DeepAI AI Chat
Log In Sign Up

Label-Descriptive Patterns and their Application to Characterizing Classification Errors

by   Michael Hedderich, et al.
Max Planck Society
Universität Saarland

State-of-the-art deep learning methods achieve human-like performance on many tasks, but make errors nevertheless. Characterizing these errors in easily interpretable terms gives insight into whether a model is prone to making systematic errors, but also gives a way to act and improve the model. In this paper we propose a method that allows us to do so for arbitrary classifiers by mining a small set of patterns that together succinctly describe the input data that is partitioned according to correctness of prediction. We show this is an instance of the more general label description problem, which we formulate in terms of the Minimum Description Length principle. To discover good pattern sets we propose the efficient and hyperparameter-free Premise algorithm, which through an extensive set of experiments we show on both synthetic and real-world data performs very well in practice; unlike existing solutions it ably recovers ground truth patterns, even on highly imbalanced data over many unique items, or where patterns are only weakly associated to labels. Through two real-world case studies we confirm that Premise gives clear and actionable insight into the systematic errors made by modern NLP classifiers.


page 1

page 2

page 3

page 4


Keeping it Short and Simple: Summarising Complex Event Sequences with Multivariate Patterns

We study how to obtain concise descriptions of discrete multivariate seq...

Towards Interpretable Graph Modeling with Vertex Replacement Grammars

An enormous amount of real-world data exists in the form of graphs. Ofte...

A Subsequence Interleaving Model for Sequential Pattern Mining

Recent sequential pattern mining methods have used the minimum descripti...

Graph Similarity Description: How Are These Graphs Similar?

How do social networks differ across platforms? How do information netwo...

TrustNet: Learning from Trusted Data Against (A)symmetric Label Noise

Robustness to label noise is a critical property for weakly-supervised c...

Algebraic Ground Truth Inference: Non-Parametric Estimation of Sample Errors by AI Algorithms

Binary classification is widely used in ML production systems. Monitorin...

RVSL: Robust Vehicle Similarity Learning in Real Hazy Scenes Based on Semi-supervised Learning

Recently, vehicle similarity learning, also called re-identification (Re...