Defines explanations for classifier outcomes using causal concepts.
problem Understanding classifier outcomes in a causal context.
method Proposes a new definition of explanation based on causality, compares it with existing notions, and evaluates it experimentally.
result Experimental evaluation shows the new definition's effectiveness on financial datasets.
Prevalent theories in cognitive science propose that humans understand and represent the knowledge of the world through causal relationships. In making sense of the world, we build causal models in our mind to encode cause-effect relations of events and use these to explain why new events happen. In this paper, we use …
Develops causal explanations for black-box classifiers.
problem Creating understandable explanations for complex models.
method Generative model with information-theoretic measures of causal influence.
result Learned latent factors influence classifier outputs.
OrphicX generates causal explanations for GNNs by isolating latent causal factors.
problem Generating interpretable causal explanations for complex graph neural networks.
method Develops a generative model and objective function to isolate latent causal factors, maximizing information flow.
result OrphicX effectively identifies causal semantics, significantly outperforming alternatives.
Language helps RL agents learn complex relational and causal structures.
problem Learning relational and causal structure in complex environments.
method Training RL agents to predict language descriptions and explanations.
result Language aids agents in learning challenging relational and causal tasks.
BRACE generates efficient counterfactual explanations by integrating causal reasoning.
problem Challenges in traditional counterfactual explanations, especially neglecting causal relationships.
method Backtracking counterfactuals with causal reasoning.
result Our method provides deeper insights into model outputs and is computationally efficient.
CLEAR learns causal graphs from attention in recommender systems to explain user behavior.
problem Understanding why specific recommendations are made in recommender systems.
method CLEAR learns session-specific causal graphs from attention in pre-trained neural recommenders, addressing latent confounders.
result CLEAR provides counterfactual explanations that are shorter and more effective than naive methods.
Develops logic programs for explaining classification model decisions.
problem Creating explanations for decisions made by classification models.
method Answer-set programs for computing counterfactual interventions.
result Maximum responsibility causal explanations can be computed.
New method quantifies intrinsic causal contributions in neural networks.
problem Measuring the causal influence of input features in deep neural networks.
method Proposes an identifiable generative post-hoc framework to quantify intrinsic causal contributions (ICC) as structural causal models.
result ICC generates more intuitive and reliable explanations compared to existing global explanation techniques.
Symmetric observations don't necessarily imply symmetric causal explanations.
problem Inferring causal models from observed correlations is challenging and computationally intensive.
method An explicit example using a tripartite probability distribution over binary events.
result Symmetries in observations cannot be used to reduce the hypothesis space of causal models.
Recourse explanations can become invalid if collective actions change statistical data.
problem Recourse explanations may become invalid due to collective behavior changing data statistics.
method Formal characterization of conditions under which recourse explanations remain valid under performativity.
result Recourse actions may become invalid if they are influenced by or intervene on non-causal variables.
Model explanations based on pure observational data cannot compute the effects of features reliably, due to their inability to estimate how each factor alteration could affect the rest. We argue that explanations should be based on the causal model of the data and the derived intervened causal models, that represent th…
CEILS generates feasible counterfactual explanations by considering causal impacts.
problem Current counterfactual explanations lack feasibility and causal impact consideration.
method CEILS integrates causal reasoning into existing counterfactuals generation algorithms.
result CEILS provides feasible recommendations to achieve desired outcomes.
Study evaluates counterfactual explanations using Pearl's method.
problem Bias in counterfactual explanations generated from machine learning models.
method Evaluates counterfactual explanations using Judea Pearl's counterfactual method.
result Thirty percent of counterfactual explanations conflicted with Pearl's method.
Study on the relationship between explanations and predictions in machine learning models.
problem Understanding the relationship between explanations and predictions in machine learning models.
method Causal inference to measure treatment effect on hyperparameters and inputs.
result The relationship between explanations and predictions is far from ideal, especially in high-performing models.
Proposes a method to explain black-box models using causal learning.
problem Existing explainability methods focus on micro-level inputs, not interpretable features.
method Learns causal graphical representations to differentiate between causal and confounding influences.
result Graphs can differentiate between interpretable and confounding features.
Debias concept-based explanations by removing confounding information.
problem Correlation between concepts and confounding features.
method Causal prior graph and two-stage regression technique.
result Success in removing biases and improving concept ranking.
