Error Detection and Constraint Recovery in Hierarchical Multi-Label Classification without Prior Knowledge

TL;DR

This paper introduces an error detection approach using explainable rules that identifies classifier errors and recovers constraints for hierarchical multi-label classification without prior knowledge, enhancing model reliability.

Contribution

It presents a novel Error Detection Rules (EDR) method that learns explainable failure modes and constraints, removing the need for pre-existing constraints in hierarchical multi-label classification.

Findings

Effective error detection and constraint recovery demonstrated

Approach is noise tolerant and adaptable to multiple datasets

Includes a new military vehicle recognition dataset

Abstract

Recent advances in Hierarchical Multi-label Classification (HMC), particularly neurosymbolic-based approaches, have demonstrated improved consistency and accuracy by enforcing constraints on a neural model during training. However, such work assumes the existence of such constraints a-priori. In this paper, we relax this strong assumption and present an approach based on Error Detection Rules (EDR) that allow for learning explainable rules about the failure modes of machine learning models. We show that these rules are not only effective in detecting when a machine learning classifier has made an error but also can be leveraged as constraints for HMC, thereby allowing the recovery of explainable constraints even if they are not provided. We show that our approach is effective in detecting machine learning errors and recovering constraints, is noise tolerant, and can function as a source of knowledge for neurosymbolic models on multiple datasets, including a newly introduced military vehicle recognition dataset.