Introduces PCG for better counterfactual explanations in vision models.
problem Ambiguity in latent-space optimization methods for counterfactual explanations.
method Constructs counterfactuals by tracing geodesics under a perceptually Riemannian metric.
result PCG outperforms baselines and reveals hidden failure modes.
Method explains anomaly detection by generating normal modifications.
problem Complexity of deep learning methods in anomaly detection.
method Generates multiple alternative modifications for anomalies.
result High-quality semantic explanations provided for anomaly detection.
Novel framework explains machine learning models using ontology-based sampling.
problem Generating precise and insightful explanations for machine learning models.
method Ontology-based sampling technique and learnable anchor algorithm.
result Our approach generates more precise and insightful explanations.
New methods create counterfactuals for image regression models.
problem Creating interpretable explanations for regression models in images.
method Two methods using diffusion-based generative models to create counterfactuals.
result Diffusion-based methods produce realistic, semantic, and smooth counterfactuals.
The impressive performance of neural networks on natural language processing tasks attributes to their ability to model complicated word and phrase compositions. To explain how the model handles semantic compositions, we study hierarchical explanation of neural network predictions. We identify non-additivity and contex…
We propose a novel perspective to understand deep neural networks in an interpretable disentanglement form. For each semantic class, we extract a class-specific functional subnetwork from the original full model, with compressed structure while maintaining comparable prediction performance. The structure representation…
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.
We introduce an adversarial method for producing high-recall explanations of neural text classifier decisions. Building on an existing architecture for extractive explanations via hard attention, we add an adversarial layer which scans the residual of the attention for remaining predictive signal. Motivated by the impo…
StylEx trains a GAN to explain classifier decisions in StyleSpace.
problem Creating meaningful image-specific explanations for classifier decisions.
method Training a StyleGAN to learn a classifier-specific StyleSpace, incorporating the classifier model.
result StylEx finds attributes that align with semantic ones and generates human-interpretable explanations.
An extensive body of empirical research has revealed remarkable regularities in the acquisition, organization, deployment, and neural representation of human semantic knowledge, thereby raising a fundamental conceptual question: what are the theoretical principles governing the ability of neural networks to acquire, or…
New insights show embedding lengths correlate with semantic properties.
problem Contrastive embedding norms ignore embedding magnitudes but correlate with semantic properties.
method Formal theoretical framework and analysis of optimization dynamics.
result Embedding lengths encode semantic information as a byproduct of training.
Optimizes explanations for better listener understanding.
problem Insufficient consideration of listener preferences in concept-based explanations.
method Iterative training procedure based on direct preference optimization.
result Pragmatic explanations improve both model accuracy and user understanding.
Post-hoc explanations improve CNNs by replacing final linear layer with k-means classifier.
problem CNNs lack accurate data representation in their built-in prototypes.
method Introduces k-means-based post-hoc explanations for CNNs, leveraging spatial consistency of convolutional receptive fields.
result Using shallower, less compressed feature activations improves semantic fidelity at the cost of slight predictive performance.
LLMs show surprising confidence in their answers, beyond just tokens.
problem LLMs lack meaningful confidence estimates for their responses.
method Semantic calibration test based on local loss optimality and equivalence classes.
result Base LLMs are semantically calibrated across tasks, contrary to expectations.
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.
ADS explains object differences by quantifying and removing underlying properties.
problem Explaining differences between two object images.
method Align-Deform-Subtract (ADS) framework that uses semantic alignments and iterative quantification/removal of differences.
result ADS provides disentangled error measures explaining object differences in terms of underlying properties.
Describes explaining neurons in deep representations using compositional logical concepts.
problem Interpreting neuron behavior in deep neural networks.
method Identifying compositional logical concepts that closely approximate neuron behavior.
result Compositional explanations provide insights into model performance and allow for adversarial example creation.
Explaining the prediction of deep neural networks (DNNs) and semantic image compression are two active research areas of deep learning with a numerous of applications in decision-critical systems, such as surveillance cameras, drones and self-driving cars, where interpretable decision is critical and storage/network ba…
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.
Unified theory explains how data augmentation improves deep learning models.
problem Understanding why data augmentation improves model generalization.
method Unified theoretical framework explaining two key effects: partial semantic feature removal and feature mixing.
result Data augmentation enhances generalization through partial semantic feature removal and feature mixing.
New feature mapping approach improves recommendation accuracy and explainability.
problem Balancing recommendation accuracy and explainability using metadata.
method Maps uninterpretable features to interpretable aspect features, minimizing both prediction and interpretation losses.
result Strong performance in recommendation and explainability, eliminating metadata need.
New framework aims to make neural network explanations more reliable.
problem Current interpretability methods rely on intuition and lack falsifiability.
method Proposes a framework for strongly falsifiable interpretability research.
result Falsifiable interpretability methods can generate meaningful advances in understanding DNNs.
SHAP Distance assesses semantic fidelity of synthetic tabular data.
problem Semantic fidelity of synthetic tabular data is not well evaluated.
method SHAP Distance, defined as cosine distance between global SHAP attribution vectors.
result SHAP Distance detects semantic discrepancies overlooked by standard measures.
