Transformer Embeddings of Irregularly Spaced Events and Their ParticipantsDownload PDF

Published: 28 Jan 2022, Last Modified: 13 Feb 2023ICLR 2022 PosterReaders: Everyone
Keywords: irregular time series, generative Transformers, neuro-symbolic architectures, logic programming
Abstract: The neural Hawkes process (Mei & Eisner, 2017) is a generative model of irregularly spaced sequences of discrete events. To handle complex domains with many event types, Mei et al. (2020a) further consider a setting in which each event in the sequence updates a deductive database of facts (via domain-specific pattern-matching rules); future events are then conditioned on the database contents. They show how to convert such a symbolic system into a neuro-symbolic continuous-time generative model, in which each database fact and possible event has a time-varying embedding that is derived from its symbolic provenance. In this paper, we modify both models, replacing their recurrent LSTM-based architectures with flatter attention-based architectures (Vaswani et al., 2017), which are simpler and more parallelizable. This does not appear to hurt our accuracy, which is comparable to or better than that of the original models as well as (where applicable) previous attention-based methods (Zuo et al., 2020; Zhang et al., 2020a).
One-sentence Summary: We design a generative continuous-time Transformer for embedding irregularly spaced events and their participants.
27 Replies