Deep Weighted Averaging Classifiers

By Dallas Card, Michael J.Q. Zhang, Noah A. Smith. 2018

42 citations recorded by the source corpus.

Recent advances in deep learning have achieved impressive gains in classification accuracy on a variety of types of data, including images and text. Despite these gains, however, concerns have been raised about the calibration, robustness, and interpretability of these models. In this paper we propose a simple way to modify any conventional deep architecture to automatically provide more transparent explanations for classification decisions, as well as an intuitive notion of the credibility of each prediction. Specifically, we draw on ideas from nonparametric kernel regression, and propose to predict labels based on a weighted sum of training instances, where the weights are determined by distance in a learned instance-embedding space. Working within the framework of conformal methods, we propose a new measure of nonconformity suggested by our model, and experimentally validate the accompanying theoretical expectations, demonstrating improved transparency, controlled error rates, and robustness to out-of-domain data, without compromising on accuracy or calibration.

Subfields: Artificial Intelligence, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Safety, Robustness & Interpretability

Citations in the corpus

Pretrained Transformers Improve Out-of-Distribution Robustness (2020, methodology): “We decompose OOD robustness into a model’s ability to (1) generalize and to (2) detect OOD examples (Card et al., 2018).”
Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges (2021, background): “[46] introduced a deep weighted averaging classifier, which classifies”
Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions (2020, methodology): “Other methods that can trace the model’s decision back into the training examples include deep weighted averaging classifiers (Card et al., 2019), which make decisions based on the labels of training examples that are most similar to the test input by some distance metrics. Croce et al. (2019) use k”
Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates (2021, background): “Models designed with explicit interpretability considerations like deep weighted averaging classifiers (Card et al., 2019) and SelfExplain (Rajagopal et al.”
How Case-Based Reasoning Explains Neural Networks: A Theoretical Analysis of XAI Using Post-Hoc Explanation-by-Example from a Survey of ANN-CBR Twin-Systems (2019, methodology): “Another approach tries to map the layers of a DNN onto particular exemplar cases using Deep k - Nearest neighbors (DkNN) [71, 91, 92].”