Bringing a Ruler Into the Black Box: Uncovering Feature Impact from Individual Conditional Expectation Plots

• URL: http://arxiv.org/abs/2109.02724v1
• Date: Mon, 6 Sep 2021 20:26:29 GMT
• Title: Bringing a Ruler Into the Black Box: Uncovering Feature Impact from Individual Conditional Expectation Plots
• Authors: Andrew Yeh, Anhthy Ngo
• Abstract summary: We introduce a model-agnostic, performance-agnostic feature impact metric drawn out from ICE plots. We also introduce an in-distribution variant of ICE feature impact to vary the influence of out-of-distribution points. We demonstrate ICE feature impact's utility in several tasks using real-world data.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: As machine learning systems become more ubiquitous, methods for understanding and interpreting these models become increasingly important. In particular, practitioners are often interested both in what features the model relies on and how the model relies on them--the feature's impact on model predictions. Prior work on feature impact including partial dependence plots (PDPs) and Individual Conditional Expectation (ICE) plots has focused on a visual interpretation of feature impact. We propose a natural extension to ICE plots with ICE feature impact, a model-agnostic, performance-agnostic feature impact metric drawn out from ICE plots that can be interpreted as a close analogy to linear regression coefficients. Additionally, we introduce an in-distribution variant of ICE feature impact to vary the influence of out-of-distribution points as well as heterogeneity and non-linearity measures to characterize feature impact. Lastly, we demonstrate ICE feature impact's utility in several tasks using real-world data.

Related papers

• Influence Functions for Scalable Data Attribution in Diffusion Models [52.92223039302037]
  Diffusion models have led to significant advancements in generative modelling. Yet their widespread adoption poses challenges regarding data attribution and interpretability. In this paper, we aim to help address such challenges by developing an textitinfluence functions framework.
  arXiv  Detail & Related papers  (2024-10-17T17:59:02Z)
• Explanatory Model Monitoring to Understand the Effects of Feature Shifts on Performance [61.06245197347139]
  We propose a novel approach to explain the behavior of a black-box model under feature shifts. We refer to our method that combines concepts from Optimal Transport and Shapley Values as Explanatory Performance Estimation.
  arXiv  Detail & Related papers  (2024-08-24T18:28:19Z)
• Do Finetti: On Causal Effects for Exchangeable Data [45.96632286841583]
  We study causal effect estimation in a setting where the data are not i.i.d. We focus on exchangeable data satisfying an assumption of independent causal mechanisms.
  arXiv  Detail & Related papers  (2024-05-29T07:31:18Z)
• CAFE: Conflict-Aware Feature-wise Explanations [12.428277452418621]
  Feature attribution methods are widely used to explain neural models by determining the influence of individual input features on the models' outputs. We propose a novel feature attribution method, CAFE (Conflict-Aware Feature-wise Explanations), that addresses three limitations of the existing methods.
  arXiv  Detail & Related papers  (2023-10-31T11:14:26Z)
• Measuring Causal Effects of Data Statistics on Language Model's `Factual' Predictions [59.284907093349425]
  Large amounts of training data are one of the major reasons for the high performance of state-of-the-art NLP models. We provide a language for describing how training data influences predictions, through a causal framework. Our framework bypasses the need to retrain expensive models and allows us to estimate causal effects based on observational data alone.
  arXiv  Detail & Related papers  (2022-07-28T17:36:24Z)
• Causal Discovery in Physical Systems from Videos [123.79211190669821]
  Causal discovery is at the core of human cognition. We consider the task of causal discovery from videos in an end-to-end fashion without supervision on the ground-truth graph structure.
  arXiv  Detail & Related papers  (2020-07-01T17:29:57Z)
• Influence Functions in Deep Learning Are Fragile [52.31375893260445]
  influence functions approximate the effect of samples in test-time predictions. influence estimates are fairly accurate for shallow networks. Hessian regularization is important to get highquality influence estimates.
  arXiv  Detail & Related papers  (2020-06-25T18:25:59Z)
• Nonparametric Feature Impact and Importance [0.6123324869194193]
  We give mathematical definitions of feature impact and importance, derived from partial dependence curves, that operate directly on the data. To assess quality, we show that features ranked by these definitions are competitive with existing feature selection techniques.
  arXiv  Detail & Related papers  (2020-06-08T17:07:35Z)

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.