Unified analysis of removal-based feature attributions robustness.
problem Robustness of removal-based feature attributions is not well understood.
method Theoretical analysis and upper bounds derivation for removal-based feature attributions under input and model perturbations.
result Upper bounds for the difference between intact and perturbed attributions derived under various perturbation settings.
Proposes training objectives for neural networks to produce robust attributions.
problem Training models that produce robust interpretations for their predictions.
method Classic robust optimization models and Integrated Gradients (IG) for axiomatic attribution.
result The proposed objectives give principled generalizations of previous objectives for robust predictions.
Adapts IG for better feature attributions and robustness.
problem Reliability concerns in feature attributions for deep learning models.
method Adaptation of path-based feature attribution to Riemannian geometry of data manifolds.
result IG along geodesics generates more intuitive and robust explanations.
RoSHAP stabilizes feature attribution in machine learning models.
problem Stochastic variation in feature attribution measures.
method Modeling feature attribution score distribution and estimating it through bootstrap resampling and kernel density estimation.
result RoSHAP provides stable feature rankings and improves model performance.
Detects adversarial examples using attribution methods.
problem Detecting adversarial examples in machine learning models.
method Integrated Gradient method for finding attributions and masking high attribution features to define causal neighborhoods.
result Adversarial inputs are not robust to masking high attribution features, while benign inputs are.
New method makes neural network explanations more robust to attacks.
problem Vulnerability of feature attributions to adversarial attacks.
method Promotes Lipschitz continuity and smoothness in DNNs to improve robustness.
result Regularization and stochastic smoothing methods enhance attribution robustness.
Robustly detects and attributes climate change impacts under interventions.
problem Detect and attribute climate change impacts from observations robustly.
method Supervised learning with anchor regression for robust predictions under interventions.
result CO2 forcing can be robustly predicted from temperature patterns under strong solar forcing interventions.
Embed nodes with multi-scale attributes for robust network analysis.
problem Capturing complex node attributes across different scales.
method Multi-scale attributed node embedding (AE & MUSAE) using Skip-gram approach.
result Proves node-feature mutual information is implicitly factorized by embeddings.
New method makes CNN interpretations robust to adversarial attacks.
problem Adversarial attacks on CNN interpretation maps.
method Renyi Differential Privacy (RDP) for robust interpretation.
result Certifiable top-k robustness and improved experimental robustness. Study shows squared loss is robust for binary classification with noisy features.
problem Learning binary classifiers with noisy features.
method Sy-De and Asy-In attribute noise models, analyzing l0−1 and lsq losses. result Squared loss is robust in Sy-De model but not in Asy-In model.
Improves authorship attribution accuracy and robustness against adversarial attacks.
problem Vulnerability of authorship attribution approaches to adversarial attacks.
method Formulated a relational adversary threat model and presented a novel learning framework, normalize-and-predict (N&P).
result Improves accuracy on adversarial inputs by up to 70% and robust accuracy by 45%.
GNNs robustness in community detection is studied with various perturbations.
problem Understanding GNNs robustness in community detection tasks.
method Systematic computational evaluation of six GNN architectures on synthetic and real-world networks.
result Supervised GNNs achieve higher baseline accuracy, while DMoN shows stronger resilience to perturbations.
Improves robustness of GNNs with minimal loss in accuracy.
problem Non-robustness of GNNs to adversarial attacks on node attributes.
method Certifiable robustness method for binary node attributes and L_0-bounded perturbations, combined with robust semi-supervised training.
result Certified robustness and non-robustness of GNNs, with minimal loss in accuracy.
New findings show local attributions can't be both robust and provide recourse.
problem Ensuring machine learning systems are accountable and provide actionable recourse options.
method Formal definition of recourse sensitivity and counterexamples for popular attribution methods.
result It is impossible for any single attribution method to be both robust and provide recourse.
WCAM assesses neural network reliability by attributing decisions to wavelet scales.
problem Challenges in evaluating neural network reliability and feature robustness.
method Introduces WCAM, a wavelet-based attribution method to assess decision reliability.
result WCAM reveals where and on what scales a model focuses, enabling reliable decision assessment.
The paper introduces COAR to estimate component attributions and enable model editing.
problem Understanding how ML models transform inputs into predictions.
method Component modeling and COAR algorithm for estimating component attributions.
result COAR enables model editing across various tasks.