A new framework for robot block-stacking tasks using causal probabilistic models.
problem Robots fail outside controlled environments due to uncertainty and lack of explicit design for all scenarios.
method Causal probabilistic framework combining causal models and probabilistic representations of noise.
result Robots can perceive, reason about, and explain their environment for block-stacking tasks.
Proposes counterfactual explainability for causal attribution, extending variance analysis methods.
problem Lack of mechanistic understanding in existing tools for explaining complex models.
method Extends global sensitivity analysis methods to causal explanations using directed acyclic graphs.
result Developed methods to estimate counterfactual explainability and applied to income inequality analysis.
DeepBC method computes backtracking counterfactuals in deep causal models.
problem Computing valid counterfactuals in complex causal models.
method DeepBC method using Langevin Monte Carlo or constrained optimization.
result DeepBC provides causally compliant, versatile, and modular counterfactuals.
Graph neural network explainer identifies causal subgraphs ensuring predictions.
problem Spurious correlations in GNN explainers.
method Proposes {
ame}, a GNN causal explainer via causal inference.
result Significantly outperforms existing GNN explainers in exact groundtruth explanation identification.
SAGE-FIN detects financial fraud using GNNs and Granger causality.
problem Detecting fraud in financial networks with limited labeled data and lack of explainability.
method Semi-supervised GNN approach with Granger causal explanations.
result SAGE-FIN outperforms on real-world financial network dataset with explainable flagged items.
Predictive models can be used for causal inference with feature selection.
problem Limitations of predictive models in interpreting causal relationships.
method Constrained learning process by selecting features according to Pearl's backdoor adjustment criterion.
result Causal models provide near unbiased effect estimates and better generalization.
To construct interpretable explanations that are consistent with the original ML model, counterfactual examples---showing how the model's output changes with small perturbations to the input---have been proposed. This paper extends the work in counterfactual explanations by addressing the challenge of feasibility of su…
Shapley values for feature importance lead to mathematical and practical issues.
problem Mathematical and practical issues with Shapley values for feature importance.
method Game-theoretic formulations of feature importance using Shapley values.
result Mathematical problems arise when using Shapley values for feature importance.
Feature importance estimates that inform users about the degree to which given inputs influence the output of a predictive model are crucial for understanding, validating, and interpreting machine-learning models. However, providing fast and accurate estimates of feature importance for high-dimensional data, and quanti…
New framework evaluates model explanations based on decision task improvement.
problem Evaluation of model explanations often misses practical value.
method Decision-theoretic framework quantifying three key values.
result Provides benchmarks and interprets human-AI decision support.
CI-GNN uses GNNs to diagnose psychiatric disorders by identifying causally relevant brain regions.
problem Leveraging GNNs for psychiatric diagnosis requires interpretable models to understand decision-making.
method CI-GNN integrates Granger causality into GNNs to identify causally relevant subgraphs.
result CI-GNN provides more reliable and concise explanations of psychiatric diagnoses.
Explaining AI systems is fundamental both to the development of high performing models and to the trust placed in them by their users. The Shapley framework for explainability has strength in its general applicability combined with its precise, rigorous foundation: it provides a common, model-agnostic language for AI e…
In many scientific contexts, different investigators experiment with or observe different variables with data from a domain in which the distinct variable sets might well be related. This sort of fragmentation sometimes occurs in molecular biology, whether in studies of RNA expression or studies of protein interaction,…
Deep neural networks are complex and opaque. As they enter application in a variety of important and safety critical domains, users seek methods to explain their output predictions. We develop an approach to explaining deep neural networks by constructing causal models on salient concepts contained in a CNN. We develop…
Triangulation filters spurious circuits in multilingual models.
problem Unreliable explanations of multilingual models across languages.
method Formalizes reference families and introduces triangulation as a causal acceptance rule.
result Triangulation provides a falsifiable standard for mechanistic claims.
