Explore the vast range of titles available.

Abstract Multimodal sentiment analysis (MSA) has garnered significant attention for its immense potential in human-computer interaction. While cross-modality attention mechanisms are widely used in MSA to capture inter-modality interactions, existing methods are limited to pairwise interactions between two modalities. Additionally, these methods can not utilize the causal relationship to guide attention learning, making them susceptible to bias information. To address these limitations, we introduce a novel method called Heterogeneous Hypergraph Attention Network with Counterfactual Learning $$(\\text {H}^2\\text {CAN}).$$ ( H 2 CAN ) . The method constructs a heterogeneous hypergraph based on sentiment expression characteristics and employs Heterogeneous Hypergraph Attention Networks (HHGAT) to capture interactions beyond pairwise constraints. Furthermore, it mitigates the effects of bias through a Counterfactual Intervention Task (CIT). Our model comprises two main branches: hypergraph fusion and counterfactual fusion. The former uses HHGAT to capture inter-modality interactions, while the latter constructs a counterfactual world using Gaussian distribution and additional weighting for the biased modality. The CIT leverages causal inference to maximize the prediction discrepancy between the two branches, guiding attention learning in the hypergraph fusion branch. We utilize unimodal labels to help the model adaptively identify the biased modality, thereby enhancing the handling of bias information. Experiments on three mainstream datasets demonstrate that $$\\text {H}^2\\text {CAN}$$ H 2 CAN sets a new benchmark.

Social behavior in human and animal populations can be studied as an evolutionary process. Individuals often make decisions between different strategies, and those strategies that yield a fitness advantage tend to spread. Traditionally, much work in evolutionary game theory considers symmetric games: individuals are assumed to have access to the same set of strategies, and they experience the same payoff consequences. As a result, they can learn more profitable strategies by imitation. However, interactions are oftentimes asymmetric. In that case, imitation may be infeasible (because individuals differ in the strategies they are able to use), or it may be undesirable (because individuals differ in their incentives to use a strategy). Here, we consider an alternative learning process which applies to arbitrary asymmetric games, introspection dynamics . According to this dynamics, individuals regularly compare their present strategy to a randomly chosen alternative strategy. If the alternative strategy yields a payoff advantage, it is more likely adopted. In this work, we formalize introspection dynamics for pairwise games. We derive simple and explicit formulas for the abundance of each strategy over time and apply these results to several well-known social dilemmas. In particular, for the volunteer’s timing dilemma, we show that the player with the lowest cooperation cost learns to cooperate without delay.

In this paper, we propose leveraging causal generative learning as an interpretable tool for explaining image classifiers. Specifically, we present a generative counterfactual inference approach to study the influence of visual features (pixels) as well as causal factors through generative learning. To this end, we first uncover the most influential pixels on a classifier’s decision by computing both Shapely and contrastive explanations for counterfactual images with different attribute values. We then establish a Monte Carlo mechanism using the generator of a causal generative model in order to adapt Shapley explainers to produce feature importances for the human-interpretable attributes of a causal dataset. This method is applied to the case where a classifier has been trained exclusively on the images of the causal dataset. Finally, we present optimization methods for creating counterfactual explanations of classifiers by means of counterfactual inference, proposing straightforward approaches for both differentiable and arbitrary classifiers. We exploit the Morpho-MNIST causal dataset as a case study for exploring our proposed methods for generating counterfactual explanations. However, our methods are applicable also to other causal datasets containing image data. We employ visual explanation methods from the OmnixAI open source toolkit to compare them with our proposed methods. By employing quantitative metrics to measure the interpretability of counterfactual explanations, we find that our proposed methods of counterfactual explanation offer more interpretable explanations compared to those generated from OmnixAI. This finding suggests that our methods are well-suited for generating highly interpretable counterfactual explanations on causal datasets.

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 relations. 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 development 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 examples, 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 evaluation metrics. This survey aims to serve as a “one-stop-shop” for building a unified understanding of graph counterfactual learning categories and current resources.

