterfactuals.I also argue for the GQA account by appeal to its theoretical virtues.展开更多
This study uses the Bayesian structural model to assess the causal effect of the futures exchange(FTX)insolvency on cryptocurrencies from October 2022 to December 14,2022.Findings show that FTX insolvency negatively i...This study uses the Bayesian structural model to assess the causal effect of the futures exchange(FTX)insolvency on cryptocurrencies from October 2022 to December 14,2022.Findings show that FTX insolvency negatively impacts cryptocurrencies.Moreover,the results indicate rapid divergence from counterfactual predictions,and the actual cryptocurrencies are consistently lower than would have been expected in the absence of the FTX collapse.Cryptocurrency is reacting strongly to the uncertainty caused by insolvency.In relative terms,the collapse of FTX has been highly detrimental to Solana and Ethereum.Furthermore,the outcomes show that cryptocurrencies would not have been negatively affected if the intervention had not occurred.FTX collapsed owing to a mismatch between the assets and liabilities.The industry is still mostly unregulated,and regulators must act quickly,highlighting the need for outstanding innovation and decentralized and trustless technology adoption.展开更多
Predicting molecular properties is essential for advancing for advancing drug discovery and design. Recently, Graph Neural Networks (GNNs) have gained prominence due to their ability to capture the complex structural ...Predicting molecular properties is essential for advancing for advancing drug discovery and design. Recently, Graph Neural Networks (GNNs) have gained prominence due to their ability to capture the complex structural and relational information inherent in molecular graphs. Despite their effectiveness, the “black-box” nature of GNNs remains a significant obstacle to their widespread adoption in chemistry, as it hinders interpretability and trust. In this context, several explanation methods based on factual reasoning have emerged. These methods aim to interpret the predictions made by GNNs by analyzing the key features contributing to the prediction. However, these approaches fail to answer critical questions: “How to ensure that the structure-property mapping learned by GNNs is consistent with established domain knowledge”. In this paper, we propose MMGCF, a novel counterfactual explanation framework designed specifically for the prediction of GNN-based molecular properties. MMGCF constructs a hierarchical tree structure on molecular motifs, enabling the systematic generation of counterfactuals through motif perturbations. This framework identifies causally significant motifs and elucidates their impact on model predictions, offering insights into the relationship between structural modifications and predicted properties. Our method demonstrates its effectiveness through comprehensive quantitative and qualitative evaluations of four real-world molecular datasets.展开更多
People learn causal relations since childhood using counterfactual reasoning. Counterfactual reasoning uses counterfactual examples which take the form of “what if this has happened differently”. Counterfactual exam...People learn causal relations since childhood using counterfactual reasoning. Counterfactual reasoning uses counterfactual examples which take the form of “what if this has happened differently”. Counterfactual examples are also the basis of counterfactual explanation in explainable artificial intelligence (XAI). However, a framework that relies solely on optimization algorithms to find and present counterfactual samples cannot help users gain a deeper understanding of the system. Without a way to verify their understanding, the users can even be misled by such explanations. Such limitations can be overcome through an interactive and iterative framework that allows the users to explore their desired “what-if” scenarios. The purpose of our research is to develop such a framework. In this paper, we present our “what-if” XAI framework (WiXAI), which visualizes the artificial intelligence (AI) classification model from the perspective of the user’s sample and guides their “what-if” exploration. We also formulated how to use the WiXAI framework to generate counterfactuals and understand the feature-feature and feature-output relations in-depth for a local sample. These relations help move the users toward causal understanding.展开更多
Counterfactual quantum cryptography, recently proposed by Noh, is featured with no transmission of signal parti- cles. This exhibits evident security advantages, such as its immunity to the well-known photon-number-sp...Counterfactual quantum cryptography, recently proposed by Noh, is featured with no transmission of signal parti- cles. This exhibits evident security advantages, such as its immunity to the well-known photon-number-splitting attack. In this paper, the theoretical security of counterfactual quantum cryptography protocol against the general intercept- resend attacks is proved by bounding the information of an eavesdropper Eve more tightly than in Yin＇s proposal [Phys. Rev. A 82 042335 （2010）]. It is also shown that practical counterfactual quantum cryptography implementations may be vulnerable when equipped with imperfect apparatuses, by proving that a negative key rate can be achieved when Eve launches a time-shift attack based on imperfect detector efficiency.展开更多
