Scientific Discovery by Generating Counterfactuals using Image Translation

• URL: http://arxiv.org/abs/2007.05500v2
• Date: Sun, 19 Jul 2020 23:38:22 GMT
• Title: Scientific Discovery by Generating Counterfactuals using Image Translation
• Authors: Arunachalam Narayanaswamy, Subhashini Venugopalan, Dale R. Webster, Lily Peng, Greg Corrado, Paisan Ruamviboonsuk, Pinal Bavishi, Rory Sayres, Abigail Huang, Siva Balasubramanian, Michael Brenner, Philip Nelson, and Avinash V. Varadarajan
• Abstract summary: We propose a framework to convert predictions from explanation techniques to a mechanism of discovery. We show how generative models in combination with black-box predictors can be used to generate hypotheses that can be critically examined. We demonstrate that the proposed framework is able to explain the underlying scientific mechanism, thus bridging the gap between the model's performance and human understanding.
• Score: 5.820406793815877
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Model explanation techniques play a critical role in understanding the source of a model's performance and making its decisions transparent. Here we investigate if explanation techniques can also be used as a mechanism for scientific discovery. We make three contributions: first, we propose a framework to convert predictions from explanation techniques to a mechanism of discovery. Second, we show how generative models in combination with black-box predictors can be used to generate hypotheses (without human priors) that can be critically examined. Third, with these techniques we study classification models for retinal images predicting Diabetic Macular Edema (DME), where recent work showed that a CNN trained on these images is likely learning novel features in the image. We demonstrate that the proposed framework is able to explain the underlying scientific mechanism, thus bridging the gap between the model's performance and human understanding.

Related papers

• Probabilistic Graphical Models: A Concise Tutorial [67.95025153592505]
  Probabilistic graphical modeling is a branch of machine learning that uses probability distributions to describe the world.<n>This tutorial provides a concise introduction to the formalisms, methods, and applications of this modeling framework.
  arXiv  Detail & Related papers  (2025-07-23T01:36:44Z)
• Learning Discrete Concepts in Latent Hierarchical Models [73.01229236386148]
  Learning concepts from natural high-dimensional data holds potential in building human-aligned and interpretable machine learning models. We formalize concepts as discrete latent causal variables that are related via a hierarchical causal model. We substantiate our theoretical claims with synthetic data experiments.
  arXiv  Detail & Related papers  (2024-06-01T18:01:03Z)
• CogDPM: Diffusion Probabilistic Models via Cognitive Predictive Coding [62.075029712357]
  This work introduces the Cognitive Diffusion Probabilistic Models (CogDPM) CogDPM features a precision estimation method based on the hierarchical sampling capabilities of diffusion models and weight the guidance with precision weights estimated by the inherent property of diffusion models. We apply CogDPM to real-world prediction tasks using the United Kindom precipitation and surface wind datasets.
  arXiv  Detail & Related papers  (2024-05-03T15:54:50Z)
• Interpretable Machine Learning for Weather and Climate Prediction: A Survey [24.028385794099435]
  We review current interpretable machine learning approaches applied to meteorological predictions. Design inherently interpretable models from scratch using architectures like tree ensembles and explainable neural networks. We discuss research challenges around achieving deeper mechanistic interpretations aligned with physical principles.
  arXiv  Detail & Related papers  (2024-03-24T14:23:35Z)
• Using generative AI to investigate medical imagery models and datasets [21.814095540433115]
  Explanations are needed in order to increase the trust in AI-based models. We present a method for automatic visual explanations leveraging team-based expertise. We demonstrate results on eight prediction tasks across three medical imaging modalities.
  arXiv  Detail & Related papers  (2023-06-01T17:59:55Z)
• Thermodynamics-inspired Explanations of Artificial Intelligence [0.0]
  We present Explainable Representations of AI and other black-box Paradigms (TERP) TERP is a method for generating accurate, and human-interpretable explanations for black-box predictions in a model-agnostic manner. To demonstrate the wide-ranging applicability of TERP, we successfully employ it to explain various black-box model architectures.
  arXiv  Detail & Related papers  (2022-06-27T17:36:50Z)
• EINNs: Epidemiologically-Informed Neural Networks [75.34199997857341]
  We introduce a new class of physics-informed neural networks-EINN-crafted for epidemic forecasting. We investigate how to leverage both the theoretical flexibility provided by mechanistic models as well as the data-driven expressability afforded by AI models.
  arXiv  Detail & Related papers  (2022-02-21T18:59:03Z)
• TorchEsegeta: Framework for Interpretability and Explainability of Image-based Deep Learning Models [0.0]
  Clinicians are often sceptical about applying automatic image processing approaches, especially deep learning based methods, in practice. This paper presents approaches that help to interpret and explain the results of deep learning algorithms by depicting the anatomical areas which influence the decision of the algorithm most. Research presents a unified framework, TorchEsegeta, for applying various interpretability and explainability techniques for deep learning models.
  arXiv  Detail & Related papers  (2021-10-16T01:00:15Z)
• Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations [64.85696493596821]
  In computer vision applications, generative counterfactual methods indicate how to perturb a model's input to change its prediction. We propose a counterfactual method that learns a perturbation in a disentangled latent space that is constrained using a diversity-enforcing loss. Our model improves the success rate of producing high-quality valuable explanations when compared to previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-03-18T12:57:34Z)
• Explainers in the Wild: Making Surrogate Explainers Robust to Distortions through Perception [77.34726150561087]
  We propose a methodology to evaluate the effect of distortions in explanations by embedding perceptual distances. We generate explanations for images in the Imagenet-C dataset and demonstrate how using a perceptual distances in the surrogate explainer creates more coherent explanations for the distorted and reference images.
  arXiv  Detail & Related papers  (2021-02-22T12:38:53Z)
• Deep Co-Attention Network for Multi-View Subspace Learning [73.3450258002607]
  We propose a deep co-attention network for multi-view subspace learning. It aims to extract both the common information and the complementary information in an adversarial setting. In particular, it uses a novel cross reconstruction loss and leverages the label information to guide the construction of the latent representation.
  arXiv  Detail & Related papers  (2021-02-15T18:46:44Z)
• Using StyleGAN for Visual Interpretability of Deep Learning Models on Medical Images [0.7874708385247352]
  We propose a new interpretability method that can be used to understand the predictions of any black-box model on images. A StyleGAN is trained on medical images to provide a mapping between latent vectors and images. By shifting the latent representation of an input image along this direction, we can produce a series of new synthetic images with changed predictions.
  arXiv  Detail & Related papers  (2021-01-19T11:13:20Z)

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.