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.
RCAV quantifies model sensitivity to semantic concepts, improving interpretability methods.
problem Lack of semantic interpretability in image classification models.
method RCAV calculates concept gradients and ascent steps to assess model sensitivity to semantic concepts.
result RCAV yields more accurate and robust interpretations of model behavior.
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.
Extends V-IP framework to use LLMs for generating task-relevant concepts, improving interpretability and performance.
problem Limited applicability of V-IP to small-scale tasks due to manual data annotation.
method Integrates Foundational Models with Large Language and Multimodal Models to generate and annotate concepts.
result FM+V-IP achieves better test performance with fewer concepts/queries compared to other frameworks.
BC-LLM uses LLMs to find concepts without predefined sets, improving interpretability and performance.
problem Finding a balance between interpretability and accuracy in concept extraction models.
method Bayesian approach with LLMs as both concept extractor and prior.
result BC-LLM outperforms interpretable and black-box models across various datasets.
LCBM model improves image classification without human supervision.
problem Improving interpretability and generalization of unsupervised concept-based models.
method LCBM models concepts as random variables in a Bernoulli latent space, reducing the number of concepts without sacrificing performance.
result LCBM outperforms existing models in generalization and interpretability.
New framework quantifies and reduces concept-based models' leakage.
problem Information leakage in concept-based models reduces interpretability.
method Information-theoretic framework with CTL and ICL measures.
result Measures predict model behaviour and identify leakage causes.
This work improves interpretability in deep learning models by introducing a two-level concept discovery framework.
problem High complexity and lack of interpretability in deep learning models, especially for safety-critical tasks.
method Concept Bottleneck Models (CBMs) framework combining vision-language models and data-driven coarse-to-fine concept selection.
result The proposed framework outperforms recent CBM approaches and provides a principled interpretability.
Geometric framework detects concept frustration between human concepts and machine representations.
problem Aligning human concepts with machine learning representations.
method Geometric framework and similarity measures for detecting concept frustration.
result Concept frustration affects machine learning model performance and reorganizes learned concept representations.
A new framework for interpretable models using sparse linear layers.
problem Performance degradation and lower interpretability in concept bottleneck models.
method Contrastive Language Image models and a single sparse linear layer with Bayesian inference.
result Our framework outperforms recent CBM approaches in accuracy and concept sparsity.
CBMs improve interpretability in RUL prediction for aircraft engines.
problem Lack of interpretability in deep learning models for asset prognostics.
method Concept Bottleneck Models (CBMs) for RUL prediction.
result CBMs achieve comparable or superior performance to black-box models while being more interpretable.
Unified approach to learn interpretable concepts from data.
problem Building interpretable machine learning models and highly-performing foundation models.
method Relating causal representation learning and foundation models, defining concepts and proving their recoverability.
result Provable recovery of human-interpretable concepts from diverse data.
New models handle survival analysis with concept-based learning.
problem Survival analysis tasks involving event times with censored data.
method SurvCBM and SurvRCM models integrating concept-based learning with survival analysis.
result SurvCBM outperforms traditional survival models in numerical experiments.
PCBMs turn any neural network into interpretable models without dense annotations.
problem Restrictive nature of CBMs and lack of dense concept annotations in training data.
method Introduce PCBMs that can turn any neural network into interpretable models without dense annotations.
result PCBMs can turn any neural network into interpretable models without dense annotations, improving interpretability and performance.
Framework learns interpretable concepts from data without interventions.
problem Learning spurious correlations between concepts in CBMs.
method Causal representation learning (CRL) to align latent variables with interpretable concepts using few labels.
result Framework provides theoretical guarantees on correctness and number of required labels without interventions.
New method learns interpretable concepts from user feedback for high-dimensional data.
problem Lack of interpretable concepts in machine learning models trained on high-dimensional tabular data.
method Proposes a method for learning transparent concept definitions from user labeling of concept features, not instances.
result Demonstrates more efficient learning of aligned concept definitions from user feedback compared to alternative transparent approaches.