With the popularity of online learning in educational settings, knowledge tracing(KT) plays an increasingly significant role. The task of KT is to help students learn more effectively by predicting their next mastery ...With the popularity of online learning in educational settings, knowledge tracing(KT) plays an increasingly significant role. The task of KT is to help students learn more effectively by predicting their next mastery of knowledge based on their historical exercise sequences. Nowadays, many related works have emerged in this field, such as Bayesian knowledge tracing and deep knowledge tracing methods. Despite the progress that has been made in KT, existing techniques still have the following limitations: 1) Previous studies address KT by only exploring the observational sparsity data distribution, and the counterfactual data distribution has been largely ignored. 2) Current works designed for KT only consider either the entity relationships between questions and concepts, or the relations between two concepts, and none of them investigates the relations among students, questions, and concepts, simultaneously, leading to inaccurate student modeling. To address the above limitations,we propose a graph counterfactual augmentation method for knowledge tracing. Concretely, to consider the multiple relationships among different entities, we first uniform students, questions, and concepts in graphs, and then leverage a heterogeneous graph convolutional network to conduct representation learning.To model the counterfactual world, we conduct counterfactual transformations on students’ learning graphs by changing the corresponding treatments and then exploit the counterfactual outcomes in a contrastive learning framework. We conduct extensive experiments on three real-world datasets, and the experimental results demonstrate the superiority of our proposed Graph CA method compared with several state-of-the-art baselines.展开更多
Quantum self-interference enables the counterfactual transmission of information,whereby the transmitted bits involve no particles traveling through the channel.In this work,we show how counterfactuality can be realiz...Quantum self-interference enables the counterfactual transmission of information,whereby the transmitted bits involve no particles traveling through the channel.In this work,we show how counterfactuality can be realized even when the self-interference is replaced by interference between identical particles.Interestingly,the facet of indistinguishability called forth here is associated with first-order coherence,and is different from the usual notion of indistinguishability associated with the(anti-)commutation relations of mode operators.From an experimental perspective,the simplest implementation of the proposed idea can be realized by slight modifications to existing protocols for differential-phase-shift quantum key distribution or interaction-free measurement.展开更多
Confounding of three binary-variable counterfactual model with directed acyclic graph (DAG) is discussed in this paper. According to the effect between the control variable and the covariate variable, we investigate t...Confounding of three binary-variable counterfactual model with directed acyclic graph (DAG) is discussed in this paper. According to the effect between the control variable and the covariate variable, we investigate three causal counterfactual models: the control variable is independent of the covariate variable, the control variable has the effect on the covariate variable and the covariate variable affects the control variable. Using the ancillary information based on conditional independence hypotheses and ignorability, the sufficient conditions to determine whether the covariate variable is an irrelevant factor or whether there is no confounding in each counterfactual model are obtained.展开更多
In eliminating the fair sampling assumption, the Greenberger, Horne, Zeilinger (GHZ) theorem is believed to confirm Bell’s historic conclusion that local hidden variables are inconsistent with the results of quantum ...In eliminating the fair sampling assumption, the Greenberger, Horne, Zeilinger (GHZ) theorem is believed to confirm Bell’s historic conclusion that local hidden variables are inconsistent with the results of quantum mechanics. The GHZ theorem depends on predicting the results of sets of measurements of which only one may be performed. In the present paper, the noncommutative aspects of these unperformed measurements are critically examined. Classical examples and the logic of the GHZ construction are analyzed to demonstrate that combined counterfactual results of noncommuting operations are in general logically inconsistent with performed measurement sequences whose results depend on noncommutation. The Bell theorem is also revisited in the light of this result. It is concluded that negative conclusions regarding local hidden variables do not follow from the GHZ and Bell theorems as historically reasoned.展开更多
Counterfactual thinking is helpful to comprehend the mistakes made previously and to move toward by proposing future actions to facilitate the success of self-regulation.The sunk cost effect rationalizes a strategy,wh...Counterfactual thinking is helpful to comprehend the mistakes made previously and to move toward by proposing future actions to facilitate the success of self-regulation.The sunk cost effect rationalizes a strategy,which is the aim of studies on decision-making.However,few of them have discussed the influence of counterfactual thinking to the sunk cost effect.This study assumes that downward counterfactual thinking can regulate the unhappy mood at the moment for relief,which may reduce the sunk cost fallacy;upward counterfactual thinking,on the contrary,emphasizes the improvement of future behaviors,which may increase the sunk cost fallacy.展开更多
This paper examines whether or not Chinese native speakers (CNSs) have difficulties in understanding English counterfactuals, whether CNSs have counterfactual reasoning problems in their own language, what the causes ...This paper examines whether or not Chinese native speakers (CNSs) have difficulties in understanding English counterfactuals, whether CNSs have counterfactual reasoning problems in their own language, what the causes of these difficulties may be, and the problems in teaching English subjunctives. It also proposes on how to improve CNSs’ English counterfactual comprehension.展开更多
