Interpretable Mesomorphic Networks for Tabular Data

• URL: http://arxiv.org/abs/2305.13072v2
• Date: Wed, 30 Oct 2024 13:54:09 GMT
• Title: Interpretable Mesomorphic Networks for Tabular Data
• Authors: Arlind Kadra, Sebastian Pineda Arango, Josif Grabocka,
• Abstract summary: We propose a new class of interpretable neural networks that are both deep and linear at the same time. We optimize deep hypernetworks to generate explainable linear models on a per-instance basis.
• Score: 25.76214343259399
• License:
• Abstract: Even though neural networks have been long deployed in applications involving tabular data, still existing neural architectures are not explainable by design. In this paper, we propose a new class of interpretable neural networks for tabular data that are both deep and linear at the same time (i.e. mesomorphic). We optimize deep hypernetworks to generate explainable linear models on a per-instance basis. As a result, our models retain the accuracy of black-box deep networks while offering free-lunch explainability for tabular data by design. Through extensive experiments, we demonstrate that our explainable deep networks have comparable performance to state-of-the-art classifiers on tabular data and outperform current existing methods that are explainable by design.

Related papers

• Escaping the Forest: Sparse Interpretable Neural Networks for Tabular Data [0.0]
  We show that our models, Sparse TABular NET or sTAB-Net with attention mechanisms, are more effective than tree-based models. They achieve better performance than post-hoc methods like SHAP.
  arXiv  Detail & Related papers  (2024-10-23T10:50:07Z)
• Coding schemes in neural networks learning classification tasks [52.22978725954347]
  We investigate fully-connected, wide neural networks learning classification tasks. We show that the networks acquire strong, data-dependent features. Surprisingly, the nature of the internal representations depends crucially on the neuronal nonlinearity.
  arXiv  Detail & Related papers  (2024-06-24T14:50:05Z)
• Unveiling Invariances via Neural Network Pruning [44.47186380630998]
  Invariance describes transformations that do not alter data's underlying semantics. Modern networks are handcrafted to handle well-known invariances. We propose a framework to learn novel network architectures that capture data-dependent invariances via pruning.
  arXiv  Detail & Related papers  (2023-09-15T05:38:33Z)
• Transfer Learning with Deep Tabular Models [66.67017691983182]
  We show that upstream data gives tabular neural networks a decisive advantage over GBDT models. We propose a realistic medical diagnosis benchmark for tabular transfer learning. We propose a pseudo-feature method for cases where the upstream and downstream feature sets differ.
  arXiv  Detail & Related papers  (2022-06-30T14:24:32Z)
• Dynamic Inference with Neural Interpreters [72.90231306252007]
  We present Neural Interpreters, an architecture that factorizes inference in a self-attention network as a system of modules. inputs to the model are routed through a sequence of functions in a way that is end-to-end learned. We show that Neural Interpreters perform on par with the vision transformer using fewer parameters, while being transferrable to a new task in a sample efficient manner.
  arXiv  Detail & Related papers  (2021-10-12T23:22:45Z)
• XBNet : An Extremely Boosted Neural Network [0.0]
  XBNet tries to combine tree-based models with that of neural networks to create a robust architecture trained by using a novel optimization technique, Boosted Gradient Descent for Tabular Data. In this paper, we describe a novel architecture XBNet, which tries to combine tree-based models with that of neural networks to create a robust architecture trained by using a novel optimization technique, Boosted Gradient Descent for Tabular Data.
  arXiv  Detail & Related papers  (2021-06-09T17:31:50Z)
• TabularNet: A Neural Network Architecture for Understanding Semantic Structures of Tabular Data [30.479822289380255]
  We propose a novel neural network architecture, TabularNet, to simultaneously extract spatial and relational information from tables. For relational information, we design a new graph construction method based on the WordNet tree and adopt a Graph Convolutional Network (GCN) based encoder. Our neural network architecture can be a unified neural backbone for different understanding tasks and utilized in a multitask scenario.
  arXiv  Detail & Related papers  (2021-06-06T11:48:09Z)
• Leveraging Sparse Linear Layers for Debuggable Deep Networks [86.94586860037049]
  We show how fitting sparse linear models over learned deep feature representations can lead to more debuggable neural networks. The resulting sparse explanations can help to identify spurious correlations, explain misclassifications, and diagnose model biases in vision and language tasks.
  arXiv  Detail & Related papers  (2021-05-11T08:15:25Z)
• Reservoir Memory Machines as Neural Computers [70.5993855765376]
  Differentiable neural computers extend artificial neural networks with an explicit memory without interference. We achieve some of the computational capabilities of differentiable neural computers with a model that can be trained very efficiently.
  arXiv  Detail & Related papers  (2020-09-14T12:01:30Z)
• Neural networks adapting to datasets: learning network size and topology [77.34726150561087]
  We introduce a flexible setup allowing for a neural network to learn both its size and topology during the course of a gradient-based training. The resulting network has the structure of a graph tailored to the particular learning task and dataset.
  arXiv  Detail & Related papers  (2020-06-22T12:46:44Z)

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.