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.
MCD offers a complete model understanding for high-stake decisions.
problem Local model understanding in XAI methods is not sufficient for high-stake decisions.
method MCD extends concept-based methods to ensure global model understanding via multi-dimensional subspaces.
result MCD provides a complete model understanding, ensuring the model reasoning is related to the actual model.
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.
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.
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.
This review covers learning under concept drift, including detection, understanding, and adaptation.
problem Unforeseeable changes in data distribution over time impact machine learning performance.
method Reviews and analyzes methodologies and techniques for concept drift detection, understanding, and adaptation.
result Establishes a framework for learning under concept drift with three main components.
New method discovers concepts in hidden feature layers using sparse subspace clustering.
problem Local attribution methods fail to identify coherent model behavior across samples.
method Sparse Subspace Clustering (SSCC) for concept discovery.
result Empirically validated method for various image classification tasks.
Proposes a simple method to represent and manipulate concepts using polynomials and moment statistics.
problem Lack of a mathematical framework to define and operate on concepts.
method Characterizes concepts as zero sets of polynomials and uses moment statistics for representation; proposes a dictionary-based method to learn hierarchical structures.
result Signature of concepts can be used to discover common structures and recursively produce higher-level concepts.
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.
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…
The study identifies latent concepts from diverse observations without assuming specific models.
problem Lack of general theoretical support for concept learning.
method Develops a nonparametric framework for identifying latent concepts from multiple classes of observations.
result Correctness guarantees for concept identification without parametric assumptions.
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 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.
New methods identify concepts in trained embeddings reliably without human labels.
problem Identifying interpretable concepts in trained embedding spaces without human labels.
method Explicitly connecting concept discovery to PCA and ICA, proposing novel approaches for dependent concepts.
result Proven methods outperform competitors on a variety of experiments, achieving up to 29% better alignment with ground truth.
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.
Generative concept representations have three major advantages over discriminative ones: they can represent uncertainty, they support integration of learning and reasoning, and they are good for unsupervised and semi-supervised learning. We discuss probabilistic and generative deep learning, which generative concept re…
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.
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.
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…
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.
A new framework forecasts stock trends by mining shared information from concepts.
problem Forecasting stock trends using static concept information limits accuracy.
method Proposes a graph-based framework that mines concept-oriented shared information from both predefined and hidden concepts.
result Improves stock trend forecasting performance through dynamic concept relevance and hidden concept information.
Unified framework for unsupervised concept extraction simplifies guarantees.
problem Establishing guarantees for unsupervised concept extraction.
method Unified theoretical framework, meta-theorem for identifiability.
result Simplifies the task of proving guarantees for concept extraction.
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.
We developed a caching method to speed up concept learning in complex knowledge bases.
problem Complex concept learning requires many instance retrieval calls, increasing runtime.
method Semantics-aware caching that links concepts to instances via crisp set operations.
result Our cache reduces concept retrieval and learning runtime by an order of magnitude.
CAVs reveal latent concept distributions, but are vulnerable to adversarial attacks.
problem Understanding latent concept encodings in AI models.
method Probabilistic perspective on CAVs, deriving mean and covariance.
result CAVs can be adversarially manipulated, highlighting a vulnerability.
A method for concept-based learning using probabilistic inference and expert rules.
problem Concept-based learning with limited training data.
method Divide images into patches, transform into embeddings, cluster, and use frequentist inference to find concepts.
result FI-CBL outperforms concept bottleneck model in small data scenarios.
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.
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.
The paper formalizes how concepts are encoded in text-guided generative models and provides a method to manipulate them.
problem Encoding and manipulating concepts in text-guided generative models.
method Formalizing concepts as subspaces of a representation space, developing algebraic manipulation methods.
result The ability to manipulate concepts in generative models through algebraic operations on the representation.
Researchers apply concept-based explainability to EEG data.
problem Understanding the internal states of complex EEG transformer models.
method Concept Activation Vectors (CAVs) adapted for EEG data, using externally labeled datasets and anatomically defined concepts.
result Both approaches to concept formation yield valuable insights into EEG model representations.
HCBM improves deep learning explainability by non-linear concept aggregation.
problem Lack of explainable and accurate predictions in deep learning for high-stake decisions.
method Introduce Hoeffding Concept Bottleneck Models (HCBM) using Hoeffding functional decomposition of gradient-boosted trees for non-linear and sparse concept aggregation.
result HCBM outperforms standard linear CBM and is robust to interconcept leakage.
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.
This paper studies concept drift detectors for financial time series.
problem Improving accuracy on financial time series with concept drifts.
method Three simple concept drift detectors tailored to financial time series.
result Two of the detectors are as effective as state-of-the-art detectors.
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.
New neural operators learn structured patterns efficiently.
problem Learning and representing complex, structured patterns in data.
method Sparse autoencoder neural operators (SAE-NOs) parameterize concepts as functions, enabling efficient and structured representation.
result SAE-FNOs learn localized patterns and generalize across different scales and discretizations.
Adversarial validation detects concept drift in user targeting systems.
problem Concept drift in user targeting automation systems deteriorates model performance over time.
method Adversarial validation approach to detect and adapt to concept drift.
result Adversarial validation effectively addresses concept drift in user targeting systems.
Extends linear representation hypothesis to categorical and hierarchical concepts in LLMs.
problem Representing concepts without natural contrasts in large language models.
method Formalizes linear representation hypothesis for categorical and hierarchical concepts, proving relationships between concept hierarchy and representation geometry.
result Validated theoretical results on large language models, estimating representations for 900+ concepts.
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.
Interpreting neural network decisions and the information learned in intermediate layers is still a challenge due to the opaque internal state and shared non-linear interactions. Although (Kim et al, 2017) proposed to interpret intermediate layers by quantifying its ability to distinguish a user-defined concept (from r…
In data stream mining, predictive models typically suffer drops in predictive performance due to concept drift. As enough data representing the new concept must be collected for the new concept to be well learnt, the predictive performance of existing models usually takes some time to recover from concept drift. To spe…
Evaluating, explaining, and visualizing high-level concepts in generative models, such as variational autoencoders (VAEs), is challenging in part due to a lack of known prediction classes that are required to generate saliency maps in supervised learning. While saliency maps may help identify relevant features (e.g., p…
Explanations for deep neural network predictions in terms of domain-related concepts can be valuable in medical applications, where justifications are important for confidence in the decision-making. In this work, we propose a methodology to exploit continuous concept measures as Regression Concept Vectors (RCVs) in th…
A new framework detects concept drift in streaming data.
problem Detecting distributional changes in non-stationary data streams.
method Treating model parameters as random variables, ERICS uses information theory measures to identify concept drift.
result ERICS effectively detects concept drift compared to existing methods.
The Internet has rich and rapidly increasing sources of high quality educational content. Inferring prerequisite relations between educational concepts is required for modern large-scale online educational technology applications such as personalized recommendations and automatic curriculum creation. We present PREREQ,…
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.
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.
Tensor decompositions are used in various data mining applications from social network to medical applications and are extremely useful in discovering latent structures or concepts in the data. Many real-world applications are dynamic in nature and so are their data. To deal with this dynamic nature of data, there exis…
CONDA-PM framework helps analyze concept drift in business processes.
problem Analyzing changes in business processes over time.
method Systematic Literature Review and framework development.
result Highlights areas needing research to complement existing efforts.