Embodied cognition theories propose that language comprehension triggers a sensorimotor system in the brain.However,most previous research has paid much attention to concrete and factual sentences,and little emphasis ...Embodied cognition theories propose that language comprehension triggers a sensorimotor system in the brain.However,most previous research has paid much attention to concrete and factual sentences,and little emphasis has been put on the research of abstract and counterfactual sentences.The primary challenges for embodied theories lie in elucidating the meanings of abstract and counterfactual sentences.The most prevalent explanation is that abstract and counterfactual sentences are grounded in the activation of a sensorimotor system,in exactly the same way as concrete and factual ones.The present research employed a dual-task experimental paradigm to investigate whether the embodied meaning is activated in comprehending action-related abstract Chinese counterfactual sentences through the presence or absence of action-sentence compatibility effect(ACE).Participants were instructed to read and listen to the action-related abstract Chinese factual or counterfactual sentences describing an abstract transfer word towards or away from them,and then move their fingers towards or away from them to press the buttons in the same direction as the motion cue of the transfer verb.The action-sentence compatibility effect was observed in both abstract factual and counterfactual sentences,in line with the embodied cognition theories,which indicated that the embodied meanings were activated in both action-related abstract factuals and counterfactuals.展开更多
A novel counterfactual quantum key distribution scheme was proposed by T.-G. Noh and a strict security analysis has been given by Z.-Q.Yin, in which two legitimate geographical separated couples may share secret keys ...A novel counterfactual quantum key distribution scheme was proposed by T.-G. Noh and a strict security analysis has been given by Z.-Q.Yin, in which two legitimate geographical separated couples may share secret keys even when the key carriers are not traveled in the quantum channel. However, there are still plenty of practical details in this protocol that haven’t been discussed yet, which are of significant importance in physical implementation. In this paper, we will give a practical analysis on such kind of counterfactual quantum cryptography in the aspects of quantum bit error rate (QBER) and stabilization. Furthermore, modified schemes are proposed, which can obtain lower QBER and will be much more robust on stabilization in physical implementation.展开更多
Artificial intelligence regulations typically require that sensitive attributes(such as gender and race)be excluded from algorithmic decision-making to prevent discrimination,a principle commonly referred to as'&#...Artificial intelligence regulations typically require that sensitive attributes(such as gender and race)be excluded from algorithmic decision-making to prevent discrimination,a principle commonly referred to as''fairness through unawareness.''However,even when sensitive attributes are removed,algorithmic models may still infer such information through proxy variables that are pervasive in data,often via complex nonlinear relationships,thereby perpetuating or even amplifying systemic bias.To address the problem of indirect discrimination under fairness through unawareness,this paper proposes an end-to-end framework that integrates discrimination auditing,diagnosis,and mitigation.First,by incorporating an advanced Transformer-Based Counterfactual Explainer(TABCF),our framework constructs a more reliable bias auditing system capable of accurately uncovering discriminatory behaviors in models.Second,once bias is detected,we introduce an innovative two-stage NOCCO-Shapley diagnostic method that identifies the key proxy variables responsible for discrimination and reveals how the model actually exploits these variables in practice.Finally,to mitigate the identified bias,we implement an adjustableλ-PCF post-processing strategy that enables a quantifiable trade-off between predictive utility and counterfactual fairness without retraining the model.Notably,we find that when the trade-off parameterλis set to the prior probability distribution of the sensitive attribute in the dataset,the model achieves an optimal balance between fairness and utility.Extensive experiments on four widely used real-world datasets demonstrate that our end-to-end framework not only outperforms existing methods in auditing and diagnosis,but also provides a practical and effective technical pathway for deploying more responsible and fair AI systems in real-world applications.展开更多
The application of machine learning in the healthcare domain has groundbreaking potential across a wide range of scenarios.However,this potential is often stalled by data-related challenges,such as the imbalanced natu...The application of machine learning in the healthcare domain has groundbreaking potential across a wide range of scenarios.However,this potential is often stalled by data-related challenges,such as the imbalanced nature of the domain's data,where critical outcomes tend to be inherently rare.To address this challenge,we propose a novel oversampling approach,the counterfactual synthetic minority oversampling technique(Counterfactual SMOTE),which combines SMOTE with a counterfactual generation framework.Our method intrinsically performs an oversampling process near the decision boundary within a safe region of space,allowing for the generation of informative but non-noisy minority samples.To validate the proposed framework,a rigorous experimental procedure was conducted across a set of highly imbalanced binary classification challenges in healthcare.The results demonstrate the superiority of the proposed method over several of the most commonly used oversampling alternatives presented in the literature.Notably,Counterfactual SMOTE was the only method to present a convincingly superior performance when compared with the original SMOTE.Although the proposed method was specifically validated in the healthcare domain,owing to its relevance and frequently imbalanced nature,we expect the findings of this study to be generalizable to any imbalanced scenario.展开更多
