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.
No feature ranking can be faithful, stable, and complete when features are collinear.
problem The impossibility of creating a feature ranking that is simultaneously faithful, stable, and complete when features are collinear.
method Proving the impossibility, quantifying it for four model classes, resolving it via ensemble averaging (DASH), and machine-verifying it with Lean 4 theorems.
result No method lies outside the dichotomy of faithful-complete methods (unstable, with rankings that flip up to 50% of the time) and ensemble methods (stable, reporting ties for symmetric features).
New credit attribution methods for machine learning models using relaxed stability guarantees.
problem Ensuring proper attribution in generative models trained on existing works.
method Proposed new definitions of stability that allow for non-stable processing of a subset of datapoints with permission.
result Extended well-studied stability notions and provided a comprehensive characterization of learnability.
SIM-Shapley improves SV approximation efficiency and stability.
problem High computational costs of Shapley value methods in high-dimensional settings.
method Stochastic Iterative Momentum for Shapley Value Approximation (SIM-Shapley).
result Reduced computation time by up to 85% while maintaining feature attribution quality.
Digital personas improve survey results for stable attributes but fail for subjective responses.
problem When can digital personas reliably approximate human survey findings?
method Using LISS panel, constructed personas from background variables and survey histories, tested against held-out post-cutoff answers.
result Digital personas improve alignment with human response distributions for stable attributes but fail for subjective responses.
AUASE embeds dynamic networks with stability guarantees for node comparison.
problem Stability in dynamic network embeddings for comparing nodes across time.
method Attributed unfolded adjacency spectral embedding (AUASE) for stable unsupervised learning.
result AUASE provides significant improvements in link prediction and node classification.
In this paper, we study the problem of transfer learning with the attribute data. In the transfer learning problem, we want to leverage the data of the auxiliary and the target domains to build an effective model for the classification problem in the target domain. Meanwhile, the attributes are naturally stable cross d…
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.
DFI maps covariates to latent representations for feature importance.
problem Feature importance when predictors are statistically dependent.
method Disentangled Feature Importance (DFI) using entropic optimal transport.
result DFI yields stable, interpretable, uncertainty-quantified attributions of shared predictive signal.
We show new connections between adversarial learning and explainability for deep neural networks (DNNs). One form of explanation of the output of a neural network model in terms of its input features, is a vector of feature-attributions. Two desirable characteristics of an attribution-based explanation are: (1) $\texti…
We present a framework to learn privacy-preserving encodings of images that inhibit inference of chosen private attributes, while allowing recovery of other desirable information. Rather than simply inhibiting a given fixed pre-trained estimator, our goal is that an estimator be unable to learn to accurately predict th…
A framework uses preprocessing to improve psychiatric questionnaire predictions while maintaining interpretability.
problem Weak predictive accuracy and limited interpretability of psychiatric questionnaires.
method Two-stage method: stable preprocessing followed by a linear mapping.
result REFINE outperforms other interpretable approaches in psychiatric and non-psychiatric prediction tasks.
We decompose the squared price-of-risk premium into three components: intervention-stable premium, confounding wedge, and information loss.
problem Decomposing the squared price-of-risk premium into its components
method Identifying an order-three obstruction to aggregation across portfolios
result The decomposition is estimable and detectable with a permutation-calibrated screen
PiNGDA learns beneficial noise for graph augmentation stability.
problem Challenges in generating effective and stable graph augmentations.
method PiNGDA uses positive-incentive noise to scientifically analyze and generate beneficial graph augmentations.
result PiNGDA improves GCL performance by learning beneficial noise on graph topology and attributes.
Paper proposes a new method to measure model sensitivity using final model only.
problem Understanding model behavior using only the final trained model.
method Reframe TDA as measuring sensitivity, propose further training as gold standard, unify gradient-based methods.
result Gradient-based methods approximate further training but vary in quality.
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.
Paper proposes an online learning algorithm for a neuro-fuzzy classifier with mixed data.
problem Inability of GFMMNN learning algorithms to handle mixed-attribute data.
method Extended online learning algorithm for GFMMNN that can handle both continuous and categorical features.
result Superior and stable classification performance compared to other learning algorithms.
This work introduces RISE to explain LLMs more reliably by distinguishing essential context.
problem Identifying which context elements influence LLM outputs reliably.
method RISE (Redundancy-Insensitive Scoring of Explanation) method.
result RISE provides more robust explanations than traditional methods.
Signed Evidence Flow (SEF) combines fitted prediction with signed feature attributions to measure evidence conflict and stability.
problem Modern data analysis lacks mechanisms to show the clarity, conflict, or stability of evidence behind predictions.
method Signed Evidence Flow (SEF) combines fitted prediction with signed feature attributions.
result SEF measures conflict and stability, and shows that conflict can improve loss prediction beyond confidence.
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…
Proposes a Taylor framework to unify and analyze attribution methods.
problem Lack of a unified guideline for feature contribution assignment in machine learning models.
method Introduces a Taylor attribution framework to model the attribution problem and reformulates fourteen mainstream methods.
result Empirically validates the Taylor reformulations and reveals a positive correlation between performance and principles followed.
Unified framework for analyzing machine learning model attributions.
problem Lack of a general and theoretical framework for understanding attribution methods.
method Proposes a Taylor attribution framework to unify and analyze seven mainstream attribution methods.
result Established three principles for good attribution and empirically validated the Taylor reformulations.
