In this work, we present an application of Locally Interpretable Machine-Agnostic Explanations to 2-D chemical structures. Using this framework we are able to provide a structural interpretation for an existing black-box model for classifying biologically produced fuel compounds with regard to Research Octane Number. T…
New definition of interpretability makes model design more actionable.
problem Current definitions of interpretability are not actionable and inform users poorly.
method Proposes a new definition of interpretability that is general, simple, and actionable.
result New definition reveals necessary properties for designing interpretable models.
Interpretable text-response modelling for structured outcomes
problem Predicting structured responses alongside textual data
method Joint non-negative matrix factorisation and binomial regression
result Recovering stable response-relevant textual signals
GISST interprets GNNs by combining attention and sparsity for graph structure and node feature importance.
problem Lack of joint consideration of graph structure and node features in GNN interpretation.
method Model-agnostic framework using attention mechanism and sparsity regularization.
result GISST achieves superior node feature and edge explanation precision in synthetic and real-world datasets.
Tracr compiles programs into transformer models for interpretability.
problem Uncertainty in understanding transformer model outputs due to unknown learned programs.
method Tracr compiles human-readable programs into known structure transformer models.
result Known structure of Tracr-compiled models serves as ground-truth for interpretability.
Interpretable framework evaluates structure learning methods for causal discovery from observational data.
problem Evaluation of structure learning methods under assumption violations in causal discovery.
method Six-dimensional evaluation metric (DOS) tailored for causal discovery.
result Amortized causal discovery delivers results with high proximity to the optimal solution.
BL learns interpretable optimization structures from data.
problem Learning interpretable optimization structures from data.
method BL parameterizes a compositional utility function from intrinsically interpretable modular blocks.
result BL supports architectures from single to hierarchical compositions, modeling hierarchical optimization structures.
Enhances tensor regression for interpretability and performance.
problem Interpreting and modeling multidimensional tensor data with structural heterogeneity.
method Generalized Nonnegative Structured Kruskal Tensor Regression (NS-KTR) with hybrid regularization and nonnegativity constraints.
result NS-KTR outperforms conventional methods in synthetic and real hyperspectral datasets.
The paper proposes a method for interpretable mixture density estimation using a tree structure.
problem Complex probability distributions in machine learning models.
method Interpretable tree structure for mixture density estimation with fast inference.
result The method achieves both high speed and interpretability for mixture density estimation.
Geometrically interprets cup products and defines combinatorial Pin structures.
problem Understanding Steenrod's cup products and their geometric interpretation.
method Constructs vector fields and combinatorial frames to interpret cochain-level formulas.
result Geometrically interprets cup products and defines Pin structures combinatorially.
PSI-KT improves KT accuracy and interpretability in learning materials.
problem Optimizing learning materials selection and timing for understanding and retention.
method Hierarchical generative approach using Bayesian inference.
result Superior multi-step predictive accuracy and scalable inference.
Method learns graph structure for multi-task learning, revealing interpretable relationships.
problem Learning relationships among tasks in multi-task learning.
method Simultaneously learns graph structure and model parameters, optimizing the graph structure with the model parameters.
result Reduces generalization error and reveals interpretable sparse graph among tasks.
DiSeNE generates interpretable node embeddings without supervision.
problem Lack of interpretability in unsupervised node embeddings.
method Disentangled representation learning with novel objective functions and metrics.
result DiSeNE produces interpretable node embeddings aligned with graph structure.
K-Models clusters functional data with ordinal constraints for better interpretability.
problem Challenges in extracting meaningful insights from functional data due to lack of interpretability.
method Integrates ordinal constraints into clustering to improve interpretability and structure identification.
result Enhances interpretability of clustering results while maintaining performance.
DCIts interprets complex time series data with interpretable coefficients.
problem Interpreting nonlinear multivariate time series data.
method Deep convolutional architecture with a Focuser and Modeler components.
result DCIts provides interpretable coefficients and interaction patterns.
Interpretable meta-learning for physical systems reduces computational costs and improves interpretability.
problem Challenges in learning from heterogeneous experimental data.
method Affine structure learning model for multi-environment generalization.
result Proves the model can identify physical parameters and demonstrates competitive performance.