Graph-structured data are pervasive in the real-world such as social networks,molecular graphs and transaction networks.Graph neural networks(GNNs)have achieved great success in representation learning on graphs,facil...Graph-structured data are pervasive in the real-world such as social networks,molecular graphs and transaction networks.Graph neural networks(GNNs)have achieved great success in representation learning on graphs,facilitating various downstream tasks.However,GNNs have several drawbacks such as lacking interpretability,can easily inherit the bias of data and cannot model casual rela-tions.Recently,counterfactual learning on graphs has shown promising results in alleviating these drawbacks.Various approaches have been proposed for counterfactual fairness,explainability,link prediction and other applications on graphs.To facilitate the develop-ment of this promising direction,in this survey,we categorize and comprehensively review papers on graph counterfactual learning.We divide existing methods into four categories based on problems studied.For each category,we provide background and motivating ex-amples,a general framework summarizing existing works and a detailed review of these works.We point out promising future research directions at the intersection of graph-structured data,counterfactual learning,and real-world applications.To offer a comprehensive view of resources for future studies,we compile a collection of open-source implementations,public datasets,and commonly-used evalu-ation metrics.This survey aims to serve as a“one-stop-shop”for building a unified understanding of graph counterfactual learning cat-egories and current resources.展开更多
The performances of numerical simulation and machine learning in production forecasting are severely dependent on precise geological modeling and high-quality history matching.To address these chal lenges,causal infer...The performances of numerical simulation and machine learning in production forecasting are severely dependent on precise geological modeling and high-quality history matching.To address these chal lenges,causal inference is an effective methodology since it can provide a causality for formalizing causality in history,not statistical dependence.In this paper,to dynamically predict oil production from causality existed in waterflooding oilfield,a dynamical counterfactual inference framework is built to predict oil production.The proposed framework can forecast the oil production under non-observation of engineering factors,i.e.,counterfactual,and provide the causal effect of engineering factors impacting on oil production.Meanwhile,combining with the practice exploitation in engineering factor impacting on production,a counterfactual experiment is designed to execute counterfactual prediction.Compared with general machine learning and statistical models,our results not only show better performance in oil production flooding but also guide the specific optimization in improving production,which holds more practical application significance.展开更多
With the rapid rise of new media platforms such as Weibo and Tiktok,communities with science communication characteristics have progressively grown on social networks.These communities pursue essential objectives such...With the rapid rise of new media platforms such as Weibo and Tiktok,communities with science communication characteristics have progressively grown on social networks.These communities pursue essential objectives such as increased visibility and influence.For the success of the public understanding of science in China,case studies of science communication communities on social media are becoming increasingly valuable as a point of reference.The authenticity of user influence plays an important role in the analysis of the final outcome during the process of community detection.By integrating counterfactual reasoning theory into a community detection algorithm,we present a novel paradigm for eliminating influence bias in online communities.We consider the community of Public Science Day of the Chinese Academy of Sciences as a case study to demonstrate the validity of the proposed paradigm.In addition,we examine data on science communication activities,analyze the key elements of activity communication,and provide references for not only augmenting the communication impact of similar types of popular science activities but also advancing science communication in China.Our main finding is that the propagation channel for the science communication experiment exhibits multi-point scattered propagation and lacks a continuous chain in the process of propagation.展开更多
基金supported in part by the National Natural Science Foundation of China(62406177)the Shandong Excellent Young Scientists Fund(Oversea)(2024HWYQ-027)+1 种基金the Natural Science Foundation of Shandong Province(ZR2023QF124)the Young Scholars Program of Shandong University。
文摘Dear Editor,This letter introduces the counterfactual-guided implicit correspondence prompting(CICP)framework,designed for visible-infrared person re-identification(VI-ReID)within Industry 5.0 intelligent control systems.CICP advances recognition accuracy in complex industrial environments through its innovative approach to handling modality-specific features and their implicit relationships.
