Uncertainty in Additive Feature Attribution methods

• URL: http://arxiv.org/abs/2311.17446v1
• Date: Wed, 29 Nov 2023 08:40:46 GMT
• Title: Uncertainty in Additive Feature Attribution methods
• Authors: Abhishek Madaan, Tanya Chowdhury, Neha Rana, James Allan, Tanmoy Chakraborty
• Abstract summary: We focus on the class of additive feature attribution explanation methods. We study the relationship between a feature's attribution and its uncertainty and observe little correlation. We coin the term "stable instances" for such instances and diagnose factors that make an instance stable.
• Score: 34.80932512496311
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this work, we explore various topics that fall under the umbrella of Uncertainty in post-hoc Explainable AI (XAI) methods. We in particular focus on the class of additive feature attribution explanation methods. We first describe our specifications of uncertainty and compare various statistical and recent methods to quantify the same. Next, for a particular instance, we study the relationship between a feature's attribution and its uncertainty and observe little correlation. As a result, we propose a modification in the distribution from which perturbations are sampled in LIME-based algorithms such that the important features have minimal uncertainty without an increase in computational cost. Next, while studying how the uncertainty in explanations varies across the feature space of a classifier, we observe that a fraction of instances show near-zero uncertainty. We coin the term "stable instances" for such instances and diagnose factors that make an instance stable. Next, we study how an XAI algorithm's uncertainty varies with the size and complexity of the underlying model. We observe that the more complex the model, the more inherent uncertainty is exhibited by it. As a result, we propose a measure to quantify the relative complexity of a blackbox classifier. This could be incorporated, for example, in LIME-based algorithms' sampling densities, to help different explanation algorithms achieve tighter confidence levels. Together, the above measures would have a strong impact on making XAI models relatively trustworthy for the end-user as well as aiding scientific discovery.

Related papers

• Cycles of Thought: Measuring LLM Confidence through Stable Explanations [53.15438489398938]
  Large language models (LLMs) can reach and even surpass human-level accuracy on a variety of benchmarks, but their overconfidence in incorrect responses is still a well-documented failure mode. We propose a framework for measuring an LLM's uncertainty with respect to the distribution of generated explanations for an answer.
  arXiv  Detail & Related papers  (2024-06-05T16:35:30Z)
• Identifying Drivers of Predictive Aleatoric Uncertainty [2.5311562666866494]
  We present a simple approach to explain predictive aleatoric uncertainties. We estimate uncertainty as predictive variance by adapting a neural network with a Gaussian output distribution. We quantify our findings with a nuanced benchmark analysis that includes real-world datasets.
  arXiv  Detail & Related papers  (2023-12-12T13:28:53Z)
• Learning to Bound Counterfactual Inference in Structural Causal Models from Observational and Randomised Data [64.96984404868411]
  We derive a likelihood characterisation for the overall data that leads us to extend a previous EM-based algorithm. The new algorithm learns to approximate the (unidentifiability) region of model parameters from such mixed data sources. It delivers interval approximations to counterfactual results, which collapse to points in the identifiable case.
  arXiv  Detail & Related papers  (2022-12-06T12:42:11Z)
• What is Flagged in Uncertainty Quantification? Latent Density Models for Uncertainty Categorization [68.15353480798244]
  Uncertainty Quantification (UQ) is essential for creating trustworthy machine learning models. Recent years have seen a steep rise in UQ methods that can flag suspicious examples. We propose a framework for categorizing uncertain examples flagged by UQ methods in classification tasks.
  arXiv  Detail & Related papers  (2022-07-11T19:47:00Z)
• Instance-optimality in optimal value estimation: Adaptivity via variance-reduced Q-learning [99.34907092347733]
  We analyze the problem of estimating optimal $Q$-value functions for a discounted Markov decision process with discrete states and actions. Using a local minimax framework, we show that this functional arises in lower bounds on the accuracy on any estimation procedure. In the other direction, we establish the sharpness of our lower bounds, up to factors logarithmic in the state and action spaces, by analyzing a variance-reduced version of $Q$-learning.
  arXiv  Detail & Related papers  (2021-06-28T00:38:54Z)
• Uncertainty-Aware Few-Shot Image Classification [118.72423376789062]
  Few-shot image classification learns to recognize new categories from limited labelled data. We propose Uncertainty-Aware Few-Shot framework for image classification.
  arXiv  Detail & Related papers  (2020-10-09T12:26:27Z)
• Robust Estimation of Tree Structured Ising Models [20.224160348675422]
  We consider the task of learning Ising models when the signs of different random variables are flipped independently with possibly unequal, unknown probabilities. We first prove that this problem is unidentifiable, however, this unidentifiability is limited to a small equivalence class of trees formed by leaf nodes exchanging positions with their neighbors.
  arXiv  Detail & Related papers  (2020-06-10T01:32:45Z)
• Instability, Computational Efficiency and Statistical Accuracy [101.32305022521024]
  We develop a framework that yields statistical accuracy based on interplay between the deterministic convergence rate of the algorithm at the population level, and its degree of (instability) when applied to an empirical object based on $n$ samples. We provide applications of our general results to several concrete classes of models, including Gaussian mixture estimation, non-linear regression models, and informative non-response models.
  arXiv  Detail & Related papers  (2020-05-22T22:30:52Z)
• On Last-Layer Algorithms for Classification: Decoupling Representation from Uncertainty Estimation [27.077741143188867]
  We propose a family of algorithms which split the classification task into two stages: representation learning and uncertainty estimation. We evaluate their performance in terms of emphselective classification (risk-coverage), and their ability to detect out-of-distribution samples.
  arXiv  Detail & Related papers  (2020-01-22T15:08:30Z)

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.