Towards Explaining Distribution Shifts
- URL: http://arxiv.org/abs/2210.10275v2
- Date: Tue, 20 Jun 2023 04:30:42 GMT
- Title: Towards Explaining Distribution Shifts
- Authors: Sean Kulinski, David I. Inouye
- Abstract summary: A distribution shift can have fundamental consequences such as signaling a change in the operating environment or significantly reducing the accuracy of downstream models.
Most prior work focuses on merely detecting if a shift has occurred and assumes any detected shift can be understood and handled appropriately by a human operator.
We hope to aid in these manual mitigation tasks by explaining the distribution shift using interpretable transportation maps from the original distribution to the shifted one.
- Score: 9.036025934093965
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: A distribution shift can have fundamental consequences such as signaling a
change in the operating environment or significantly reducing the accuracy of
downstream models. Thus, understanding distribution shifts is critical for
examining and hopefully mitigating the effect of such a shift. Most prior work
focuses on merely detecting if a shift has occurred and assumes any detected
shift can be understood and handled appropriately by a human operator. We hope
to aid in these manual mitigation tasks by explaining the distribution shift
using interpretable transportation maps from the original distribution to the
shifted one. We derive our interpretable mappings from a relaxation of optimal
transport, where the candidate mappings are restricted to a set of
interpretable mappings. We then inspect multiple quintessential use-cases of
distribution shift in real-world tabular, text, and image datasets to showcase
how our explanatory mappings provide a better balance between detail and
interpretability than baseline explanations by both visual inspection and our
PercentExplained metric.
Related papers
- Identifiable Latent Neural Causal Models [82.14087963690561]
Causal representation learning seeks to uncover latent, high-level causal representations from low-level observed data.
We determine the types of distribution shifts that do contribute to the identifiability of causal representations.
We translate our findings into a practical algorithm, allowing for the acquisition of reliable latent causal representations.
arXiv Detail & Related papers (2024-03-23T04:13:55Z) - Proxy Methods for Domain Adaptation [78.03254010884783]
proxy variables allow for adaptation to distribution shift without explicitly recovering or modeling latent variables.
We develop a two-stage kernel estimation approach to adapt to complex distribution shifts in both settings.
arXiv Detail & Related papers (2024-03-12T09:32:41Z) - Distribution Shift Inversion for Out-of-Distribution Prediction [57.22301285120695]
We propose a portable Distribution Shift Inversion algorithm for Out-of-Distribution (OoD) prediction.
We show that our method provides a general performance gain when plugged into a wide range of commonly used OoD algorithms.
arXiv Detail & Related papers (2023-06-14T08:00:49Z) - Leveraging sparse and shared feature activations for disentangled
representation learning [112.22699167017471]
We propose to leverage knowledge extracted from a diversified set of supervised tasks to learn a common disentangled representation.
We validate our approach on six real world distribution shift benchmarks, and different data modalities.
arXiv Detail & Related papers (2023-04-17T01:33:24Z) - Evaluating Robustness and Uncertainty of Graph Models Under Structural
Distributional Shifts [43.40315460712298]
In node-level problems of graph learning, distributional shifts can be especially complex.
We propose a general approach for inducing diverse distributional shifts based on graph structure.
We show that simple models often outperform more sophisticated methods on the considered structural shifts.
arXiv Detail & Related papers (2023-02-27T15:25:21Z) - Explanation Shift: Detecting distribution shifts on tabular data via the
explanation space [13.050516715665166]
We investigate how model predictive performance and model explanation characteristics are affected under distribution shifts.
We find that the modeling of explanation shifts can be a better indicator for the detection of predictive performance changes.
arXiv Detail & Related papers (2022-10-22T06:47:13Z) - Interpretable Distribution Shift Detection using Optimal Transport [22.047388001308253]
We propose a method to identify and characterize distribution shifts in classification datasets based on optimal transport.
It allows the user to identify the extent to which each class is affected by the shift, and retrieves corresponding pairs of samples to provide insights on its nature.
arXiv Detail & Related papers (2022-08-04T21:55:29Z) - Evaluating Robustness to Dataset Shift via Parametric Robustness Sets [7.347989843033034]
We give a method for proactively identifying small, plausible shifts in distribution which lead to large differences in model performance.
We apply an approach to classifying gender from images, revealing sensitivity to shifts in non-causal attributes.
arXiv Detail & Related papers (2022-05-31T16:44:18Z) - Predicting with Confidence on Unseen Distributions [90.68414180153897]
We connect domain adaptation and predictive uncertainty literature to predict model accuracy on challenging unseen distributions.
We find that the difference of confidences (DoC) of a classifier's predictions successfully estimates the classifier's performance change over a variety of shifts.
We specifically investigate the distinction between synthetic and natural distribution shifts and observe that despite its simplicity DoC consistently outperforms other quantifications of distributional difference.
arXiv Detail & Related papers (2021-07-07T15:50:18Z) - Explainers in the Wild: Making Surrogate Explainers Robust to
Distortions through Perception [77.34726150561087]
We propose a methodology to evaluate the effect of distortions in explanations by embedding perceptual distances.
We generate explanations for images in the Imagenet-C dataset and demonstrate how using a perceptual distances in the surrogate explainer creates more coherent explanations for the distorted and reference images.
arXiv Detail & Related papers (2021-02-22T12:38:53Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.