Search Results for author:
Found 12 papers, 7 papers with code
The Solvability of Interpretability Evaluation Metrics
Feature attribution methods are popular for explaining neural network predictions, and they are often evaluated on metrics such as comprehensiveness and sufficiency, which are motivated by the principle that more important features -- as judged by the explanation -- should have larger impacts on model prediction.
ExSum: From Local Explanations to Model Understanding
Interpretability methods are developed to understand the working mechanisms of black-box models, which is crucial to their responsible deployment.
The Irrationality of Neural Rationale Models
We call for more rigorous and comprehensive evaluations of these models to ensure desired properties of interpretability are indeed achieved.
Do Feature Attribution Methods Correctly Attribute Features?
Feature attribution methods are exceedingly popular in interpretable machine learning.
Long-Term Resource Allocation Fairness in Average Markov Decision Process (AMDP) Environment
Fairness has emerged as an important concern in automated decision-making in recent years, especially when these decisions affect human welfare.
Towards Understanding the Behaviors of Optimal Deep Active Learning Algorithms
Active learning (AL) algorithms may achieve better performance with fewer data because the model guides the data selection process.
Bayes-TrEx: a Bayesian Sampling Approach to Model Transparency by Example
To address these challenges, we introduce a flexible model inspection framework: Bayes-TrEx.
Adversarially Guided Self-Play for Adopting Social Conventions
Robotic agents must adopt existing social conventions in order to be effective teammates.
Sampling Prediction-Matching Examples in Neural Networks: A Probabilistic Programming Approach
In this paper, we consider the problem of exploring the prediction level sets of a classifier using probabilistic programming.
Learning Household Task Knowledge from WikiHow Descriptions
Commonsense procedural knowledge is important for AI agents and robots that operate in a human environment.
On Memory Mechanism in Multi-Agent Reinforcement Learning
Multi-agent reinforcement learning (MARL) extends (single-agent) reinforcement learning (RL) by introducing additional agents and (potentially) partial observability of the environment.
Predicting ConceptNet Path Quality Using Crowdsourced Assessments of Naturalness
In this paper we instead propose to learn to predict path quality from crowdsourced human assessments.
