Interpretable by Design: Learning Predictors by Composing Interpretable Queries

• URL: http://arxiv.org/abs/2207.00938v1
• Date: Sun, 3 Jul 2022 02:40:34 GMT
• Title: Interpretable by Design: Learning Predictors by Composing Interpretable Queries
• Authors: Aditya Chattopadhyay, Stewart Slocum, Benjamin D. Haeffele, Rene Vidal and Donald Geman
• Abstract summary: We argue that machine learning algorithms should be interpretable by design. We minimize the expected number of queries needed for accurate prediction. Experiments on vision and NLP tasks demonstrate the efficacy of our approach.
• Score: 8.054701719767293
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: There is a growing concern about typically opaque decision-making with high-performance machine learning algorithms. Providing an explanation of the reasoning process in domain-specific terms can be crucial for adoption in risk-sensitive domains such as healthcare. We argue that machine learning algorithms should be interpretable by design and that the language in which these interpretations are expressed should be domain- and task-dependent. Consequently, we base our model's prediction on a family of user-defined and task-specific binary functions of the data, each having a clear interpretation to the end-user. We then minimize the expected number of queries needed for accurate prediction on any given input. As the solution is generally intractable, following prior work, we choose the queries sequentially based on information gain. However, in contrast to previous work, we need not assume the queries are conditionally independent. Instead, we leverage a stochastic generative model (VAE) and an MCMC algorithm (Unadjusted Langevin) to select the most informative query about the input based on previous query-answers. This enables the online determination of a query chain of whatever depth is required to resolve prediction ambiguities. Finally, experiments on vision and NLP tasks demonstrate the efficacy of our approach and its superiority over post-hoc explanations.

Related papers

• Likelihood as a Performance Gauge for Retrieval-Augmented Generation [78.28197013467157]
  We show that likelihoods serve as an effective gauge for language model performance. We propose two methods that use question likelihood as a gauge for selecting and constructing prompts that lead to better performance.
  arXiv  Detail & Related papers  (2024-11-12T13:14:09Z)
• Generating Feasible and Plausible Counterfactual Explanations for Outcome Prediction of Business Processes [45.502284864662585]
  We introduce a data-driven approach, REVISEDplus, to generate plausible counterfactual explanations. First, we restrict the counterfactual algorithm to generate counterfactuals that lie within a high-density region of the process data. We also ensure plausibility by learning sequential patterns between the activities in the process cases.
  arXiv  Detail & Related papers  (2024-03-14T09:56:35Z)
• Learning-Augmented Algorithms with Explicit Predictors [67.02156211760415]
  Recent advances in algorithmic design show how to utilize predictions obtained by machine learning models from past and present data. Prior research in this context was focused on a paradigm where the predictor is pre-trained on past data and then used as a black box. In this work, we unpack the predictor and integrate the learning problem it gives rise for within the algorithmic challenge.
  arXiv  Detail & Related papers  (2024-03-12T08:40:21Z)
• Clarify When Necessary: Resolving Ambiguity Through Interaction with LMs [58.620269228776294]
  We propose a task-agnostic framework for resolving ambiguity by asking users clarifying questions. We evaluate systems across three NLP applications: question answering, machine translation and natural language inference. We find that intent-sim is robust, demonstrating improvements across a wide range of NLP tasks and LMs.
  arXiv  Detail & Related papers  (2023-11-16T00:18:50Z)
• Variational Information Pursuit for Interpretable Predictions [8.894670614193677]
  Variational Information Pursuit (V-IP) is a variational characterization of IP which bypasses the need for learning generative models. V-IP finds much shorter query chains when compared to reinforcement learning which is typically used in sequential-decision-making problems. We demonstrate the utility of V-IP on challenging tasks like medical diagnosis where the performance is far superior to the generative modelling approach.
  arXiv  Detail & Related papers  (2023-02-06T15:43:48Z)
• Explainable Data-Driven Optimization: From Context to Decision and Back Again [76.84947521482631]
  Data-driven optimization uses contextual information and machine learning algorithms to find solutions to decision problems with uncertain parameters. We introduce a counterfactual explanation methodology tailored to explain solutions to data-driven problems. We demonstrate our approach by explaining key problems in operations management such as inventory management and routing.
  arXiv  Detail & Related papers  (2023-01-24T15:25:16Z)
• What Should I Know? Using Meta-gradient Descent for Predictive Feature Discovery in a Single Stream of Experience [63.75363908696257]
  computational reinforcement learning seeks to construct an agent's perception of the world through predictions of future sensations. An open challenge in this line of work is determining from the infinitely many predictions that the agent could possibly make which predictions might best support decision-making. We introduce a meta-gradient descent process by which an agent learns what predictions to make, 2) the estimates for its chosen predictions, and 3) how to use those estimates to generate policies that maximize future reward.
  arXiv  Detail & Related papers  (2022-06-13T21:31:06Z)
• An Explainable Regression Framework for Predicting Remaining Useful Life of Machines [6.374451442486538]
  This paper proposes an explainable regression framework for the prediction of machines' Remaining Useful Life (RUL) We also evaluate several Machine Learning (ML) algorithms including classical and Neural Networks (NNs) based solutions for the task.
  arXiv  Detail & Related papers  (2022-04-28T15:44:12Z)
• Non-Clairvoyant Scheduling with Predictions Revisited [77.86290991564829]
  In non-clairvoyant scheduling, the task is to find an online strategy for scheduling jobs with a priori unknown processing requirements. We revisit this well-studied problem in a recently popular learning-augmented setting that integrates (untrusted) predictions in algorithm design. We show that these predictions have desired properties, admit a natural error measure as well as algorithms with strong performance guarantees.
  arXiv  Detail & Related papers  (2022-02-21T13:18:11Z)
• Learning Optimal Representations with the Decodable Information Bottleneck [43.30367159353152]
  In machine learning, our goal is not compression but rather generalization, which is intimately linked to the predictive family or decoder of interest. We propose the Decodable Information Bottleneck (DIB) that considers information retention and compression from the perspective of the desired predictive family. As a result, DIB gives rise to representations that are optimal in terms of expected test performance and can be estimated with guarantees.
  arXiv  Detail & Related papers  (2020-09-27T08:33:08Z)

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.