Anomaly detection method separates contextual from behavioral attributes.
problem Detect anomalies in data without labeled examples.
method Uses joint deep variational generative models.
result Robust to anomalous or novel contextual attributes.
New method shows data-driven causal studies can be misleading.
problem Misattribution of causality in data-driven earth science studies.
method Subsample-based ensemble approach for robust causality analysis.
result Transfer entropy-based causal graphs can be spurious.
Wavelet Attribution Method (WAM) improves feature attribution for deep models.
problem Inability of pixel-based heatmaps to capture data structure and variability in feature attribution.
method Wavelet domain for feature attribution, leveraging spatial and scale-localized properties of wavelet coefficients.
result WAM provides quantitatively superior explanations across audio, image, and volume modalities.
Method generates time-series attribution maps with identifiability guarantees.
problem Lack of identifiability guarantees in gradient-based attribution methods.
method Regularized contrastive learning algorithm trained on time-series data.
result Empirically shows robust approximation of zero vs. non-zero entries in the ground-truth attribution map.
Study shows adversarial robustness and common perturbation robustness are independent.
problem Understanding the relationship between adversarial robustness and common perturbation robustness in neural networks.
method Conducted experiments to benchmark neural network robustness to common perturbations and adversarial examples.
result Adversarial robustness and common perturbation robustness are independent attributes.
In principle, zero-shot learning makes it possible to train a recognition model simply by specifying the category's attributes. For example, with classifiers for generic attributes like \emph{striped} and \emph{four-legged}, one can construct a classifier for the zebra category by enumerating which properties it posses…
Decision maker's preferences are often captured by some choice functions which are used to rank prospects. In this paper, we consider ambiguity in choice functions over a multi-attribute prospect space. Our main result is a robust preference model where the optimal decision is based on the worst-case choice function fr…
New algorithm learns PTFs with noisy data efficiently.
problem Learning low-degree PTFs with noisy data efficiently.
method Structural result and novel robust Chow vector estimation.
result PAC learns PTFs with nasty noise using efficient samples.
New framework for robust reinforcement learning policies in uncertain environments.
problem Robust reinforcement learning policies in environments with distributional shifts.
method Comprehensive modeling framework centered around robust Markov decision processes (RMDPs).
result Existence and conditions for the dynamic programming principle (DPP) in RMDPs.
Study evaluates consistency of feature attribution in deep learning for multi-omics data.
problem Challenges in interpretability of deep learning models in biological research.
method Investigation of Shapley Additive Explanations (SHAP) on multi-view deep learning models applied to multi-omics data.
result SHAP rankings are sensitive to architecture and random initialization, suggesting caution.
The study assesses ML model robustness under worst-case subpopulations.
problem ML model performance degradation under non-training population.
method Two-stage estimation procedure for evaluating worst-case robustness over subpopulations.
result The method certifies model robustness and prevents unreliable deployments.
Paper tackles product categorization with structured and unstructured attributes for large-scale eCommerce.
problem Challenges in categorizing products with thousands of classes and millions of products.
method Compares hierarchical and flat models, uses Deep Learning for feature extraction, combines structured and unstructured attributes.
result Flat models perform better in specific cases, and the proposed approach handles faulty attribute names and values.
RKHS-SHAP uses Shapley values for kernel methods to provide feature attributions.
problem Feature attribution for kernel methods is often heuristic and not individualised.
method RKHS-SHAP uses Shapley values from coalition game theory to compute feature attributions for kernel machines efficiently.
result RKHS-SHAP can compute both Interventional and Observational Shapley values.
Paper tackles source attribution for LLM-generated texts.
problem Identify the data provider of synthetic texts generated by LLMs.
method Watermarking to embed information about data providers in synthetic texts.
result Proposes and evaluates a source attribution framework that achieves effective source attribution.
SX-GeoTree improves spatially coherent explanations in geospatial regression trees.
problem Capturing spatial dependence and producing robust explanations in tabular prediction models.
method Integrates three objectives: impurity reduction, spatial residual control, and explanation robustness via modularity maximization on a consensus similarity network.
result Improves residual spatial evenness and doubles attribution consensus (modularity: Fujian 0.19 vs 0.09; Seattle 0.10 vs 0.05).
ExCIR provides efficient, consistent, and scalable explainability for complex models.
problem Complex models lack transparency and require efficient, stable, and scalable explainability methods.
method ExCIR uses correlation-aware feature attribution with robust centering and groupwise aggregation.
result ExCIR delivers trustworthy agreement with global baselines and full model rankings, reduces runtime, and scales to large datasets.