基金supported by the Basic Science Research Program through the National Research Foundation of Korea(NRF),funded by the Ministry of Education(RS-2023-00249743).
文摘Most Convolutional Neural Network(CNN)interpretation techniques visualize only the dominant cues that the model relies on,but there is no guarantee that these represent all the evidence the model uses for classification.This limitation becomes critical when hidden secondary cues—potentially more meaningful than the visualized ones—remain undiscovered.This study introduces CasCAM(Cascaded Class Activation Mapping)to address this fundamental limitation through counterfactual reasoning.By asking“if this dominant cue were absent,what other evidence would the model use?”,CasCAM progressively masks the most salient features and systematically uncovers the hierarchy of classification evidence hidden beneath them.Experimental results demonstrate that CasCAM effectively discovers the full spectrum of reasoning evidence and can be universally applied with nine existing interpretation methods.
基金supported by the Major Program of National Social Science Foundation of China(No.23&ZD240)。
文摘It has long been noticed that focus is able to influence the truth-conditions of coun-terfactual conditionals.Namely,stressing different parts of a counterfactual leads to distinct interpretations.However,existing theories,such as those by von Finte1 and Rooth,fail to ad-equately account for this phenomenon.In this paper,I exposit the drawbacks of these theories and then propose a novel account,ie.the Good Question-Answer(GQA)view.The GQA account posits that focus triggers question-answer pairs,and pragmatic pressures conceming the adequacy of such question answer pairs in contexts are able to affect the truth-conditions of counterfactuals.I also argue for the GQA account by appeal to its theoretical virtues.
文摘This study uses the Bayesian structural model to assess the causal effect of the futures exchange(FTX)insolvency on cryptocurrencies from October 2022 to December 14,2022.Findings show that FTX insolvency negatively impacts cryptocurrencies.Moreover,the results indicate rapid divergence from counterfactual predictions,and the actual cryptocurrencies are consistently lower than would have been expected in the absence of the FTX collapse.Cryptocurrency is reacting strongly to the uncertainty caused by insolvency.In relative terms,the collapse of FTX has been highly detrimental to Solana and Ethereum.Furthermore,the outcomes show that cryptocurrencies would not have been negatively affected if the intervention had not occurred.FTX collapsed owing to a mismatch between the assets and liabilities.The industry is still mostly unregulated,and regulators must act quickly,highlighting the need for outstanding innovation and decentralized and trustless technology adoption.
文摘Predicting molecular properties is essential for advancing for advancing drug discovery and design. Recently, Graph Neural Networks (GNNs) have gained prominence due to their ability to capture the complex structural and relational information inherent in molecular graphs. Despite their effectiveness, the “black-box” nature of GNNs remains a significant obstacle to their widespread adoption in chemistry, as it hinders interpretability and trust. In this context, several explanation methods based on factual reasoning have emerged. These methods aim to interpret the predictions made by GNNs by analyzing the key features contributing to the prediction. However, these approaches fail to answer critical questions: “How to ensure that the structure-property mapping learned by GNNs is consistent with established domain knowledge”. In this paper, we propose MMGCF, a novel counterfactual explanation framework designed specifically for the prediction of GNN-based molecular properties. MMGCF constructs a hierarchical tree structure on molecular motifs, enabling the systematic generation of counterfactuals through motif perturbations. This framework identifies causally significant motifs and elucidates their impact on model predictions, offering insights into the relationship between structural modifications and predicted properties. Our method demonstrates its effectiveness through comprehensive quantitative and qualitative evaluations of four real-world molecular datasets.
