• Corpus ID: 252873687

Parameter Averaging for Feature Ranking

  title={Parameter Averaging for Feature Ranking},
  author={Talip Ucar and Ehsan Hajiramezanali},
Neural Networks are known to be sensitive to initialisation. The methods that rely on neural networks for feature ranking are not robust since they can have variations in their ranking when the model is initialized and trained with different random seeds. In this work, we introduce a novel method based on parameter averaging to estimate accurate and robust feature importance in tabular data setting, referred as XTab. We first initialize and train multiple instances of a shallow network (referred… 



PyTorch: An Imperative Style, High-Performance Deep Learning Library

This paper details the principles that drove the implementation of PyTorch and how they are reflected in its architecture, and explains how the careful and pragmatic implementation of the key components of its runtime enables them to work together to achieve compelling performance.

Axiomatic Attribution for Deep Networks

We study the problem of attributing the prediction of a deep network to its input features, a problem previously studied by several other works. We identify two fundamental axioms— Sensitivity and

Greedy function approximation: A gradient boosting machine.

A general gradient descent boosting paradigm is developed for additive expansions based on any fitting criterion, and specific algorithms are presented for least-squares, least absolute deviation, and Huber-M loss functions for regression, and multiclass logistic likelihood for classification.

Learning to Explain: An Information-Theoretic Perspective on Model Interpretation

An efficient variational approximation to the mutual information is developed, and the effectiveness of the method is shown on a variety of synthetic and real data sets using both quantitative metrics and human evaluation.

Communication-Efficient Learning of Deep Networks from Decentralized Data

This work presents a practical method for the federated learning of deep networks based on iterative model averaging, and conducts an extensive empirical evaluation, considering five different model architectures and four datasets.

Scaling Up the Accuracy of Naive-Bayes Classifiers: A Decision-Tree Hybrid

A new algorithm, NBTree, is proposed, which induces a hybrid of decision-tree classifiers and Naive-Bayes classifiers: the decision-Tree nodes contain univariate splits as regular decision-trees, but the leaves contain Naïve-Bayesian classifiers.

SubTab: Subsetting Features of Tabular Data for Self-Supervised Representation Learning

This paper introduces a new framework, Subsetting features of Tabular data (SubTab), that turns the task of learning from tabular data into a multi-view representation learning problem by dividing the input features to multiple subsets and argues that reconstructing the data from the subset of its features rather than its corrupted version in an autoencoder setting can better capture its underlying latent representation.

TabNet: Attentive Interpretable Tabular Learning

It is demonstrated that TabNet outperforms other neural network and decision tree variants on a wide range of non-performance-saturated tabular datasets and yields interpretable feature attributions plus insights into the global model behavior.

INVASE: Instance-wise Variable Selection using Neural Networks

Long Short-Term Memory

A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.