Reinforcement Explanation Learning

• URL: http://arxiv.org/abs/2111.13406v1
• Date: Fri, 26 Nov 2021 10:20:01 GMT
• Title: Reinforcement Explanation Learning
• Authors: Siddhant Agarwal, Owais Iqbal, Sree Aditya Buridi, Madda Manjusha, Abir Das
• Abstract summary: Black-box methods to generate saliency maps are particularly interesting due to the fact that they do not utilize the internals of the model to explain the decision. We formulate saliency map generation as a sequential search problem and leverage upon Reinforcement Learning (RL) to accumulate evidence from input images. Experiments on three benchmark datasets demonstrate the superiority of the proposed approach in inference time over state-of-the-arts without hurting the performance.
• Score: 4.852320309766702
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep Learning has become overly complicated and has enjoyed stellar success in solving several classical problems like image classification, object detection, etc. Several methods for explaining these decisions have been proposed. Black-box methods to generate saliency maps are particularly interesting due to the fact that they do not utilize the internals of the model to explain the decision. Most black-box methods perturb the input and observe the changes in the output. We formulate saliency map generation as a sequential search problem and leverage upon Reinforcement Learning (RL) to accumulate evidence from input images that most strongly support decisions made by a classifier. Such a strategy encourages to search intelligently for the perturbations that will lead to high-quality explanations. While successful black box explanation approaches need to rely on heavy computations and suffer from small sample approximation, the deterministic policy learned by our method makes it a lot more efficient during the inference. Experiments on three benchmark datasets demonstrate the superiority of the proposed approach in inference time over state-of-the-arts without hurting the performance. Project Page: https://cvir.github.io/projects/rexl.html

Related papers

• Adapting Vision-Language Models to Open Classes via Test-Time Prompt Tuning [50.26965628047682]
  Adapting pre-trained models to open classes is a challenging problem in machine learning. In this paper, we consider combining the advantages of both and come up with a test-time prompt tuning approach. Our proposed method outperforms all comparison methods on average considering both base and new classes.
  arXiv  Detail & Related papers  (2024-08-29T12:34:01Z)
• How to Choose a Reinforcement-Learning Algorithm [29.76033485145459]
  We streamline the process of choosing reinforcement-learning algorithms and action-distribution families. We provide a structured overview of existing methods and their properties, as well as guidelines for when to choose which methods.
  arXiv  Detail & Related papers  (2024-07-30T15:54:18Z)
• R-Tuning: Instructing Large Language Models to Say `I Don't Know' [66.11375475253007]
  Large language models (LLMs) have revolutionized numerous domains with their impressive performance but still face their challenges. Previous instruction tuning methods force the model to complete a sentence no matter whether the model knows the knowledge or not. We present a new approach called Refusal-Aware Instruction Tuning (R-Tuning) Experimental results demonstrate R-Tuning effectively improves a model's ability to answer known questions and refrain from answering unknown questions.
  arXiv  Detail & Related papers  (2023-11-16T08:45:44Z)
• McXai: Local model-agnostic explanation as two games [5.2229999775211216]
  This work introduces a reinforcement learning-based approach called Monte Carlo tree search for eXplainable Artificial Intelligent (McXai) to explain the decisions of any black-box classification model (classifier) Our experiments show, that the features found by our method are more informative with respect to classifications than those found by classical approaches like LIME and SHAP.
  arXiv  Detail & Related papers  (2022-01-04T09:02:48Z)
• TDLS: A Top-Down Layer Searching Algorithm for Generating Counterfactual Visual Explanation [4.4553061479339995]
  We adapt counterfactual explanation over fine-grained image classification problem. We have proved that our TDLS algorithm could provide more flexible counterfactual visual explanation. At the end, we discussed several applicable scenarios of counterfactual visual explanations.
  arXiv  Detail & Related papers  (2021-08-08T15:27:14Z)
• MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning [65.52675802289775]
  We show that an uncertainty aware classifier can solve challenging reinforcement learning problems. We propose a novel method for computing the normalized maximum likelihood (NML) distribution. We show that the resulting algorithm has a number of intriguing connections to both count-based exploration methods and prior algorithms for learning reward functions.
  arXiv  Detail & Related papers  (2021-07-15T08:19:57Z)
• Search Methods for Sufficient, Socially-Aligned Feature Importance Explanations with In-Distribution Counterfactuals [72.00815192668193]
  Feature importance (FI) estimates are a popular form of explanation, and they are commonly created and evaluated by computing the change in model confidence caused by removing certain input features at test time. We study several under-explored dimensions of FI-based explanations, providing conceptual and empirical improvements for this form of explanation.
  arXiv  Detail & Related papers  (2021-06-01T20:36:48Z)
• Low-Regret Active learning [64.36270166907788]
  We develop an online learning algorithm for identifying unlabeled data points that are most informative for training. At the core of our work is an efficient algorithm for sleeping experts that is tailored to achieve low regret on predictable (easy) instances.
  arXiv  Detail & Related papers  (2021-04-06T22:53:45Z)
• PointHop++: A Lightweight Learning Model on Point Sets for 3D Classification [55.887502438160304]
  The PointHop method was recently proposed by Zhang et al. for 3D point cloud classification with unsupervised feature extraction. We improve the PointHop method furthermore in two aspects: 1) reducing its model complexity in terms of the model parameter number and 2) ordering discriminant features automatically based on the cross-entropy criterion. With experiments conducted on the ModelNet40 benchmark dataset, we show that the PointHop++ method performs on par with deep neural network (DNN) solutions and surpasses other unsupervised feature extraction methods.
  arXiv  Detail & Related papers  (2020-02-09T04:49:32Z)
• Black Box Explanation by Learning Image Exemplars in the Latent Feature Space [20.16179026989117]
  We present an approach to explain the decisions of black box models for image classification. Our method exploits the latent feature space learned through an adversarial autoencoder. We show that the proposed method outperforms existing explainers in terms of fidelity, relevance, coherence, and stability.
  arXiv  Detail & Related papers  (2020-01-27T15:42:14Z)
• Auditing and Debugging Deep Learning Models via Decision Boundaries: Individual-level and Group-level Analysis [0.0]
  We use flip points to explain, audit, and debug deep learning models. A flip point is any point that lies on the boundary between two output classes. We demonstrate our methods by investigating several models trained on standard datasets used in social applications of machine learning.
  arXiv  Detail & Related papers  (2020-01-03T01:45:36Z)

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.