ECBMs unify concept-based interpretations in deep learning models.
problem Suboptimal final accuracy and lack of concept interaction and conditional dependencies.
method ECBMs use a set of neural networks to define joint energy, enabling concept correction and conditional dependency quantification.
result ECBMs achieve higher accuracy and richer concept interpretations compared to state-of-the-art methods.
CREAM models enable concept-grounded predictions and interpretability.
problem Designing models that can encode and extend prior knowledge about concept-concept and concept-task relationships.
method Proposes a flexible and efficient framework (CREAMs) that encodes arbitrary C−C and CoY relationships, incorporating a side-channel for incomplete concept sets. result CREAM models achieve competitive task performance while encouraging concept-grounded predictions, avoiding concept leakage and achieving black-box-level performance.
Concept-driven OPE reduces variance in off-policy decision evaluation.
problem High variance in off-policy decision evaluation due to limited sample sizes.
method Integrating human-explainable concepts into OPE to reduce variance.
result Concept-based OPE estimators remain unbiased and reduce variance when concepts are known and predefined.
Concept bottleneck models enable concept manipulation for model interpretation.
problem Training models to directly predict labels without intermediate concepts.
method Train models to predict intermediate concepts at training time, then use these concepts to predict labels.
result Concept bottleneck models achieve competitive accuracy with standard models while enabling concept manipulation.
In an attempt to gather a deeper understanding of how convolutional neural networks (CNNs) reason about human-understandable concepts, we present a method to infer labeled concept data from hidden layer activations and interpret the concepts through a shallow decision tree. The decision tree can provide information abo…
Improves interpretability of neural network intermediate layers by making concept activations more robust and effective.
problem Challenges in interpreting neural network decisions and learning in intermediate layers due to opacity and shared interactions.
method Proposes A-CAV to increase effectiveness and employs Gram-Schmidt process to improve robustness.
result Significant improvement in recall rate of concept images from 18.35% to 76.83% for VGG16, with reduced variance in recall across different random seeds.
Proposes new methods for interpreting document classification models.
problem Interpretation fragility of attention-based neural networks.
method Corpus-level and concept-based explanation methods using attention weights.
result Extracts semantically meaningful keywords and concepts for model predictions.
Method makes non-interpretable models more intervenable.
problem Making non-interpretable models more understandable and controllable.
method Intervenability formalization and fine-tuning of black-box models.
result Fine-tuned black-box models are more intervenable and often better-calibrated.
New method extracts biological concepts from cell microscopy images.
problem Extracting meaningful concepts from vision foundation models trained on cell microscopy images.
method Sparse dictionary learning (DL) combined with PCA whitening pre-processing.
result Successfully retrieved biologically meaningful concepts like cell types and genetic perturbations.
Interpretable surrogates of black-box predictors trained on high-dimensional tabular datasets can struggle to generate comprehensible explanations in the presence of correlated variables. We propose a model-agnostic interpretable surrogate that provides global and local explanations of black-box classifiers to address …
VICE embeds concepts in a vector space using human data.
problem Developing numerical models for mental representations of object concepts.
method Variational Interpretable Concept Embeddings (VICE) using variational inference and triplet odd-one-out task data.
result VICE outperforms SPoSE at predicting human behavior and provides more reproducible object representations.
In this paper we propose and study the novel problem of explaining node embeddings by finding embedded human interpretable subspaces in already trained unsupervised node representation embeddings. We use an external knowledge base that is organized as a taxonomy of human-understandable concepts over entities as a guide…
CW normalizes and decorrelates neural network layers for better concept understanding.
problem Challenges in understanding neural network hidden layers.
method Introducing concept whitening (CW) to alter neural network layers.
result CW provides clearer understanding of how networks learn concepts over layers.
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.
Human explanations of high-level decisions are often expressed in terms of key concepts the decisions are based on. In this paper, we study such concept-based explainability for Deep Neural Networks (DNNs). First, we define the notion of completeness, which quantifies how sufficient a particular set of concepts is in e…
Interpretable representations improve explainable AI by translating complex data into understandable concepts.
problem Many explainers use interpretable representations but overlook their full potential and assumptions.
method An in-depth analysis of interpretable representations for tabular, image, and text data, identifying strengths, weaknesses, and desiderata.
result Linear model quantifies interpretable concepts' influence on black-box predictions, revealing their explanatory properties and manipulability.