The model‐free algorithms of “reinforcement learning” (RL) have gained clout across disciplines, but so too have model‐based alternatives. The present study emphasizes other dimensions of this model space in consideration of associative or discriminative generalization across states and actions. This “generalized reinforcement learning” (GRL) model, a frugal extension of RL, parsimoniously retains the single reward‐prediction error (RPE), but the scope of learning goes beyond the experienced state and action. Instead, the generalized RPE is efficiently relayed for bidirectional counterfactual updating of value estimates for other representations. Aided by structural information but as an implicit rather than explicit cognitive map, GRL provided the most precise account of human behavior and individual differences in a reversal‐learning task with hierarchical structure that encouraged inverse generalization across both states and actions. Reflecting inference that could be true, false (i.e., overgeneralization), or absent (i.e., undergeneralization), state generalization distinguished those who learned well more so than action generalization. With high‐resolution high‐field fMRI targeting the dopaminergic midbrain, the GRL model's RPE signals (alongside value and decision signals) were localized within not only the striatum but also the substantia nigra and the ventral tegmental area, including specific effects of generalization that also extend to the hippocampus. Factoring in generalization as a multidimensional process in value‐based learning, these findings shed light on complexities that, while challenging classic RL, can still be resolved within the bounds of its core computations. This “generalized reinforcement learning” (GRL) model, a frugal extension of RL, parsimoniously retains the single reward‐prediction error (RPE), but the scope of learning goes beyond the experienced state and action. Aided by structural information but as an implicit rather than explicit cognitive map, GRL provided the most precise account of human behavior and individual differences in a reversal‐learning task with hierarchical structure that encouraged inverse generalization across both states and actions. With high‐resolution high‐field fMRI targeting the dopaminergic midbrain, the GRL model's RPE signals (alongside value and decision signals) were localized within not only the striatum but also the substantia nigra and the ventral tegmental area, including specific effects of generalization that also extend to the hippocampus.

Most multimodal recommender systems utilize multimodal content of user-interacted items as supplemental information to capture user preferences based on historical interactions without considering user-uninteracted items. In contrast, multimodal recommender systems based on causal inference counterfactual learning utilize the causal difference between the multimodal content of user-interacted and user-uninteracted items to purify the content related to user preferences. However, existing methods adopt a unified multimodal channel, which treats each modality equally, resulting in the inability to distinguish users’ tastes for different modalities. Therefore, the differences in users’ attention and perception of different modalities' content cannot be reflected. To cope with the above issue, this paper proposes a novel recommender system based on multi-channel counterfactual learning (MCCL) networks to capture user fine-grained preferences on different modalities. First, two independent channels are established based on the corresponding features for the content of image and text modalities for modality-specific feature extraction. Then, leveraging the counterfactual theory of causal inference, features in each channel unrelated to user preferences are eliminated using the features of the user-uninteracted items. Features related to user preferences are enhanced and multimodal user preferences are modeled at the content level, which portrays the users' taste for the different modalities of items. Finally, semantic entities are extracted to model semantic-level multimodal user preferences, which are fused with historical user interaction information and content-level user preferences for recommendation. Extensive experiments on three different datasets show that our results improve up to 4.17% on NDCG compared to the optimal model.

Multimodal sentiment analysis (MSA) has garnered significant attention for its immense potential in human-computer interaction. While cross-modality attention mechanisms are widely used in MSA to capture inter-modality interactions, existing methods are limited to pairwise interactions between two modalities. Additionally, these methods can not utilize the causal relationship to guide attention learning, making them susceptible to bias information. To address these limitations, we introduce a novel method called Heterogeneous Hypergraph Attention Network with Counterfactual Learning ( H 2 CAN ) . The method constructs a heterogeneous hypergraph based on sentiment expression characteristics and employs Heterogeneous Hypergraph Attention Networks (HHGAT) to capture interactions beyond pairwise constraints. Furthermore, it mitigates the effects of bias through a Counterfactual Intervention Task (CIT). Our model comprises two main branches: hypergraph fusion and counterfactual fusion. The former uses HHGAT to capture inter-modality interactions, while the latter constructs a counterfactual world using Gaussian distribution and additional weighting for the biased modality. The CIT leverages causal inference to maximize the prediction discrepancy between the two branches, guiding attention learning in the hypergraph fusion branch. We utilize unimodal labels to help the model adaptively identify the biased modality, thereby enhancing the handling of bias information. Experiments on three mainstream datasets demonstrate that H 2 CAN sets a new benchmark.

