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

Our contributions are as follows: Recent advances in Hierarchical Multi-label Classification (HMC), particularly neurosymbolic-based approaches, have demonstrated We extend the EDR framework of [32] to address the HMC improved consistency and accuracy by enforcing constraints on problem without prior knowledge of the hierarchy by both a neural model during training. However, such work assumes the extending the language of that work and presenting a new existence of such constraints a-priori. In this paper, we relax this Focused-EDR which addresses an objective function mismatch strong assumption and present an approach based on Error Detection of [32] by leveraging approximate optimization of Rules (EDR) that allow for learning explainable rules about the ratio of two submodular functions; the failure modes of machine learning models. We show that these We demonstrate how our new approach, provides significant rules are not only effective in detecting when a machine learning improvement in the detection of errors when compared to a classifier has made an error but also can be leveraged as constraints black-box baseline neural error detector and the detection for HMC, thereby allowing the recovery of explainable constraints algorithm of [32] on three different HMC datasets; even if they are not provided. We show that our approach is effective We show our approach can recover constraints and that in detecting machine learning errors and recovering constraints, both the F1-score of constraints recovered as well as error is noise tolerant, and can function as a source of knowledge for F1 degrades gracefully with noise - with noise injected in a neurosymbolic models on multiple datasets, including a newly introduced manner to remove certain classes from consideration; military vehicle recognition dataset. We show the recovered constraints can then be used as a source for in neurosymbolic model learning (i.e., Logic Tensor Networks (LTN) [4]) to provide improved model performance