Providing explanations along with predictions is crucial in some text processing tasks. Therefore, we propose a new self-interpretable model that performs output prediction and simultaneously provides an explanation in terms of the presence of particular concepts in the input. To do so, our model's prediction relies so…
Interpretability has become an important topic of research as more machine learning (ML) models are deployed and widely used to make important decisions. Most of the current explanation methods provide explanations through feature importance scores, which identify features that are important for each individual input. …
COMET learns concepts for few-shot learning, improving performance.
problem Few-shot learning challenges in machine learning.
method Meta-learning with human-interpretable concept dimensions.
result Significant improvement in 1-shot learning tasks.
The interpretation of deep learning models is a challenge due to their size, complexity, and often opaque internal state. In addition, many systems, such as image classifiers, operate on low-level features rather than high-level concepts. To address these challenges, we introduce Concept Activation Vectors (CAVs), whic…
PCBM improves neural network generalization by partially observing concepts.
problem Decreased generalization performance due to observing all concepts in CBM.
method Developed a theoretical analysis of PCBM's Bayesian generalization error.
result PCBM's generalization error is lower than CBM's due to partial concept observation.
This work abstracts deep neural networks into concept graphs for better interpretability in medical tasks.
problem Lack of interpretability in deep learning models, especially in medical domains.
method Developed a graphical representation of medical image processing models to understand concept-based reasoning.
result Extracted a concept-level graph that reveals the decision-making process of deep learning models.
The last decade has seen huge progress in the development of advanced machine learning models; however, those models are powerless unless human users can interpret them. Here we show how the mind's construction of concepts and meaning can be used to create more interpretable machine learning models. By proposing a nove…
Recently, interpretable models called self-explaining models (SEMs) have been proposed with the goal of providing interpretability robustness. We evaluate the interpretability robustness of SEMs and show that explanations provided by SEMs as currently proposed are not robust to adversarial inputs. Specifically, we succ…
Interpretable ML methods for better decision-making with explanations.
problem Lack of transparency in black-box ML models.
method Use of Formal Concept Analysis and cooperative game theory to assess attribute importance and reduce attribute count.
result Developed methods to assess attribute importance and reduce attribute count in ML models.
Improved scalability and interpretability in training data attribution.
problem Identifying which training data drives specific behaviors, especially unintended ones.
method Leveraging interpretable structures within the model to attribute model behavior to semantic directions, not individual test examples.
result Simple probe-based attribution methods are first-order approximations of Concept Influence that achieve comparable performance while being over an order-of-magnitude faster.
COCKATIEL explains neural net models on NLP tasks by identifying meaningful concepts.
problem Transformer models are complex and hard to interpret.
method COCKATIEL uses NMF and sensitivity analysis to identify and rank concepts used by the model.
result COCKATIEL provides accurate and meaningful explanations without affecting model performance.
CB-SLICE identifies concept-based error slices in deep learning models.
problem Systematic errors in deep learning models on specific groups.
method Concept Bottleneck Models (CBMs) and concept representations.
result CB-SLICE outperforms state-of-the-art methods in error slice identification.
A theory for approximating complex concepts with simple decision trees.
problem Approximating complex concepts with simple decision trees.
method Introducing interpretable approximations, studying binary concept approximation by decision trees.
result A trichotomy of cases for approximating a binary concept by decision trees based on a simple class.
Deep learning skin lesion classifier explained using CAVs.
problem Limited acceptance of deep learning CAD systems due to opaque decision-making.
method Mapped human understandable concepts to RECOD model using CAVs.
result Classifier learns and encodes disease-related concepts in its latent representation.
CA connects visual concepts to neural network representations.
problem Global association of human interpretable concepts with neural network internals.
method Established a taxonomy for CA methods and reviewed state-of-the-art research.
result Unified understanding of CA methods and datasets.
EAMDrift improves time series prediction accuracy by 20%.
problem Handling unpredictable patterns in time series data.
method Combines forecasts from multiple individual predictors, retraining models automatically.
result EAMDrift outperforms individual baseline models by 20%.