Optimal Interpretability-Performance Trade-off of Classification Trees with Black-Box Reinforcement Learning

• URL: http://arxiv.org/abs/2304.05839v1
• Date: Tue, 11 Apr 2023 09:43:23 GMT
• Title: Optimal Interpretability-Performance Trade-off of Classification Trees with Black-Box Reinforcement Learning
• Authors: Hector Kohler (Scool, CRIStAL), Riad Akrour (Scool, CRIStAL), Philippe Preux (Scool, CRIStAL)
• Abstract summary: Interpretability of AI models allows for user safety checks to build trust in these models. Decision trees (DTs) provide a global view on the learned model and clearly outlines the role of the features that are critical to classify a given data. To learn compact trees, a Reinforcement Learning framework has been recently proposed to explore the space of DTs.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Interpretability of AI models allows for user safety checks to build trust in these models. In particular, decision trees (DTs) provide a global view on the learned model and clearly outlines the role of the features that are critical to classify a given data. However, interpretability is hindered if the DT is too large. To learn compact trees, a Reinforcement Learning (RL) framework has been recently proposed to explore the space of DTs. A given supervised classification task is modeled as a Markov decision problem (MDP) and then augmented with additional actions that gather information about the features, equivalent to building a DT. By appropriately penalizing these actions, the RL agent learns to optimally trade-off size and performance of a DT. However, to do so, this RL agent has to solve a partially observable MDP. The main contribution of this paper is to prove that it is sufficient to solve a fully observable problem to learn a DT optimizing the interpretability-performance trade-off. As such any planning or RL algorithm can be used. We demonstrate the effectiveness of this approach on a set of classical supervised classification datasets and compare our approach with other interpretability-performance optimizing methods.

Related papers

• Self-supervised Preference Optimization: Enhance Your Language Model with Preference Degree Awareness [27.43137305486112]
  We propose a novel Self-supervised Preference Optimization (SPO) framework, which constructs a self-supervised preference degree loss combined with the alignment loss. The results demonstrate that SPO can be seamlessly integrated with existing preference optimization methods to achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-09-26T12:37:26Z)
• Interpretable Modeling of Deep Reinforcement Learning Driven Scheduling [3.890533943135602]
  We present a framework called IRL (Interpretable Reinforcement Learning) to address the issue of interpretability of DRL scheduling. ILR is capable of converting a black-box DNN policy into an interpretable rulebased decision tree while maintaining comparable scheduling performance.
  arXiv  Detail & Related papers  (2024-03-24T20:56:16Z)
• Analyzing Adversarial Inputs in Deep Reinforcement Learning [53.3760591018817]
  We present a comprehensive analysis of the characterization of adversarial inputs, through the lens of formal verification. We introduce a novel metric, the Adversarial Rate, to classify models based on their susceptibility to such perturbations. Our analysis empirically demonstrates how adversarial inputs can affect the safety of a given DRL system with respect to such perturbations.
  arXiv  Detail & Related papers  (2024-02-07T21:58:40Z)
• Learning Interpretable Rules for Scalable Data Representation and Classification [11.393431987232425]
  Rule-based Learner Representation (RRL) learns interpretable non-fuzzy rules for data representation and classification. RRL can be easily adjusted to obtain a trade-off between classification accuracy and model complexity for different scenarios.
  arXiv  Detail & Related papers  (2023-10-22T15:55:58Z)
• Limits of Actor-Critic Algorithms for Decision Tree Policies Learning in IBMDPs [9.587070290189507]
  Interpretability of AI models allows for user safety checks to build trust in such AIs. Decision Trees (DTs) provide a global look at the learned model and transparently reveal which features of the input are critical for making a decision. Recent Reinforcement Learning framework has been proposed to explore the space of DTs using deep RL.
  arXiv  Detail & Related papers  (2023-09-23T13:06:20Z)
• Denoised MDPs: Learning World Models Better Than the World Itself [94.74665254213588]
  This work categorizes information out in the wild into four types based on controllability and relation with reward, and formulates useful information as that which is both controllable and reward-relevant. Experiments on variants of DeepMind Control Suite and RoboDesk demonstrate superior performance of our denoised world model over using raw observations alone.
  arXiv  Detail & Related papers  (2022-06-30T17:59:49Z)
• MACE: An Efficient Model-Agnostic Framework for Counterfactual Explanation [132.77005365032468]
  We propose a novel framework of Model-Agnostic Counterfactual Explanation (MACE) In our MACE approach, we propose a novel RL-based method for finding good counterfactual examples and a gradient-less descent method for improving proximity. Experiments on public datasets validate the effectiveness with better validity, sparsity and proximity.
  arXiv  Detail & Related papers  (2022-05-31T04:57:06Z)
• Optimal Decision Diagrams for Classification [68.72078059880018]
  We study the training of optimal decision diagrams from a mathematical programming perspective. We introduce a novel mixed-integer linear programming model for training. We show how this model can be easily extended for fairness, parsimony, and stability notions.
  arXiv  Detail & Related papers  (2022-05-28T18:31:23Z)
• Feeding What You Need by Understanding What You Learned [54.400455868448695]
  Machine Reading (MRC) reveals the ability to understand a given text passage and answer questions based on it. Existing research works in MRC rely heavily on large-size models and corpus to improve the performance evaluated by metrics such as Exact Match. We argue that a deep understanding of model capabilities and data properties can help us feed a model with appropriate training data.
  arXiv  Detail & Related papers  (2022-03-05T14:15:59Z)
• Scalable Rule-Based Representation Learning for Interpretable Classification [12.736847587988853]
  Rule-based Learner Representation (RRL) learns interpretable non-fuzzy rules for data representation and classification. RRL can be easily adjusted to obtain a trade-off between classification accuracy and model complexity for different scenarios.
  arXiv  Detail & Related papers  (2021-09-30T13:07:42Z)
• Prototypical Contrastive Learning of Unsupervised Representations [171.3046900127166]
  Prototypical Contrastive Learning (PCL) is an unsupervised representation learning method. PCL implicitly encodes semantic structures of the data into the learned embedding space. PCL outperforms state-of-the-art instance-wise contrastive learning methods on multiple benchmarks.
  arXiv  Detail & Related papers  (2020-05-11T09:53:36Z)

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.