arXiv research

The paper formalizes feature attribution to address inconsistent definitions and evaluate methods.

Efficiently explains model outputs using HSIC, a dependence measure.

Study reveals class-dependent effects in perturbation-based feature attribution metrics for time series classification.

DFI maps covariates to latent representations for feature importance.

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 …

Proposes a new method for fairness in machine learning with multiple protected attributes.

StylEx trains a GAN to explain classifier decisions in StyleSpace.

Unified analysis for graph learning from multi-attribute Gaussian time series.

Paper learns latent and hierarchical structures in CDMs from data.

New method optimizes fairness in predictive models for continuous sensitive attributes.

In this paper we analyze a budgeted learning setting, in which the learner can only choose and observe a small subset of the attributes of each training example. We develop efficient algorithms for ridge and lasso linear regression, which utilize the geometry of the data by a novel data-dependent sampling scheme. When …

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…

Mining tasks over sequential data, such as clickstreams and gene sequences, require a careful design of embeddings usable by learning algorithms. Recent research in feature learning has been extended to sequential data, where each instance consists of a sequence of heterogeneous items with a variable length. However, m…

Framework learns dynamic graph attributes and links co-evolution.

Generating graph structures is a challenging problem due to the diverse representations and complex dependencies among nodes. In this paper, we introduce Graph Variational Recurrent Neural Network (GraphVRNN), a probabilistic autoregressive model for graph generation. Through modeling the latent variables of graph data…

New method predicts model output distributions to improve data attribution.

Quantile regression is a tool for learning conditional distributions. In this paper we study quantile regression in the setting where a protected attribute is unavailable when fitting the model. This can lead to "unfair'' quantile estimators for which the effective quantiles are very different for the subpopulations de…

Interpreting predictions from tree ensemble methods such as gradient boosting machines and random forests is important, yet feature attribution for trees is often heuristic and not individualized for each prediction. Here we show that popular feature attribution methods are inconsistent, meaning they can lower a featur…

STICC clusters geographic objects considering both spatial contiguity and attributes.

Attributing forecast gaps to component models in complex model suites

Archipelago provides interpretable explanations of feature interactions in machine learning models.

SISR improves feature attribution in complex payoff schemes.

The paper tackles attributing forecast gaps in complex model suites.

Paper analyzes multi-attribute data to estimate differences in Gaussian graphical models.

New method R-LOCO improves local feature importance analysis.

Model infers functions for attributes using multi-aggregate datasets with knowledge transfer.

Estimates conversion probabilities from click sequences with privacy constraints.

This work addresses fairness in ML models by training and evaluating attribute classifiers under uncertain and incomplete data.

Anomaly detection aims to distinguish observations that are rare and different from the majority. While most existing algorithms assume that instances are i.i.d., in many practical scenarios, links describing instance-to-instance dependencies and interactions are available. Such systems are called attributed networks. …

Proposes GNAN model for detecting various network structures.

DArtNet predicts time series data using graph structure and dynamic attributes.

New findings show local attributions can't be both robust and provide recourse.

A framework to explain decoder-only sequence classification models using intermediate predictions.

Joint models are a common and important tool in the intersection of machine learning and the physical sciences, particularly in contexts where real-world measurements are scarce. Recent developments in rainfall-runoff modeling, one of the prime challenges in hydrology, show the value of a joint model with shared repres…

CDA framework infers channel influence from aggregated data without user identifiers.

New algorithm reduces regret in dynamic assortment selection.

Medical imaging models may encode demographic attributes without violating fairness, depending on the approach.

New algorithm learns PTFs with noisy data efficiently.

Tab-Shapley identifies top-k anomalies in tabular data quality insights.

ABC method analyzes diffusion model dependence without retraining.

Proposes counterfactual explainability for causal attribution, extending variance analysis methods.

AP-Calculus offers a new framework for causal inference in Bayesian networks.

We propose a neural network architecture for learning vector representations of hotels. Unlike previous works, which typically only use user click information for learning item embeddings, we propose a framework that combines several sources of data, including user clicks, hotel attributes (e.g., property type, star ra…

This paper tackles graph translation challenges by predicting both node and edge attributes simultaneously.

Algorithm optimizes a single attribute in multi-armed bandits with constraints.

New Shapley values reveal non-linear feature dependencies.

R package innsight interprets deep neural networks predictions.

Predictive models are increasingly deployed for the purpose of determining access to services such as credit, insurance, and employment. Despite potential gains in productivity and efficiency, several potential problems have yet to be addressed, particularly the potential for unintentional discrimination. We present an…