文摘People learn causal relations since childhood using counterfactual reasoning. Counterfactual reasoning uses counterfactual examples which take the form of “what if this has happened differently”. Counterfactual examples are also the basis of counterfactual explanation in explainable artificial intelligence (XAI). However, a framework that relies solely on optimization algorithms to find and present counterfactual samples cannot help users gain a deeper understanding of the system. Without a way to verify their understanding, the users can even be misled by such explanations. Such limitations can be overcome through an interactive and iterative framework that allows the users to explore their desired “what-if” scenarios. The purpose of our research is to develop such a framework. In this paper, we present our “what-if” XAI framework (WiXAI), which visualizes the artificial intelligence (AI) classification model from the perspective of the user’s sample and guides their “what-if” exploration. We also formulated how to use the WiXAI framework to generate counterfactuals and understand the feature-feature and feature-output relations in-depth for a local sample. These relations help move the users toward causal understanding.
基金Project supported by the National Natural Science Foundation of China (Grant No 60872052)
文摘Counterfactual quantum cryptography, recently proposed by Noh, is featured with no transmission of signal parti- cles. This exhibits evident security advantages, such as its immunity to the well-known photon-number-splitting attack. In this paper, the theoretical security of counterfactual quantum cryptography protocol against the general intercept- resend attacks is proved by bounding the information of an eavesdropper Eve more tightly than in Yin＇s proposal [Phys. Rev. A 82 042335 （2010）]. It is also shown that practical counterfactual quantum cryptography implementations may be vulnerable when equipped with imperfect apparatuses, by proving that a negative key rate can be achieved when Eve launches a time-shift attack based on imperfect detector efficiency.
基金supported by the Natural Science Foundation of China (62372277)the Natural Science Foundation of Shandong Province (ZR2022MF257, ZR2022MF295)Humanities and Social Sciences Fund of the Ministry of Education (21YJC630157)。
文摘With the popularity of online learning in educational settings, knowledge tracing(KT) plays an increasingly significant role. The task of KT is to help students learn more effectively by predicting their next mastery of knowledge based on their historical exercise sequences. Nowadays, many related works have emerged in this field, such as Bayesian knowledge tracing and deep knowledge tracing methods. Despite the progress that has been made in KT, existing techniques still have the following limitations: 1) Previous studies address KT by only exploring the observational sparsity data distribution, and the counterfactual data distribution has been largely ignored. 2) Current works designed for KT only consider either the entity relationships between questions and concepts, or the relations between two concepts, and none of them investigates the relations among students, questions, and concepts, simultaneously, leading to inaccurate student modeling. To address the above limitations,we propose a graph counterfactual augmentation method for knowledge tracing. Concretely, to consider the multiple relationships among different entities, we first uniform students, questions, and concepts in graphs, and then leverage a heterogeneous graph convolutional network to conduct representation learning.To model the counterfactual world, we conduct counterfactual transformations on students’ learning graphs by changing the corresponding treatments and then exploit the counterfactual outcomes in a contrastive learning framework. We conduct extensive experiments on three real-world datasets, and the experimental results demonstrate the superiority of our proposed Graph CA method compared with several state-of-the-art baselines.
基金the support from the Interdisciplinary Cyber Physical Systems(ICPS)program of the Department of Science and Technology(DST),India,Grant No.DST/ICPS/Qu ST/Theme-1/2019/14the support and encouragement from the Admar Mutt Education Foundation
文摘Quantum self-interference enables the counterfactual transmission of information,whereby the transmitted bits involve no particles traveling through the channel.In this work,we show how counterfactuality can be realized even when the self-interference is replaced by interference between identical particles.Interestingly,the facet of indistinguishability called forth here is associated with first-order coherence,and is different from the usual notion of indistinguishability associated with the(anti-)commutation relations of mode operators.From an experimental perspective,the simplest implementation of the proposed idea can be realized by slight modifications to existing protocols for differential-phase-shift quantum key distribution or interaction-free measurement.
文摘Confounding of three binary-variable counterfactual model with directed acyclic graph (DAG) is discussed in this paper. According to the effect between the control variable and the covariate variable, we investigate three causal counterfactual models: the control variable is independent of the covariate variable, the control variable has the effect on the covariate variable and the covariate variable affects the control variable. Using the ancillary information based on conditional independence hypotheses and ignorability, the sufficient conditions to determine whether the covariate variable is an irrelevant factor or whether there is no confounding in each counterfactual model are obtained.
