XGL uses global explanations to guide human supervision in machine learning.
problem Improving model quality through human-machine interaction.
method XGL employs global explanations to guide human selection of informative examples.
result XGL avoids overselling the model's quality and performs comparably to other strategies.
Interactions such as double negation in sentences and scene interactions in images are common forms of complex dependencies captured by state-of-the-art machine learning models. We propose Mahé, a novel approach to provide Model-agnostic hierarchical éxplanations of how powerful machine learning models, such as deep ne…
GRANITE unifies feature-based explanation methods to reduce disagreement.
problem Disagreement among feature-based explanation methods.
method GRANITE partitions feature space into regions minimizing interaction and distribution influences.
result Unified and consistent feature explanations.
Interactive explanations improve machine learning transparency.
problem Transparency of machine learning predictions for diverse stakeholders.
method Personalized counterfactual explanations and follow-up questions.
result Improved understanding of black-box systems through interactive explanations.
Unified framework for feature-based explanations using ANOVA and game theory.
problem Differences between feature-based explanations methods limit their applicability.
method Introduces a unified framework combining fANOVA and cooperative game theory.
result Uncovered similarities and differences between various explanation techniques.
SurvFD and SurvSHAP-IQ provide interpretable survival models by analyzing feature interactions.
problem Non-additivity of hazard and survival functions limits standard additive explanation methods.
method SurvFD decomposes higher-order effects into time-dependent and time-independent components, extending Shapley interactions to time-indexed functions.
result SurvFD and SurvSHAP-IQ offer a new perspective on survival explanations, explicitly characterizing feature interactions.
DECE visualizes machine learning decisions with counterfactual explanations.
problem Making machine learning models transparent and explainable.
method Interactive visualization system supporting counterfactual explanations at instance- and subgroup-levels.
result DECE enables users to explore and understand machine learning model decisions.
Explainable Artificial Intelligence (XAI)has received a great deal of attention recently. Explainability is being presented as a remedy for the distrust of complex and opaque models. Model agnostic methods such as LIME, SHAP, or Break Down promise instance-level interpretability for any complex machine learning model. …
Archipelago provides interpretable explanations of feature interactions in machine learning models.
problem Interpreting the impact of feature interactions on predictions in machine learning models.
method Archipelago is a novel framework for extracting and attributing feature interactions in a scalable and interpretable manner.
result Archipelago provides significantly more interpretable explanations of feature interactions than comparable methods.
As machine learning becomes more pervasive, there is an urgent need for interpretable explanations of predictive models. Prior work has developed effective methods for visualizing global model behavior, as well as generating local (instance-specific) explanations. However, relatively little work has addressed regional …
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.
System allows users to critique explanations of recommendations.
problem Improving trust and perceived quality in recommendation systems.
method Personalized explanations generated from review texts, with a novel critiquing method.
result Users prefer explanations with critiques over those without.
Interactive framework improves understanding of deep neural networks.
problem False sense of comprehension from static explanation methods.
method Interactive framework allowing exhaustive inspection and testing of decisions.
result Interactive approach leads to better understanding of complex decision boundaries.
A new framework quantifies how model explanations influence each other.
problem Understanding how different model explanations interact and influence each other.
method Introducing the metagame, a conceptual framework for measuring second-order interaction effects of model explanations using Shapley values.
result Meta-attributions provide directional insights into how feature interactions influence model explanations.
Unified local and global explanations through functional decomposition of low dimensional structures.
problem Tackles the challenge of extracting meaningful local and global explanations from machine learning models.
method Proposes a new identification constraint to decompose the global representation into main and interaction components of arbitrary order.
result Unified local and global explanations by connecting partial dependence plots and interventional SHAP values.
Model shows how traders' interactions can create market patterns.
problem Explaining stylized facts in high-frequency trading markets.
method Agent-based model of limit order book trading with zero-intelligence agents.
result Scale-free connectivity between traders reproduces market patterns, while no interaction does not.
Scientists interact with deep learning models to avoid misleading results.
problem Deep neural networks can misinterpret data and achieve high performance by exploiting confounding factors.
method Introduce explanatory interactive learning (XIL) where scientists revise models based on explanations.
result XIL helps prevent misleading results and encourages model trust.
