Constraint-aware Learning of Probabilistic Sequential Models for Multi-Label Classification
This addresses multi-label classification problems with constraints, but it appears incremental as it builds on existing sequential models without introducing a fundamentally new approach.
The paper tackled multi-label classification with logical constraints by using an expressive sequential model to produce a joint distribution, demonstrating empirically that the architecture can exploit constraints during training and enforce them at inference.
We investigate multi-label classification involving large sets of labels, where the output labels may be known to satisfy some logical constraints. We look at an architecture in which classifiers for individual labels are fed into an expressive sequential model, which produces a joint distribution. One of the potential advantages for such an expressive model is its ability to modelling correlations, as can arise from constraints. We empirically demonstrate the ability of the architecture both to exploit constraints in training and to enforce constraints at inference time.