A Sim2Real Approach for Identifying Task-Relevant Properties in Interpretable Machine Learning

• URL: http://arxiv.org/abs/2406.00116v1
• Date: Fri, 31 May 2024 18:08:35 GMT
• Title: A Sim2Real Approach for Identifying Task-Relevant Properties in Interpretable Machine Learning
• Authors: Eura Nofshin, Esther Brown, Brian Lim, Weiwei Pan, Finale Doshi-Velez,
• Abstract summary: We introduce a generalizable, cost-effective method for identifying task-relevant explanation properties in silico. We use our approach to identify relevant proxies for three example tasks and validate our simulation with real user studies.
• Score: 18.965568482077344
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Existing user studies suggest that different tasks may require explanations with different properties. However, user studies are expensive. In this paper, we introduce a generalizable, cost-effective method for identifying task-relevant explanation properties in silico, which can guide the design of more expensive user studies. We use our approach to identify relevant proxies for three example tasks and validate our simulation with real user studies.

Related papers

• Distribution Matching for Multi-Task Learning of Classification Tasks: a Large-Scale Study on Faces & Beyond [62.406687088097605]
  Multi-Task Learning (MTL) is a framework, where multiple related tasks are learned jointly and benefit from a shared representation space. We show that MTL can be successful with classification tasks with little, or non-overlapping annotations. We propose a novel approach, where knowledge exchange is enabled between the tasks via distribution matching.
  arXiv  Detail & Related papers  (2024-01-02T14:18:11Z)
• Assisting Human Decisions in Document Matching [52.79491990823573]
  We devise a proxy matching task that allows us to evaluate which kinds of assistive information improve decision makers' performance. We find that providing black-box model explanations reduces users' accuracy on the matching task. On the other hand, custom methods that are designed to closely attend to some task-specific desiderata are found to be effective in improving user performance.
  arXiv  Detail & Related papers  (2023-02-16T17:45:20Z)
• A Case Study on Designing Evaluations of ML Explanations with Simulated User Studies [6.2511886555343805]
  We conduct the first SimEvals on a real-world use case to evaluate whether explanations can better support ML-assisted decision-making in e-commerce fraud detection. We find that SimEvals suggest that all considered explainers are equally performant, and none beat a baseline without explanations.
  arXiv  Detail & Related papers  (2023-02-15T03:27:55Z)
• Complementary Explanations for Effective In-Context Learning [77.83124315634386]
  Large language models (LLMs) have exhibited remarkable capabilities in learning from explanations in prompts. This work aims to better understand the mechanisms by which explanations are used for in-context learning.
  arXiv  Detail & Related papers  (2022-11-25T04:40:47Z)
• Use-Case-Grounded Simulations for Explanation Evaluation [23.584251632331046]
  We introduce Use-Case-Grounded Simulated Evaluations (SimEvals) SimEvals involve training algorithmic agents that take as input the information content that would be presented to each participant in a human subject study. We run a comprehensive evaluation on three real-world use cases to demonstrate that Simevals can effectively identify which explanation methods will help humans for each use case.
  arXiv  Detail & Related papers  (2022-06-05T20:12:19Z)
• An Empirical Investigation of Representation Learning for Imitation [76.48784376425911]
  Recent work in vision, reinforcement learning, and NLP has shown that auxiliary representation learning objectives can reduce the need for large amounts of expensive, task-specific data. We propose a modular framework for constructing representation learning algorithms, then use our framework to evaluate the utility of representation learning for imitation.
  arXiv  Detail & Related papers  (2022-05-16T11:23:42Z)
• Reciprocal Feature Learning via Explicit and Implicit Tasks in Scene Text Recognition [60.36540008537054]
  In this work, we excavate the implicit task, character counting within the traditional text recognition, without additional labor annotation cost. We design a two-branch reciprocal feature learning framework in order to adequately utilize the features from both the tasks. Experiments on 7 benchmarks show the advantages of the proposed methods in both text recognition and the new-built character counting tasks.
  arXiv  Detail & Related papers  (2021-05-13T12:27:35Z)
• Reinforcement Learning with Prototypical Representations [114.35801511501639]
  Proto-RL is a self-supervised framework that ties representation learning with exploration through prototypical representations. These prototypes simultaneously serve as a summarization of the exploratory experience of an agent as well as a basis for representing observations. This enables state-of-the-art downstream policy learning on a set of difficult continuous control tasks.
  arXiv  Detail & Related papers  (2021-02-22T18:56:34Z)
• From Demonstrations to Task-Space Specifications: Using Causal Analysis to Extract Rule Parameterization from Demonstrations [16.330400985738205]
  We show that it is possible to learn generative models for distinct user behavioural types extracted from human demonstrations. We use these models to differentiate between user types and to find cases with overlapping solutions. Our method successfully identifies the correct type, within the specified time, in 99% [97.8 - 99.8] of the cases, which outperforms an IRL baseline.
  arXiv  Detail & Related papers  (2020-06-08T00:21:13Z)

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.