Online reviews provided by consumers are a valuable asset for e-Commerce platforms, influencing potential consumers in making purchasing decisions. However, these reviews are of varying quality, with the useful ones buried deep within a heap of non-informative reviews. In this work, we attempt to automatically identify…
Layer-wise Relevance Propagation (LRP) and saliency maps have been recently used to explain the predictions of Deep Learning models, specifically in the domain of text classification. Given different attribution-based explanations to highlight relevant words for a predicted class label, experiments based on word deleti…
GSP improves global average pooling for deep metric learning by learning weights and selecting semantic entities.
problem Improving global average pooling for deep metric learning.
method Generalized Sum Pooling (GSP) method that learns weights and selects semantic entities.
result GSP improves metric learning performance on 4 popular benchmarks.
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…
Graph Neural Networks (GNNs) are a powerful tool for machine learning on graphs.GNNs combine node feature information with the graph structure by recursively passing neural messages along edges of the input graph. However, incorporating both graph structure and feature information leads to complex models, and explainin…
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.
Method generates visual explanations for similarity models without classification.
problem Lack of visual explanations for similarity models trained without classification loss.
method Gradient-based visual attention using learned feature embeddings.
result Attention maps improve model performance and can be used as constraints.
Survey of determinism issues in financial AI systems.
problem Vulnerabilities in reproducibility of financial AI systems.
method Literature review and first-party experiments on public financial datasets.
result Proposed a layered evaluation framework linking modality-specific metrics to audit readiness.
ProtoX-AD: A self-explainable time series anomaly detection framework
problem Lack of explainability in self-supervised time series anomaly detection
method Learning transformation-aware latent representations and interpretable prototypes
result Achieves detection performance comparable to black-box methods while offering more consistent and semantically meaningful explanations
Paper proposes MMD-Sense-Analysis for detecting word sense shifts.
problem Detecting and interpreting shifts in word meanings over time.
method Leverages Maximum Mean Discrepancy (MMD) to identify and explain word sense changes.
result Demonstrates effectiveness of MMD-Sense-Analysis through empirical results.
SAEs struggle with feature consistency across runs, hindering MI reliability.
problem Inconsistency of learned SAE features across different training runs.
method Propose using the Pairwise Dictionary Mean Correlation Coefficient (PW-MCC) to measure feature consistency.
result High levels of feature consistency (0.80 for TopK SAEs on LLM activations) are achievable with appropriate architectural choices.
Improves recommender system explainability by clarifying representation learning.
problem Lack of explainability in recommender systems.
method Proposes a novel explainable recommendation model by improving transparency in representation learning.
result The proposed model learns interpretable representations that are faithful to explanations.
Semantic TrueLearn uses semantic graphs to improve educational recommendation systems.
problem Challenges in handling semantic and hierarchical structure in knowledge areas.
method Introduces a novel learner model that exploits semantic relatedness between knowledge components using a Wikipedia link graph.
result Achieves statistically significant improvements in predictive performance for educational engagement.
We develop a model of how information flows into a market, and derive algorithms for automatically detecting and explaining relevant events. We analyze data from twenty-two "political stock markets" (i.e., betting markets on political outcomes) on the Iowa Electronic Market (IEM). We prove that, under certain efficienc…
Many methods to explain black-box models, whether local or global, are additive. In this paper, we study global additive explanations for non-additive models, focusing on four explanation methods: partial dependence, Shapley explanations adapted to a global setting, distilled additive explanations, and gradient-based e…
AXE evaluates explanations to avoid misleading Rashomon set model selection.
problem Evaluating explanations for Rashomon set models to avoid false selection.
method Proposed AXE method to evaluate explanation quality.
result AXE detects adversarial fairwashing with 100% success rate.
Unified framework for OOD detection using class ratio estimation.
problem Density-based OOD detection is unreliable for OOD images.
method Unified framework that builds energy-based models and employs differing base distributions, directly estimating the density ratio through class ratio estimation.
result Competitive results on OOD image problems compared to recent work.
DeepUnHide uses deep learning to reveal hidden demographic features in recommender systems.
problem Extracting hidden demographic features from recommender systems factors.
method Gradient-based localization in deep learning for feature extraction.
result DeepUnHide outperforms state-of-the-art feature selection methods.
While many models are purposed for detecting the occurrence of significant events in financial systems, the task of providing qualitative detail on the developments is not usually as well automated. We present a deep learning approach for detecting relevant discussion in text and extracting natural language description…
The paper proposes criteria and methods for evaluating and aggregating feature-based model explanations.
problem Lack of quantitative evaluation criteria for feature-based model explanations.
method Developed quantitative evaluation criteria (low sensitivity, high faithfulness, low complexity), devised a framework for aggregation, and derived a new aggregate Shapley value explanation function.
result A new aggregate Shapley value explanation function that minimizes sensitivity.
Transfer learning aims at building robust prediction models by transferring knowledge gained from one problem to another. In the semantic Web, learning tasks are enhanced with semantic representations. We exploit their semantics to augment transfer learning by dealing with when to transfer with semantic measurements an…
New definition reveals encoding explanations that retain predictive power.
problem Challenges in evaluating and identifying encoding explanations.
method Developed a definition of encoding based on conditional dependence.
result Existing evaluation scores do not rank non-encoding explanations correctly, but STRIPE-X does.
Supervisory signals have the potential to make low-dimensional data representations, like those learned by mixture and topic models, more interpretable and useful. We propose a framework for training latent variable models that explicitly balances two goals: recovery of faithful generative explanations of high-dimensio…
This paper presents a Semantic Attribute Modulation (SAM) for language modeling and style variation. The semantic attribute modulation includes various document attributes, such as titles, authors, and document categories. We consider two types of attributes, (title attributes and category attributes), and a flexible a…
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.