The Dirichlet Belief Network~(DirBN) has been recently proposed as a promising approach in learning interpretable deep latent representations for objects. In this work, we leverage its interpretable modelling architecture and propose a deep dynamic probabilistic framework -- the Recurrent Dirichlet Belief Network~(Recu…
ReGEN-TAD detects anomalies in financial time series with interpretable models.
problem Detecting anomalies in complex financial time series with high-dimensional data.
method Integrates machine learning with econometric diagnostics in a refined convolutional--transformer architecture.
result Unified anomaly score without labeled data, robust to structured deviations.
The workshop focuses on AI principles for structured data.
problem Using AI on structured data for decision-making.
method Addressing principles of privacy, accountability, interpretability, robustness, and reasoning.
result Designing approaches to use structured data for reliable decisions.
DCR improves interpretability of concept-based models by using neural networks to build rule structures.
problem Inability of concept-based models to provide transparent decision processes.
method DCR uses neural networks to build syntactic rule structures using concept embeddings and executes these rules on concept truth degrees.
result DCR improves interpretability by up to 25% on challenging benchmarks and discovers meaningful logic rules.
Linear attention in Transformers can be interpreted as dynamic VAR models.
problem Misalignment between Transformers and autoregressive forecasting objectives.
method Interpreting linear attention as VAR, rearranging MLP, attention, and flow.
result SAMoVAR improves performance, interpretability, and efficiency.
Proposes PRMs for interpreting financial risk concept drift.
problem Concept drift in high-stakes predictions like credit risk.
method Probabilistic Rule Models (PRMs) using Markov Logic Networks.
result Interpretable rules explain borrower risk changes.
This paper proposes a hierarchical, fine-grained and interpretable latent variable model for prosody based on the Tacotron 2 text-to-speech model. It achieves multi-resolution modeling of prosody by conditioning finer level representations on coarser level ones. Additionally, it imposes hierarchical conditioning across…
Defines contact structures on Heisenberg groups for geometric interpretation.
problem Finding a geometric interpretation for the Yamabe equation on Heisenberg groups.
method Defines contact structures of Heisenberg type, introduces a natural connection, and computes conformal scalar curvature.
result Establishes equivalence between contact Riemannian manifolds and contact structures of Heisenberg type.
New framework for interpretable firm characteristics factors.
problem Creating statistically efficient and economically interpretable factors from firm characteristics.
method Grouping related characteristics and deriving one factor per group, combining economic intuition with data-driven clustering.
result Parsimonious, transparent factors outperform benchmarks in out-of-sample tests.
GAMI-Net improves neural network interpretability while maintaining accuracy.
problem Lack of interpretability in neural network models.
method GAMI-Net is a disentangled feedforward network with multiple additive subnetworks designed for capturing main effects and pairwise interactions, considering sparsity, heredity, and marginal clarity.
result GAMI-Net achieves superior interpretability and competitive prediction accuracy compared to explainable boosting machine and other models.
Paper compares econometric models with machine learning for energy forecasting.
problem Tackles the trade-off between predictive accuracy and interpretability in energy markets.
method Integrates TVP-SVAR with copulas for forecasting energy--macro dynamics.
result Copula-enhanced econometric models provide interpretable insights while matching machine learning accuracy.
New methods interpret clustering outcomes without altering data structure.
problem Post-processing methods destroy data integrity and obscure interpretations.
method Algorithm-agnostic interpretation methods using permutation feature importance, individual conditional expectation, and partial dependence.
result Preserves original feature structure and explains clustering outcomes.
Most research on the interpretability of machine learning systems focuses on the development of a more rigorous notion of interpretability. I suggest that a better understanding of the deficiencies of the intuitive notion of interpretability is needed as well. I show that visualization enables but also impedes intuitiv…
Combining additive models and neural networks allows to broaden the scope of statistical regression and extend deep learning-based approaches by interpretable structured additive predictors at the same time. Existing attempts uniting the two modeling approaches are, however, limited to very specific combinations and, m…
Pruning is a standard technique for removing unnecessary structure from a neural network to reduce its storage footprint, computational demands, or energy consumption. Pruning can reduce the parameter-counts of many state-of-the-art neural networks by an order of magnitude without compromising accuracy, meaning these n…
Novel ternary structures reveal new interpretations of linear connections.
problem Examining the ternary structure of Lie algebroid connections.
method Study of endomorphisms and explicit presentation of the endomorphism truss.
result Explicitly presented endomorphism truss of linear connections.