文摘In eliminating the fair sampling assumption, the Greenberger, Horne, Zeilinger (GHZ) theorem is believed to confirm Bell’s historic conclusion that local hidden variables are inconsistent with the results of quantum mechanics. The GHZ theorem depends on predicting the results of sets of measurements of which only one may be performed. In the present paper, the noncommutative aspects of these unperformed measurements are critically examined. Classical examples and the logic of the GHZ construction are analyzed to demonstrate that combined counterfactual results of noncommuting operations are in general logically inconsistent with performed measurement sequences whose results depend on noncommutation. The Bell theorem is also revisited in the light of this result. It is concluded that negative conclusions regarding local hidden variables do not follow from the GHZ and Bell theorems as historically reasoned.
文摘Counterfactual thinking is helpful to comprehend the mistakes made previously and to move toward by proposing future actions to facilitate the success of self-regulation.The sunk cost effect rationalizes a strategy,which is the aim of studies on decision-making.However,few of them have discussed the influence of counterfactual thinking to the sunk cost effect.This study assumes that downward counterfactual thinking can regulate the unhappy mood at the moment for relief,which may reduce the sunk cost fallacy;upward counterfactual thinking,on the contrary,emphasizes the improvement of future behaviors,which may increase the sunk cost fallacy.
文摘This paper examines whether or not Chinese native speakers (CNSs) have difficulties in understanding English counterfactuals, whether CNSs have counterfactual reasoning problems in their own language, what the causes of these difficulties may be, and the problems in teaching English subjunctives. It also proposes on how to improve CNSs’ English counterfactual comprehension.
文摘Embodied cognition theories propose that language comprehension triggers a sensorimotor system in the brain.However,most previous research has paid much attention to concrete and factual sentences,and little emphasis has been put on the research of abstract and counterfactual sentences.The primary challenges for embodied theories lie in elucidating the meanings of abstract and counterfactual sentences.The most prevalent explanation is that abstract and counterfactual sentences are grounded in the activation of a sensorimotor system,in exactly the same way as concrete and factual ones.The present research employed a dual-task experimental paradigm to investigate whether the embodied meaning is activated in comprehending action-related abstract Chinese counterfactual sentences through the presence or absence of action-sentence compatibility effect(ACE).Participants were instructed to read and listen to the action-related abstract Chinese factual or counterfactual sentences describing an abstract transfer word towards or away from them,and then move their fingers towards or away from them to press the buttons in the same direction as the motion cue of the transfer verb.The action-sentence compatibility effect was observed in both abstract factual and counterfactual sentences,in line with the embodied cognition theories,which indicated that the embodied meanings were activated in both action-related abstract factuals and counterfactuals.
文摘A novel counterfactual quantum key distribution scheme was proposed by T.-G. Noh and a strict security analysis has been given by Z.-Q.Yin, in which two legitimate geographical separated couples may share secret keys even when the key carriers are not traveled in the quantum channel. However, there are still plenty of practical details in this protocol that haven’t been discussed yet, which are of significant importance in physical implementation. In this paper, we will give a practical analysis on such kind of counterfactual quantum cryptography in the aspects of quantum bit error rate (QBER) and stabilization. Furthermore, modified schemes are proposed, which can obtain lower QBER and will be much more robust on stabilization in physical implementation.
文摘Artificial intelligence regulations typically require that sensitive attributes(such as gender and race)be excluded from algorithmic decision-making to prevent discrimination,a principle commonly referred to as''fairness through unawareness.''However,even when sensitive attributes are removed,algorithmic models may still infer such information through proxy variables that are pervasive in data,often via complex nonlinear relationships,thereby perpetuating or even amplifying systemic bias.To address the problem of indirect discrimination under fairness through unawareness,this paper proposes an end-to-end framework that integrates discrimination auditing,diagnosis,and mitigation.First,by incorporating an advanced Transformer-Based Counterfactual Explainer(TABCF),our framework constructs a more reliable bias auditing system capable of accurately uncovering discriminatory behaviors in models.Second,once bias is detected,we introduce an innovative two-stage NOCCO-Shapley diagnostic method that identifies the key proxy variables responsible for discrimination and reveals how the model actually exploits these variables in practice.Finally,to mitigate the identified bias,we implement an adjustableλ-PCF post-processing strategy that enables a quantifiable trade-off between predictive utility and counterfactual fairness without retraining the model.Notably,we find that when the trade-off parameterλis set to the prior probability distribution of the sensitive attribute in the dataset,the model achieves an optimal balance between fairness and utility.Extensive experiments on four widely used real-world datasets demonstrate that our end-to-end framework not only outperforms existing methods in auditing and diagnosis,but also provides a practical and effective technical pathway for deploying more responsible and fair AI systems in real-world applications.