Background Learning policies for decision-making, such as recommending treatments in clinical settings, is important for enhancing clinical decision-support systems. However, the challenge lies in accurately evaluating and optimizing these policies for maximum efficacy. This paper addresses this gap by focusing on two key aspects of policy learning: evaluation and optimization. Method We develop counterfactual policy learning algorithms for practical clinical applications to suggest viable treatment for patients. We first design a bootstrap method for counterfactual assessment and enhancement of policies, aiming to diminish uncertainty in clinical decisions. Building on this, we introduce an innovative adversarial learning algorithm, inspired by bootstrap principles, to further advance policy optimization. Results The efficacy of our algorithms was validated using both semi-synthetic and real-world clinical datasets. Our method outperforms baseline algorithms, reducing the variance in policy evaluation by 30% and the error rate by 25%. In policy optimization, it enhances the reward by 1% to 3%, highlighting the practical value of our approach in clinical decision-making. Conclusion This study demonstrates the effectiveness of combining bootstrap and adversarial learning techniques in policy learning for clinical decision support. It not only enhances the accuracy and reliability of policy evaluation and optimization but also paves avenues for leveraging advanced counterfactual machine learning in healthcare.

Decision-making is strongly influenced by the counterfactual anticipation of personal regret and relief, through a learning process involving the ventromedial-prefrontal cortex. We previously reported that observing the regretful outcomes of another's choices reactivates the regret-network. Here we extend those findings by investigating whether this resonant mechanism also underpins interactive-learning from others' previous outcomes. In this functional-Magnetic-Resonance-Imaging study 24 subjects either played a gambling task or observed another player's risky/non-risky choices and resulting outcomes, thus experiencing personal or shared regret/relief for risky/non-risky decisions. Subjects' risk-aptitude in subsequent choices was significantly influenced by both their and the other's previous outcomes. This influence reflected in cerebral regions specifically coding the effect of previously experienced regret/relief, as indexed by the difference between factual and counterfactual outcomes in the last trial, when making a new choice. The subgenual cortex and caudate nucleus tracked the outcomes that increased risk-seeking (relief for a risky choice, and regret for a non-risky choice), while activity in the ventromedial-prefrontal cortex, amygdala and periaqueductal gray-matter reflected those reducing risk-seeking (relief for a non-risky choice, and regret for a risky choice). Crucially, a subset of the involved regions was also activated when subjects chose after observing the other player's outcomes, leading to the same behavioural change as in a first person experience. This resonant neural mechanism at choice may subserve interactive-learning in decision-making. ►Risk-aptitude is influenced by both 1st and 3rd-person previous regret and relief ►Specific brain regions track previous regret and relief outcomes at the next choice ►Distinct regions track the previous outcomes that increase or decrease risk-seeking ►The regions tracking past outcomes are also active after observing others' outcomes ►A resonant neural mechanism may subserve interactive-learning in decision-making

Can machine learning improve human decision making? Bail decisions provide a good test case. Millions of times each year, judges make jail-or-release decisions that hinge on a prediction of what a defendant would do if released. The concreteness of the prediction task combined with the volume of data available makes this a promising machine-learning application. Yet comparing the algorithm to judges proves complicated. First, the available data are generated by prior judge decisions. We only observe crime outcomes for released defendants, not for those judges detained. This makes it hard to evaluate counterfactual decision rules based on algorithmic predictions. Second, judges may have a broader set of preferences than the variable the algorithm predicts; for instance, judges may care specifically about violent crimes or about racial inequities. We deal with these problems using different econometric strategies, such as quasi-random assignment of cases to judges. Even accounting for these concerns, our results suggest potentially large welfare gains: one policy simulation shows crime reductions up to 24.7% with no change in jailing rates, or jailing rate reductions up to 41.9% with no increase in crime rates. Moreover, all categories of crime, including violent crimes, show reductions; these gains can be achieved while simultaneously reducing racial disparities. These results suggest that while machine learning can be valuable, realizing this value requires integrating these tools into an economic framework: being clear about the link between predictions and decisions; specifying the scope of payoff functions; and constructing unbiased decision counterfactuals.