As machine learning is increasingly used to inform consequential decision-making (e.g., pre-trial bail and loan approval), it becomes important to explain how the system arrived at its decision, and also suggest actions to achieve a favorable decision. Counterfactual explanations -- "how the world would have (had) to b…
Post-hoc explanations of machine learning models are crucial for people to understand and act on algorithmic predictions. An intriguing class of explanations is through counterfactuals, hypothetical examples that show people how to obtain a different prediction. We posit that effective counterfactual explanations shoul…
Develops methods for finding counterfactual explanations in sequential decision making.
problem Finding counterfactual explanations for sequential decision making processes.
method Formal characterization of sequential actions and states using Markov decision processes and Gumbel-Max structural causal model. Introduces a polynomial time algorithm based on dynamic programming.
result Algorithm finds optimal counterfactual explanations for sequential decision making.
We study the Johansen-Ledoit-Sornette (JLS) model of financial market crashes (Johansen, Ledoit, and Sornette [2000] "Crashes as Critical Points." Int. J. Theor. Appl. Finan. 3(2) 219-255). On our view, the JLS model is a curious case from the perspective of the recent philosophy of science literature, as it is natural…
This tutorial introduces causal modeling methods for researchers.
problem Understanding causal relationships in research studies.
method Integrates potential outcomes and graphical methods for causal modeling.
result Clear notation and practical examples for applied researchers.
Differentiable causal discovery methods perform robustly under model violations.
problem Causal discovery algorithms struggle with real-world data due to unverifiable causal assumptions.
method Benchmarked differentiable causal discovery methods under eight model assumption violations.
result Differentiable causal discovery methods exhibit robust performance under Structural Hamming Distance and Structural Intervention Distance metrics.
Method finds counterfactual explanations for random forest models.
problem Limited interpretability of random forest models in regulated industries.
method Similarity learning exploiting random forest's feature representation.
result Generated explanations are sparser and more useful than Shapley values.
Measures faithfulness of LLM explanations to reveal hidden biases and misleading claims.
problem LLM explanations can misrepresent the model's reasoning process, leading to over-trust and misuse.
method Defines faithfulness in terms of concept influence and uses counterfactuals and Bayesian models to estimate it.
result Can quantify and discover interpretable patterns of unfaithfulness in LLM explanations.
A new approach to rationalization identifies true rationales by considering causal relationships.
problem Existing rationalization methods struggle with spuriousness, where snippets with similar contributions are hard to distinguish.
method The method leverages causal inference to identify non-spurious rationales, defining probabilities of causation based on a structural causal model.
result The proposed causal rationalization outperforms existing methods on real-world datasets.
CausAdv detects adversarial examples using causal reasoning.
problem Vulnerability of CNNs to adversarial perturbations.
method Causal framework based on counterfactual reasoning.
result Adversarial examples exhibit different CI distributions compared to clean samples.
ISL improves causal structure learning with invariant structures across different environments.
problem Improving causal structure discovery for better generalization and explainability.
method ISL splits data into environments, learns invariant structures, and selects optimal classifiers based on graph structures.
result ISL accurately discovers causal structures and outperforms alternative methods on synthetic and real-world datasets.
The causal compatibility question asks whether a given causal structure graph -- possibly involving latent variables -- constitutes a genuinely plausible causal explanation for a given probability distribution over the graph's observed variables. Algorithms predicated on merely necessary constraints for causal compatib…
Bell's Theorem shows that quantum mechanical correlations can violate the constraints that the causal structure of certain experiments impose on any classical explanation. It is thus natural to ask to which degree the causal assumptions -- e.g. locality or measurement independence -- have to be relaxed in order to allo…
PWSHAP provides targeted explanations for complex models.
problem Inability of black-box models to explain targeted effects in sensitive domains.
method Augments model with DAG, uses Shapley values for causal pathway identification.
result Establishes error bounds and demonstrates resolution, interpretability, and locality.
Proposes an efficient method for ordered counterfactual explanations.
problem Insufficient explanation of perturbation vectors for executing actions.
method Mixed-Integer Linear Optimization (MILP) approach for evaluating and extracting optimal pairs of actions and orders.
result Demonstrated effectiveness of the proposed method on real datasets.
This work explains RL policies using causal models, revealing important patterns and failures.
problem Understanding why RL policies succeed or fail in complex, high-dimensional systems.
method Developed a nonlinear Causal Model Reduction framework to learn simplified causal models from RL policy actions and rewards.
result The approach can uncover important behavioral patterns and failure modes in trained RL policies.