Search Results for author:
Found 38 papers, 21 papers with code
Efficient Shapley Values for Attributing Global Properties of Diffusion Models to Data Group
As diffusion models are deployed in real-world settings, data attribution is needed to ensure fair acknowledgment for contributors of high-quality training data and to identify sources of harmful content.
Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution
Many tasks in explainable machine learning, such as data valuation and feature attribution, perform expensive computation for each data point and are intractable for large datasets.
Estimating Conditional Mutual Information for Dynamic Feature Selection
Dynamic feature selection, where we sequentially query features to make accurate predictions with a minimal budget, is a promising paradigm to reduce feature acquisition costs and provide transparency into a model's predictions.
Learning to Maximize Mutual Information for Dynamic Feature Selection
Feature selection helps reduce data acquisition costs in ML, but the standard approach is to train models with static feature subsets.
Contrastive Corpus Attribution for Explaining Representations
To address this, we propose contrastive corpus similarity, a novel and semantically meaningful scalar explanation output based on a reference corpus and a contrasting foil set of samples.
Algorithms to estimate Shapley value feature attributions
Based on the various feature removal approaches, we describe the multiple types of Shapley value feature attributions and methods to calculate each one.
Learning to Estimate Shapley Values with Vision Transformers
Transformers have become a default architecture in computer vision, but understanding what drives their predictions remains a challenging problem.
A Deep Bayesian Bandits Approach for Anticancer Therapy: Exploration via Functional Prior
Learning personalized cancer treatment with machine learning holds great promise to improve cancer patients' chance of survival.
Moment Matching Deep Contrastive Latent Variable Models
In the contrastive analysis (CA) setting, machine learning practitioners are specifically interested in discovering patterns that are enriched in a target dataset as compared to a background dataset generated from sources of variation irrelevant to the task at hand.
FastSHAP: Real-Time Shapley Value Estimation
Shapley values are widely used to explain black-box models, but they are costly to calculate because they require many model evaluations.
Pitfalls of Explainable ML: An Industry Perspective
The goal of explainable ML is to intuitively explain the predictions of a ML system, while adhering to the needs to various stakeholders.
Explaining a Series of Models by Propagating Shapley Values
Local feature attribution methods are increasingly used to explain complex machine learning models.
Improving KernelSHAP: Practical Shapley Value Estimation via Linear Regression
The Shapley value concept from cooperative game theory has become a popular technique for interpreting ML models, but efficiently estimating these values remains challenging, particularly in the model-agnostic setting.
Explaining by Removing: A Unified Framework for Model Explanation
We describe a new unified class of methods, removal-based explanations, that are based on the principle of simulating feature removal to quantify each feature's influence.
Feature Removal Is a Unifying Principle for Model Explanation Methods
Researchers have proposed a wide variety of model explanation approaches, but it remains unclear how most methods are related or when one method is preferable to another.
True to the Model or True to the Data?
Furthermore, we argue that the choice comes down to whether it is desirable to be true to the model or true to the data.
Understanding Global Feature Contributions With Additive Importance Measures
Understanding the inner workings of complex machine learning models is a long-standing problem and most recent research has focused on local interpretability.
Forecasting adverse surgical events using self-supervised transfer learning for physiological signals
Here, we present a transferable embedding method (i. e., a method to transform time series signals into input features for predictive machine learning models) named PHASE (PHysiologicAl Signal Embeddings) that enables us to more accurately forecast adverse surgical outcomes based on physiological signals.
Explaining Explanations: Axiomatic Feature Interactions for Deep Networks
Integrated Hessians overcomes several theoretical limitations of previous methods to explain interactions, and unlike such previous methods is not limited to a specific architecture or class of neural network.
An Adversarial Approach for the Robust Classification of Pneumonia from Chest Radiographs
In order for these models to be safely deployed, we would like to ensure that they do not use confounding variables to make their classification, and that they will work well even when tested on images from hospitals that were not included in the training data.
Learning Deep Attribution Priors Based On Prior Knowledge
In real-world problems we often have sets of additional information for each feature that are predictive of that feature's importance to the task at hand.
Explaining Models by Propagating Shapley Values of Local Components
In healthcare, making the best possible predictions with complex models (e. g., neural networks, ensembles/stacks of different models) can impact patient welfare.
Deep unsupervised feature selection
Unsupervised feature selection involves finding a small number of highly informative features, in the absence of a specific supervised learning task.
Improving performance of deep learning models with axiomatic attribution priors and expected gradients
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.
Explainable AI for Trees: From Local Explanations to Global Understanding
3) A new set of tools for understanding global model structure based on combining many local explanations of each prediction.
Physiological Signal Embeddings (PHASE) via Interpretable Stacked Models
Here, we present the PHASE (PHysiologicAl Signal Embeddings) framework, which consists of three components: i) learning neural network embeddings of physiological signals, ii) predicting outcomes based on the learned embedding, and iii) interpreting the prediction results by estimating feature attributions in the "stacked" models (i. e., feature embedding model followed by prediction model).
Consistent Individualized Feature Attribution for Tree Ensembles
A unified approach to explain the output of any machine learning model.
Hybrid Gradient Boosting Trees and Neural Networks for Forecasting Operating Room Data
In this paper, we present feature learning via long short term memory (LSTM) networks and prediction via gradient boosting trees (XGB).
Anesthesiologist-level forecasting of hypoxemia with only SpO2 data using deep learning
We also provide a simple way to visualize the reason why a patient's risk is low or high by assigning weight to the patient's past blood oxygen values.
Checkpoint Ensembles: Ensemble Methods from a Single Training Process
We present the checkpoint ensembles method that can learn ensemble models on a single training process.
Consistent feature attribution for tree ensembles
Note that a newer expanded version of this paper is now available at: arXiv:1802. 03888 It is critical in many applications to understand what features are important for a model, and why individual predictions were made.
A Unified Approach to Interpreting Model Predictions
Understanding why a model makes a certain prediction can be as crucial as the prediction's accuracy in many applications.
Learning Sparse Gaussian Graphical Models with Overlapping Blocks
3) It can jointly learn a network structure and overlapping blocks.
An unexpected unity among methods for interpreting model predictions
Here, we present how a model-agnostic additive representation of the importance of input features unifies current methods.
Learning Graphical Models With Hubs
We consider the problem of learning a high-dimensional graphical model in which certain hub nodes are highly-connected to many other nodes.
Node-Based Learning of Multiple Gaussian Graphical Models
We consider estimation under two distinct assumptions: (1) differences between the K networks are due to individual nodes that are perturbed across conditions, or (2) similarities among the K networks are due to the presence of common hub nodes that are shared across all K networks.
Structured Learning of Gaussian Graphical Models
We consider estimation of multiple high-dimensional Gaussian graphical models corresponding to a single set of nodes under several distinct conditions.