Improves global counterfactual explanations for model recourse.
problem Inability to provide explanations beyond local instances.
method Investigates and improves Actionable Recourse Summaries (AReS) for global counterfactual explanations.
result Develops more efficient and interactive explainability tools.
Hybrid Deep Embedding for aspect-level explanations in recommendations.
problem Challenges in personalization, dynamic explanations, and aspect-level granularity in recommendation systems.
method Proposes Hybrid Deep Embedding (HDE) to learn dynamic embeddings for user and item preferences, and aspect-level quality vectors.
result Demonstrates improved recommending performance and dynamic aspect-level explanations.
New approach models how explanations shift with distribution changes.
problem Model performance drops with changing input data distributions.
method Models explanation shifts and compares them to state-of-the-art techniques.
result Modeling explanation shifts better detects out-of-distribution behavior.
A fast method for finding counterfactual explanations for decision forests.
problem Finding counterfactual explanations for decision forests efficiently.
method Constrain optimization to data-populated regions, reducing to nearest-neighbor search.
result Very fast and realistic counterfactual explanations for decision forests.
Despite outstanding contribution to the significant progress of Artificial Intelligence (AI), deep learning models remain mostly black boxes, which are extremely weak in explainability of the reasoning process and prediction results. Explainability is not only a gateway between AI and society but also a powerful tool t…
Tree-based machine learning models such as random forests, decision trees, and gradient boosted trees are the most popular non-linear predictive models used in practice today, yet comparatively little attention has been paid to explaining their predictions. Here we significantly improve the interpretability of tree-bas…
GADGET framework decomposes global feature effects using recursive partitioning.
problem Misleading global feature effects when feature interactions are present.
method Generalized additive decomposition of global effects (GADGET) based on recursive partitioning.
result Minimizes interaction-related heterogeneity of local feature effects.
GLOBE-CE offers efficient global counterfactual explanations.
problem Lack of reliable and scalable global counterfactual explanations.
method Translation-based approach for global counterfactual explanations.
result GLOBE-CE performs significantly better than current methods across multiple metrics.
Proposes a new model for explainable recommendation systems.
problem Developing predictive models that provide explanations for item recommendations.
method Generalized Additive Models with Manifest and Latent Interactions (GAMMLI).
result Advantages in both predictive performance and explainability.
Formulates approach for guiding explanation types based on user specifications.
problem Creating explainable AI components from user-defined specifications.
method Develops a method for generating explanations based on user-defined specifications.
result Demonstrates feasibility of user-defined explanations for complex models like Bayesian networks and graph neural networks.
New method for explaining dialogue response generation models.
problem Interpreting sequence generation models, especially dialogue response generation.
method Local Explanation of Response Generation (LERG) method.
result LERG improves dialogue response generation explanations compared to existing methods.
Paper identifies problematic baselines in Shapley value explanations and proposes a reweighting mechanism.
problem Identifying and addressing the suboptimality of baselines in Shapley value feature importance analysis.
method Analyzed suboptimality of baselines, identified problematic baseline, generalized uninformativeness, and designed a reweighting mechanism.
result Proposed uncertainty-based reweighting mechanism effectively accelerates computation and improves explanation quality.
Although interactive learning puts the user into the loop, the learner remains mostly a black box for the user. Understanding the reasons behind queries and predictions is important when assessing how the learner works and, in turn, trust. Consequently, we propose the novel framework of explanatory interactive learning…
This research integrates attention into XAI frameworks for better model explanations.
problem Improving the interpretability of transformer models.
method Developed two novel explanation methods: Shapley value decomposition and token-level directional derivatives.
result Attention weights can be meaningfully incorporated into XAI frameworks, enhancing transformer explainability.
Dropout regularizes against high-order interactions by canceling interaction rates.
problem Overfitting to high-order interactions in neural networks.
method Analyzes Dropout through the lens of interaction effects, showing how it effectively cancels out the probability of surviving interactions of different orders.
result Dropout regularizes against high-order interactions by effectively canceling out the probability of surviving interactions of different orders.
