Missingness Bias in Model Debugging
Missingness, or the absence of features from an input, is a concept fundamental to many model debugging tools. However, in computer vision, pixels cannot simply be removed from an image. One thus tends to resort to heuristics such as blacking out pixels, which may in turn introduce bias into the debugging process. We study such biases and, in particular, show how transformer-based architectures can enable a more natural implementation of missingness, which side-steps these issues and improves the reliability of model debugging in practice. Our code is available at https://github.com/madrylab/missingness
Code (1)
Tasks
modelSimilar Papers 제목 키워드 기반
Missingness Bias Calibration in Feature Attribution Explanations
Popular explanation methods often produce unreliable feature importance scores due to missingness bias, a systematic distortion that arises when models are probed with ablated, out-of-distribution inputs. Existing soluti…
Feature ImportanceTo Impute or not to Impute? Missing Data in Treatment Effect Estimation
Missing data is a systemic problem in practical scenarios that causes noise and bias when estimating treatment effects. This makes treatment effect estimation from data with missingness a particularly tricky endeavour. A…
ImputationIncreasing Missingness to Reduce Bias: Richardson-SGD with Missing Data
Stochastic gradient methods are central to modern large-scale learning, but their use with incomplete covariates remains delicate since imputation schemes generally introduce systematic gradient biases, as shown for line…
Dimension Reduction for Data with Heterogeneous Missingness
Dimension reduction plays a pivotal role in analysing high-dimensional data. However, observations with missing values present serious difficulties in directly applying standard dimension reduction techniques. As a large…
Dimensionality ReductionMissing ValuesOff-Policy Evaluation Under Nonignorable Missing Data
Off-Policy Evaluation (OPE) aims to estimate the value of a target policy using offline data collected from potentially different policies. In real-world applications, however, logged data often suffers from missingness.…