Classification Models for Partially Ordered Sequences
This addresses a gap in classification models for data with partial order, which is incremental as it adapts transformers to a specific scenario.
The paper tackles the problem of classifying partially-ordered sequences, where events have uncertain or granular timestamps, by introducing a novel transformer-based model. The result shows that this model outperforms extensions of existing set models on three datasets, though no concrete numbers are provided.
Many models such as Long Short Term Memory (LSTMs), Gated Recurrent Units (GRUs) and transformers have been developed to classify time series data with the assumption that events in a sequence are ordered. On the other hand, fewer models have been developed for set based inputs, where order does not matter. There are several use cases where data is given as partially-ordered sequences because of the granularity or uncertainty of time stamps. We introduce a novel transformer based model for such prediction tasks, and benchmark against extensions of existing order invariant models. We also discuss how transition probabilities between events in a sequence can be used to improve model performance. We show that the transformer-based equal-time model outperforms extensions of existing set models on three data sets.