Artificial neural networks (NN) are instrumental in realizing highly-automated driving functionality. An overarching challenge is to identify best safety engineering practices for NN and other learning-enabled components. In particular, there is an urgent need for an adequate set of metrics for measuring all-important …
CDLEEDS detects local changes in evolving data streams for accurate feature attributions.
problem Local feature attributions become obsolete in evolving data streams.
method CDLEEDS, a flexible framework for detecting local change and concept drift.
result CDLEEDS reliably detects both local and global concept drift.
New method disentangles latent subspaces under correlation shifts.
problem Correlations between factors of variation make disentanglement models less robust.
method Enforces independence between subspaces conditioned on available attributes using adversarial CMI minimization.
result Models are disentangled and robust under correlation shifts, including in weakly supervised settings.
New method attributes feature uncertainty in ML models using cooperative game theory.
problem Lack of feature-level uncertainty attribution in explainable AI.
method Proposes a novel, model-agnostic uncertainty attribution method using cooperative game theory and conformal prediction.
result Demonstrates improved runtime efficiency and practical utility in real-world applications.
New method interprets deep neural networks for better recommendation system understanding.
problem Making deep neural networks explainable for better user trust and understanding.
method Proposes a novel formulation of interpretable deep neural networks using masked weights and hidden features.
result Demonstrates models achieving close predictive performance with informative attributions.
Estimates conversion probabilities from click sequences with privacy constraints.
problem Training models in advertising with limited direct click-conversion links.
method Formalizes learning from attribution sets, constructs unbiased estimator, applies Empirical Risk Minimization.
result Empirical Risk Minimization achieves generalization guarantees and robustness against prior errors.
Graph Prototypical Networks improve few-shot node classification on attributed networks.
problem Few-shot node classification in attributed networks with limited labeled instances.
method Graph Prototypical Networks (GPN) using meta-learning to extract meta-knowledge and identify informative labeled instances.
result GPN achieves superior performance in few-shot node classification.
Paper defends sensitive attributes in GNNs from inference attacks.
problem Protecting sensitive attributes in GNNs from inference attacks.
method Proposes adversarial training with TV and Wasserstein distance to locally filter sensitive attributes.
result Framework creates strong defense against inference attacks with minimal performance loss.
Paper explores alternative cooperative game theory methods for machine learning feature attribution.
problem Debate over Shapley values' relevance in feature attribution.
method Introduces Weber and Harsanyi sets as alternative allocation schemes.
result Provides a coherent framework for designing robust feature attributions.
Estimates causal contributions of multiple causes on outcome changes.
problem Quantifying the effect of multiple causes on an outcome change.
method Develops a multiply robust estimation strategy combining regression and re-weighting methods.
result The method recovers the target parameter under partial misspecification and is consistent and asymptotically normal.
A new method, VIF, calculates influence for non-decomposable losses efficiently.
problem Efficiently calculating influence for complex machine learning models with non-decomposable losses.
method Revisiting influence function from robust statistics, proposing Versatile Influence Function (VIF) for any non-decomposable loss.
result VIF method is up to 10^3 times faster than brute-force methods and closely matches influence results.
Algorithm uncovers latent attribute graph from molecular data.
problem Learning latent representations and interpreting them for limited data.
method Perturbation experiments on latent codes of a generative autoencoder.
result Effective graphical model of latent codes and attributes.
Paper proposes MUCS for more reliable TDA in diffusion models.
problem Current TDA approaches lack reliability and robustness.
method Mirrored unlearning and noise-consistent skew (MUCS).
result MUCS outperforms existing methods on three datasets.
Improved local feature attributions using neighbourhood reference distributions.
problem Misleading results from global population in local model behaviour.
method Formulation of neighbourhood reference distributions and self-normalised importance sampling.
result Neighbourhood Shapley values provide meaningful sparse feature attributions.
Method verifies robustness of graph neural networks to graph perturbations.
problem Vulnerability of graph neural networks to adversarial attacks.
method Proposes efficient method for certifying robustness to graph perturbations.
result Efficient computation of robustness certificates for graph neural networks.
Network embedding leverages the node proximity manifested to learn a low-dimensional node vector representation for each node in the network. The learned embeddings could advance various learning tasks such as node classification, network clustering, and link prediction. Most, if not all, of the existing works, are ove…