Evaluating Feature Attribution: An Information-Theoretic Perspective

• URL: http://arxiv.org/abs/2202.00449v1
• Date: Tue, 1 Feb 2022 15:00:26 GMT
• Title: Evaluating Feature Attribution: An Information-Theoretic Perspective
• Authors: Yao Rong, Tobias Leemann, Vadim Borisov, Gjergji Kasneci, Enkelejda Kasneci
• Abstract summary: We present an information-theoretic analysis of evaluation strategies based on pixel perturbations. Our findings reveal that the results output by different evaluation strategies are strongly affected by information leakage through the shape of the removed pixels. We propose a novel evaluation framework termed Remove and Debias (ROAD) which offers two contributions.
• Score: 21.101718565039015
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With a variety of local feature attribution methods being proposed in recent years, follow-up work suggested several evaluation strategies. To assess the attribution quality across different attribution techniques, the most popular among these evaluation strategies in the image domain use pixel perturbations. However, recent advances discovered that different evaluation strategies produce conflicting rankings of attribution methods and can be prohibitively expensive to compute. In this work, we present an information-theoretic analysis of evaluation strategies based on pixel perturbations. Our findings reveal that the results output by different evaluation strategies are strongly affected by information leakage through the shape of the removed pixels as opposed to their actual values. Using our theoretical insights, we propose a novel evaluation framework termed Remove and Debias (ROAD) which offers two contributions: First, it mitigates the impact of the confounders, which entails higher consistency among evaluation strategies. Second, ROAD does not require the computationally expensive retraining step and saves up to 99% in computational costs compared to the state-of-the-art. Our source code is available at https://github.com/tleemann/road_evaluation.

Related papers

• Exploring the Performance of Continuous-Time Dynamic Link Prediction Algorithms [14.82820088479196]
  Dynamic Link Prediction (DLP) addresses the prediction of future links in evolving networks. In this work, we contribute tools to perform such a comprehensive evaluation. We describe an exhaustive taxonomy of negative sampling methods that can be used at evaluation time.
  arXiv  Detail & Related papers  (2024-05-27T14:03:28Z)
• Evaluation in Neural Style Transfer: A Review [0.7614628596146599]
  We provide an in-depth analysis of existing evaluation techniques, identify the inconsistencies and limitations of current evaluation methods, and give recommendations for standardized evaluation practices. We believe that the development of a robust evaluation framework will not only enable more meaningful and fairer comparisons but will also enhance the comprehension and interpretation of research findings in the field.
  arXiv  Detail & Related papers  (2024-01-30T15:45:30Z)
• A Call to Reflect on Evaluation Practices for Age Estimation: Comparative Analysis of the State-of-the-Art and a Unified Benchmark [2.156208381257605]
  We offer an extensive comparative analysis for state-of-the-art facial age estimation methods. We find that the performance differences between the methods are negligible compared to the effect of other factors. We propose using FaRL as the backbone model and demonstrate its effectiveness on all public datasets.
  arXiv  Detail & Related papers  (2023-07-10T14:02:31Z)
• Better Understanding Differences in Attribution Methods via Systematic Evaluations [57.35035463793008]
  Post-hoc attribution methods have been proposed to identify image regions most influential to the models' decisions. We propose three novel evaluation schemes to more reliably measure the faithfulness of those methods. We use these evaluation schemes to study strengths and shortcomings of some widely used attribution methods over a wide range of models.
  arXiv  Detail & Related papers  (2023-03-21T14:24:58Z)
• On The Coherence of Quantitative Evaluation of Visual Explanations [0.7212939068975619]
  Evaluation methods have been proposed to assess the "goodness" of visual explanations. We study a subset of the ImageNet-1k validation set where we evaluate a number of different commonly-used explanation methods. Results of our study suggest that there is a lack of coherency on the grading provided by some of the considered evaluation methods.
  arXiv  Detail & Related papers  (2023-02-14T13:41:57Z)
• Towards Better Understanding Attribution Methods [77.1487219861185]
  Post-hoc attribution methods have been proposed to identify image regions most influential to the models' decisions. We propose three novel evaluation schemes to more reliably measure the faithfulness of those methods. We also propose a post-processing smoothing step that significantly improves the performance of some attribution methods.
  arXiv  Detail & Related papers  (2022-05-20T20:50:17Z)
• Performance Evaluation of Adversarial Attacks: Discrepancies and Solutions [51.8695223602729]
  adversarial attack methods have been developed to challenge the robustness of machine learning models. We propose a Piece-wise Sampling Curving (PSC) toolkit to effectively address the discrepancy. PSC toolkit offers options for balancing the computational cost and evaluation effectiveness.
  arXiv  Detail & Related papers  (2021-04-22T14:36:51Z)
• Learning Expectation of Label Distribution for Facial Age and Attractiveness Estimation [65.5880700862751]
  We analyze the essential relationship between two state-of-the-art methods (Ranking-CNN and DLDL) and show that the Ranking method is in fact learning label distribution implicitly. We propose a lightweight network architecture and propose a unified framework which can jointly learn facial attribute distribution and regress attribute value. Our method achieves new state-of-the-art results using the single model with 36$times$ fewer parameters and 3$times$ faster inference speed on facial age/attractiveness estimation.
  arXiv  Detail & Related papers  (2020-07-03T15:46:53Z)
• Minimax-Optimal Off-Policy Evaluation with Linear Function Approximation [49.502277468627035]
  This paper studies the statistical theory of batch data reinforcement learning with function approximation. Consider the off-policy evaluation problem, which is to estimate the cumulative value of a new target policy from logged history.
  arXiv  Detail & Related papers  (2020-02-21T19:20:57Z)
• Kalman meets Bellman: Improving Policy Evaluation through Value Tracking [59.691919635037216]
  Policy evaluation is a key process in Reinforcement Learning (RL) We devise an optimization method, called Kalman Optimization for Value Approximation (KOVA) KOVA minimizes a regularized objective function that concerns both parameter and noisy return uncertainties.
  arXiv  Detail & Related papers  (2020-02-17T13:30:43Z)

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.