A new method identifies a stable subnetwork in overparameterized student models.
problem Identifying a stable subnetwork in overparameterized student models.
method Spectral representation of linear transfer of information, focusing on eigenvalues and eigenvectors.
result A stable student substructure is isolated that mirrors the true complexity of the teacher.
Study optimizes fairness in predictive models by balancing utility and separation.
problem Balancing fairness and utility in predictive models.
method Information-theoretic approach using conditional mutual information (CMI).
result Reduces separation violations while maintaining or improving utility.
TSFMs show redundant components in layers, affecting their performance.
problem Redundant components in TSFMs layers impact their predictive accuracy.
method Mechanistic interpretability tools, ablations, logit attribution, theoretical framework.
result TSFMs are robust to ablations of entire layers and specific heads.
Facial attribute editing aims to manipulate single or multiple attributes of a face image, i.e., to generate a new face with desired attributes while preserving other details. Recently, generative adversarial net (GAN) and encoder-decoder architecture are usually incorporated to handle this task with promising results.…
We analyze long-term memory properties of hourly prices of electricity in the Czech Republic between 2009 and 2012. As the dynamics of the electricity prices is dominated by cycles -- mainly intraday and daily -- we opt for the detrended fluctuation analysis, which is well suited for such specific series. We find that …
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.
Recent research has demonstrated that feature attribution methods for deep networks can themselves be incorporated into training; these attribution priors optimize for a model whose attributions have certain desirable properties -- most frequently, that particular features are important or unimportant. These attributio…
Proposes VCLANC for attributed network clustering using node and attribute embeddings.
problem Lack of mutual affinity exploitation between nodes and attributes in graph convolution.
method Dual variational auto-encoders for node and attribute embeddings, Gaussian mixture model priors, mutual distance and clustering assignment hardening losses.
result Demonstrates effectiveness on real-world attributed network datasets.
Investors seek to attribute performance to various features using Shapley value method.
problem Attributing performance to different features in an investment process.
method Use Shapley value method for attribution, either exactly or approximately.
result Shapley value method provides a preferred attribution approach.
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.
A new method for disentangled latent spaces in VAEs that can manipulate attributes.
problem Disentangled representation of attributes in latent spaces of VAEs.
method Attribute-based regularization loss to enforce monotonic relationships between attributes and latent codes.
result Manipulation of attributes in latent spaces post-training.
Graph structured data provide two-fold information: graph structures and node attributes. Numerous graph-based algorithms rely on both information to achieve success in supervised tasks, such as node classification and link prediction. However, node attributes could be missing or incomplete, which significantly deterio…
Deep reinforcement learning (DRL) methods such as the Deep Q-Network (DQN) have achieved state-of-the-art results in a variety of challenging, high-dimensional domains. This success is mainly attributed to the power of deep neural networks to learn rich domain representations for approximating the value function or pol…
We are interested in attribute-guided face generation: given a low-res face input image, an attribute vector that can be extracted from a high-res image (attribute image), our new method generates a high-res face image for the low-res input that satisfies the given attributes. To address this problem, we condition the …
In many graphs such as social networks, nodes have associated attributes representing their behavior. Predicting node attributes in such graphs is an important problem with applications in many domains like recommendation systems, privacy preservation, and targeted advertisement. Attributes values can be predicted by a…
New framework for attributing online marketing touchpoints.
problem Fine-grained attribution of individual touchpoints' effects.
method Graphical point process framework for studying conversion effects.
result Proposed methods allocate proper credit to touchpoints for each customer's path.
Anomaly detection on attributed networks aims at finding nodes whose patterns deviate significantly from the majority of reference nodes, which is pervasive in many applications such as network intrusion detection and social spammer detection. However, most existing methods neglect the complex cross-modality interactio…
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.
New method separates graph structure from node attributes to recover lost signal.
problem Standard representation learning on attributed graphs merges incompatible metric spaces, leading to geometrically flawed alignment.
method Custom variational autoencoder that separates manifold learning from structural alignment.
result Transforms geometric conflict into interpretable structural descriptor, uncovering connectivity patterns and anomalies.
Attributes, such as metadata and profile, carry useful information which in principle can help improve accuracy in recommender systems. However, existing approaches have difficulty in fully leveraging attribute information due to practical challenges such as heterogeneity and sparseness. These approaches also fail to c…
New method builds complex networks from attribute interactions without normalization.
problem Improving high-level classification algorithms by capturing hidden attribute interactions.
method Proposes a new complex network building methodology based on attribute-attribute interactions, avoiding normalization.
result Demonstrates improved performance in high-level classification techniques.
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.
Framework learns dynamic graph attributes and links co-evolution.
problem Forecasting change of node attributes and link formation in dynamic graphs.
method CoEvoGNN framework with temporal self-attention and joint optimization.
result Framework outperforms baselines on predicting unseen graph snapshots.
A new framework quantifies how model explanations influence each other.
problem Understanding how different model explanations interact and influence each other.
method Introducing the metagame, a conceptual framework for measuring second-order interaction effects of model explanations using Shapley values.
result Meta-attributions provide directional insights into how feature interactions influence model explanations.
Convolutional neural networks (CNN) have led to many state-of-the-art results spanning through various fields. However, a clear and profound theoretical understanding of the forward pass, the core algorithm of CNN, is still lacking. In parallel, within the wide field of sparse approximation, Convolutional Sparse Coding…