MuVI models multi-view data with structured sparsity, integrating domain knowledge.
problem Disentangling variation across multiple data views in complex systems.
method Multi-view latent variable model with structured sparsity using a modified horseshoe prior.
result MuVI outperforms state-of-the-art methods in structured sparsity modeling and integrates noisy domain expertise.
VALC provides concept-level interpretations of FLMs, overcoming word-level limitations.
problem Lack of higher-level structure interpretation in FLMs' attention weights.
method Formal definition of conceptual interpretation, variational Bayesian framework (VALC).
result VALC finds optimal language concepts for FLM predictions, providing concept-level interpretations.
This paper proposes a method to reveal task relationships in multi-task learning models using sparse graphs.
problem Understanding the underlying task relationships in multi-task learning models.
method Proposes a bilevel formulation of multi-task learning that induces sparse graphs.
result The method improves interpretability of multi-task learning models without sacrificing generalization performance.
We show how to analyze and interpret the correlation structures, the conditional expectation values and correlation coefficients of exchangeable Bernoulli random variables. We study implied default distributions for the iTraxx-CJ tranches and some popular probabilistic models, including the Gaussian copula model, Beta …
ADHAM provides interpretable survival analysis for healthcare.
problem Limited interpretability in deep learning survival models.
method Additive Deep Hazard Analysis Mixtures (ADHAM) with latent subgroup structure.
result ADHAM offers interpretable insights into exposure-outcome associations.
Geometrically interprets symplectic structure in 3-manifold triangulations.
problem Understanding symplectic structures in 3-manifold triangulations.
method Geometric interpretation and algorithm construction for symplectic basis.
result Algorithm constructs curves forming a symplectic basis.
Principal component analysis (PCA) is an exploratory tool widely used in data analysis to uncover dominant patterns of variability within a population. Despite its ability to represent a data set in a low-dimensional space, the interpretability of PCA remains limited. However, in neuroimaging, it is essential to uncove…
FLANs process each feature separately for better interpretability.
problem Need for interpretable machine learning models in critical scenarios.
method Feature-wise latent representations summed for prediction.
result FLANs enhance interpretability without sacrificing performance.
Bayesian neural networks learn graph structure with interpretable parameters.
problem Learning graph structure from nodal observations in data with uncertainty.
method Introduces novel iterations with independently interpretable parameters and Bayesian neural networks.
result Bayesian neural networks provide well-calibrated uncertainty quantification on graph structure.
The theories of strings and D-branes have motivated the development of non Abelian cohomology techniques in differential geometry, on the purpose to find a geometric interpretation of characteristic classes. The spaces studied here, like orbifolds are not often smooth. In classical differential geometry, non smooth s…
TINs use neural networks to interpret technical indicators for trading.
problem Lack of interpretable neural architectures for technical indicators in trading.
method Introduced TINs, a neural architecture that reformulates technical indicators into trainable modules.
result Improved risk-adjusted performance compared to traditional indicator-based strategies.
This paper extends semi-structured networks to functional data.
problem Maintaining interpretability in functional data analysis while capturing non-linearities and interactions.
method Proposes a functional SSN method that scales well and improves predictive performance.
result The functional SSN method accurately recovers underlying signals and performs favorably compared to competing methods.
SIRUS creates interpretable rules from random forests for regression.
problem Lack of interpretability in complex machine learning models.
method Random forest with rule extraction for stability and simplicity.
result SIRUS produces stable and interpretable rule sets.
It is difficult to quantify structure-property relationships and to identify structural features of complex materials. The characterization of amorphous materials is especially challenging because their lack of long-range order makes it difficult to define structural metrics. In this work, we apply deep learning algori…
Elie Cartan's general equivalence problem is recast in the language of Lie algebroids. The resulting formalism, being coordinate and model-free, allows for a full geometric interpretation of Cartan's method of equivalence via reduction and prolongation. We show how to construct certain normal forms (Cartan algebroids) …
DICCA maps multi-view data into a shared latent space with interpretable components.
problem Learning from multiple related but distinct data views.
method DICCA extends CCA to deep generative networks and uses sparsity-inducing priors for interpretability.
result DICCA effectively disentangles shared and view-specific variations in multi-view data.