Surrogate-based analysis of interactions via local effect smooths
problem Detecting and characterizing feature interactions in machine learning models
method Surrogate-based analysis using generalized additive models
result Empirical validation of effectiveness for pairwise interactions
PIN models feature interactions using a neural network that mimics decision trees.
problem Modeling feature interactions in tabular data for predictive modeling.
method Tree-like Pairwise Interaction Network (PIN) architecture that captures pairwise feature interactions through a shared feed-forward neural network.
result PIN outperforms traditional and modern neural networks benchmarks in predictive accuracy.
This work introduces RISE to explain LLMs more reliably by distinguishing essential context.
problem Identifying which context elements influence LLM outputs reliably.
method RISE (Redundancy-Insensitive Scoring of Explanation) method.
result RISE provides more robust explanations than traditional methods.
One approach to monitoring a dynamic system relies on decomposition of the system into weakly interacting subsystems. An earlier paper introduced a notion of weak interaction called separability, and showed that it leads to exact propagation of marginals for prediction. This paper addresses two questions left open by t…
PredDiff measures prediction changes while marginalizing features, offering new insights into interaction effects.
problem Understanding interaction effects in black-box models.
method Model-agnostic, local attribution method based on probability theory.
result Introduced a new measure for interaction effects between arbitrary feature subsets.
The paper explains credit decisions using Shapley decomposition for adverse actions.
problem Identifying predictors responsible for adverse credit decisions.
method Develops a simple and intuitive approach based on Shapley decomposition for models with low-order interactions.
result Shows the approach generalizes to Shapley decomposition and Baseline Shapley.
Paper addresses feasibility of counterfactual explanations in ML models, especially for critical domains.
problem Feasibility of counterfactual examples in ML models, especially in healthcare and finance.
method Uses partial structural causal models and modified variational autoencoder loss to generate counterfactuals that satisfy feasibility constraints.
result Generated counterfactuals better satisfy feasibility constraints than existing methods.
As artificial intelligence and machine learning algorithms make further inroads into society, calls are increasing from multiple stakeholders for these algorithms to explain their outputs. At the same time, these stakeholders, whether they be affected citizens, government regulators, domain experts, or system developer…
HyperSHAP explains HPO hyperparameters and interactions, improving trust and adoption.
problem Tackling opaque HPO methods and lack of user trust.
method Game-theoretic explainability framework based on Shapley values and interactions.
result Provides insights into hyperparameter contributions and interactions.
CUBE explains models by balanced experiments and contrasts.
problem Post-hoc explanation of trained predictive models.
method Design-based framework using balanced low-high probes.
result Reveals dominant learned effect structure and clarifies query efficiency.
CFRecs uses counterfactual reasoning to improve graph-based recommendations in real estate.
problem Improving model interpretability and actionable insights in graph-based recommender systems.
method A two-stage architecture combining GNN and Graph-VAE to propose minimal yet impactful changes in graph structure and node attributes.
result Demonstrates effectiveness in delivering actionable recommendations for home buyers and sellers.
We provide a unified view of additive explanations for dependent inputs.
problem Challenges in obtaining a tractable representation and estimating the decomposition for dependent inputs.
method Combining Hilbert space methods with generalized functional ANOVA, we build an explicit decomposition Riesz Basis.
result Proposed a simple yet powerful algorithm to estimate the decomposition from data.
This paper reviews some of the phenomenological models which have been introduced to incorporate the scaling properties of financial data. It also illustrates a microscopic model, based on heterogeneous interacting agents, which provides a possible explanation for the complex dynamics of markets' returns. Scaling and m…
A new method captures higher-order interactions in data clusters.
problem Accurately characterizing complex higher-order variable interactions.
method Local Correlation Explanation (CorEx) method: clustering and total correlation.
result Captures higher-order interactions at a local scale.
New method explains feature interactions in neural networks.
problem Understanding feature interactions in deep networks.
method Integrated Hessians, an extension of Integrated Gradients.
result Integrated Hessians explains pairwise feature interactions efficiently and accurately.
MEI model improves knowledge graph completion by efficiently modeling interactions between embeddings.
problem Efficiently modeling interactions between knowledge graph embeddings to predict missing links.
method MEI divides embeddings into partitions and uses Tucker and block term formats to model interactions efficiently.
result Achieves state-of-the-art performance on link prediction tasks.