基金supported by national funds through FCT(Fundaçao para a Ciencia e a Tecnologia),under the project-UIDB/04152/2020-Centro de Investigaçao em Gestao de Informaçao(MagIC)/NOVA IMS).
文摘The application of machine learning in the healthcare domain has groundbreaking potential across a wide range of scenarios.However,this potential is often stalled by data-related challenges,such as the imbalanced nature of the domain's data,where critical outcomes tend to be inherently rare.To address this challenge,we propose a novel oversampling approach,the counterfactual synthetic minority oversampling technique(Counterfactual SMOTE),which combines SMOTE with a counterfactual generation framework.Our method intrinsically performs an oversampling process near the decision boundary within a safe region of space,allowing for the generation of informative but non-noisy minority samples.To validate the proposed framework,a rigorous experimental procedure was conducted across a set of highly imbalanced binary classification challenges in healthcare.The results demonstrate the superiority of the proposed method over several of the most commonly used oversampling alternatives presented in the literature.Notably,Counterfactual SMOTE was the only method to present a convincingly superior performance when compared with the original SMOTE.Although the proposed method was specifically validated in the healthcare domain,owing to its relevance and frequently imbalanced nature,we expect the findings of this study to be generalizable to any imbalanced scenario.
基金supported by,or in part by the National Science Foundation(NSF),USA(No.IIS-1909702)Army Research Office(ARO),USA(No.W911NF-21-10198),and Cisco Faculty Research Award.
文摘Graph-structured data are pervasive in the real-world such as social networks,molecular graphs and transaction networks.Graph neural networks(GNNs)have achieved great success in representation learning on graphs,facilitating various downstream tasks.However,GNNs have several drawbacks such as lacking interpretability,can easily inherit the bias of data and cannot model casual rela-tions.Recently,counterfactual learning on graphs has shown promising results in alleviating these drawbacks.Various approaches have been proposed for counterfactual fairness,explainability,link prediction and other applications on graphs.To facilitate the develop-ment of this promising direction,in this survey,we categorize and comprehensively review papers on graph counterfactual learning.We divide existing methods into four categories based on problems studied.For each category,we provide background and motivating ex-amples,a general framework summarizing existing works and a detailed review of these works.We point out promising future research directions at the intersection of graph-structured data,counterfactual learning,and real-world applications.To offer a comprehensive view of resources for future studies,we compile a collection of open-source implementations,public datasets,and commonly-used evalu-ation metrics.This survey aims to serve as a“one-stop-shop”for building a unified understanding of graph counterfactual learning cat-egories and current resources.
文摘The performances of numerical simulation and machine learning in production forecasting are severely dependent on precise geological modeling and high-quality history matching.To address these chal lenges,causal inference is an effective methodology since it can provide a causality for formalizing causality in history,not statistical dependence.In this paper,to dynamically predict oil production from causality existed in waterflooding oilfield,a dynamical counterfactual inference framework is built to predict oil production.The proposed framework can forecast the oil production under non-observation of engineering factors,i.e.,counterfactual,and provide the causal effect of engineering factors impacting on oil production.Meanwhile,combining with the practice exploitation in engineering factor impacting on production,a counterfactual experiment is designed to execute counterfactual prediction.Compared with general machine learning and statistical models,our results not only show better performance in oil production flooding but also guide the specific optimization in improving production,which holds more practical application significance.
基金supported by the Informatization Project,Chinese Academy of Sciences(No.CAS-wx2022gc-0304).
文摘With the rapid rise of new media platforms such as Weibo and Tiktok,communities with science communication characteristics have progressively grown on social networks.These communities pursue essential objectives such as increased visibility and influence.For the success of the public understanding of science in China,case studies of science communication communities on social media are becoming increasingly valuable as a point of reference.The authenticity of user influence plays an important role in the analysis of the final outcome during the process of community detection.By integrating counterfactual reasoning theory into a community detection algorithm,we present a novel paradigm for eliminating influence bias in online communities.We consider the community of Public Science Day of the Chinese Academy of Sciences as a case study to demonstrate the validity of the proposed paradigm.In addition,we examine data on science communication activities,analyze the key elements of activity communication,and provide references for not only augmenting the communication impact of similar types of popular science activities but also advancing science communication in China.Our main finding is that the propagation channel for the science communication experiment exhibits multi-point scattered propagation and lacks a continuous chain in the process of propagation.
