Learning outside the Black-Box: The pursuit of interpretable models
- URL: http://arxiv.org/abs/2011.08596v1
- Date: Tue, 17 Nov 2020 12:39:44 GMT
- Title: Learning outside the Black-Box: The pursuit of interpretable models
- Authors: Jonathan Crabb\'e, Yao Zhang, William Zame, Mihaela van der Schaar
- Abstract summary: This paper proposes an algorithm that produces a continuous global interpretation of any given continuous black-box function.
Our interpretation represents a leap forward from the previous state of the art.
- Score: 78.32475359554395
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Machine Learning has proved its ability to produce accurate models but the
deployment of these models outside the machine learning community has been
hindered by the difficulties of interpreting these models. This paper proposes
an algorithm that produces a continuous global interpretation of any given
continuous black-box function. Our algorithm employs a variation of projection
pursuit in which the ridge functions are chosen to be Meijer G-functions,
rather than the usual polynomial splines. Because Meijer G-functions are
differentiable in their parameters, we can tune the parameters of the
representation by gradient descent; as a consequence, our algorithm is
efficient. Using five familiar data sets from the UCI repository and two
familiar machine learning algorithms, we demonstrate that our algorithm
produces global interpretations that are both highly accurate and parsimonious
(involve a small number of terms). Our interpretations permit easy
understanding of the relative importance of features and feature interactions.
Our interpretation algorithm represents a leap forward from the previous state
of the art.
Related papers
- On Discriminative Probabilistic Modeling for Self-Supervised Representation Learning [85.75164588939185]
We study the discriminative probabilistic modeling problem on a continuous domain for (multimodal) self-supervised representation learning.
We conduct generalization error analysis to reveal the limitation of current InfoNCE-based contrastive loss for self-supervised representation learning.
arXiv Detail & Related papers (2024-10-11T18:02:46Z) - How Graph Neural Networks Learn: Lessons from Training Dynamics [80.41778059014393]
We study the training dynamics in function space of graph neural networks (GNNs)
We find that the gradient descent optimization of GNNs implicitly leverages the graph structure to update the learned function.
This finding offers new interpretable insights into when and why the learned GNN functions generalize.
arXiv Detail & Related papers (2023-10-08T10:19:56Z) - Interpretability at Scale: Identifying Causal Mechanisms in Alpaca [62.65877150123775]
We use Boundless DAS to efficiently search for interpretable causal structure in large language models while they follow instructions.
Our findings mark a first step toward faithfully understanding the inner-workings of our ever-growing and most widely deployed language models.
arXiv Detail & Related papers (2023-05-15T17:15:40Z) - Interpreting Black-box Machine Learning Models for High Dimensional
Datasets [40.09157165704895]
We train a black-box model on a high-dimensional dataset to learn the embeddings on which the classification is performed.
We then approximate the behavior of the black-box model by means of an interpretable surrogate model on the top-k feature space.
Our approach outperforms state-of-the-art methods like TabNet and XGboost when tested on different datasets.
arXiv Detail & Related papers (2022-08-29T07:36:17Z) - Invariant Causal Mechanisms through Distribution Matching [86.07327840293894]
In this work we provide a causal perspective and a new algorithm for learning invariant representations.
Empirically we show that this algorithm works well on a diverse set of tasks and in particular we observe state-of-the-art performance on domain generalization.
arXiv Detail & Related papers (2022-06-23T12:06:54Z) - Model-agnostic interpretation by visualization of feature perturbations [0.0]
We propose a model-agnostic interpretation approach that uses visualization of feature perturbations induced by the particle swarm optimization algorithm.
We validate our approach both qualitatively and quantitatively on publicly available datasets.
arXiv Detail & Related papers (2021-01-26T00:53:29Z) - Interactive slice visualization for exploring machine learning models [0.0]
We use interactive visualization of slices of predictor space to address the interpretability deficit.
In effect, we open up the black-box of machine learning algorithms, for the purpose of interrogating, explaining, validating and comparing model fits.
arXiv Detail & Related papers (2021-01-18T10:47:53Z) - Deducing neighborhoods of classes from a fitted model [68.8204255655161]
In this article a new kind of interpretable machine learning method is presented.
It can help to understand the partitioning of the feature space into predicted classes in a classification model using quantile shifts.
Basically, real data points (or specific points of interest) are used and the changes of the prediction after slightly raising or decreasing specific features are observed.
arXiv Detail & Related papers (2020-09-11T16:35:53Z) - Classification Under Human Assistance [29.220005688025378]
We show that supervised learning models trained to operate under different automation levels can outperform those trained for full automation as well as humans operating alone.
Experiments on synthetic and real-world data from several applications in medical diagnosis illustrate our theoretical findings.
arXiv Detail & Related papers (2020-06-21T16:52:37Z)
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.