Pith. sign in

REVIEW 4 cited by

Transformer Embeddings of Irregularly Spaced Events and Their Participants

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2201.00044 v3 pith:EYLIF727 submitted 2021-12-31 cs.LG cs.AIcs.LO

classification cs.LGcs.AIcs.LO
keywords databaseeventeventsarchitecturesattention-basedgenerativeirregularlymodel
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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 the 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).

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. SurF: A Generative Model for Multivariate Irregular Time Series Forecasting

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    SurF applies the Time Rescaling Theorem as a learnable bijection to create a single generative model for forecasting irregular multivariate event streams that outperforms or matches baselines on six benchmarks.

  2. Deep Kernel Learning for Stratifying Glaucoma Trajectories

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    A deep kernel learning architecture with transformer feature extraction on clinical-BERT embeddings and Gaussian process backend identifies three glaucoma subgroups by decoupling progression trajectories from current ...

  3. Towards Event-Aware Forecasting in DeFi: Insights from On-chain Automated Market Maker Protocols

    cs.LG 2026-04 unverdicted novelty 6.0 of 10

    New 8.9M-event dataset from Pendle, Uniswap v3, Aave and Morpho plus UWM loss yields 56.41% average reduction in time-prediction error for TPP models while preserving event-type accuracy.

  4. In-Context Learning of Temporal Point Processes with Foundation Inference Models

    cs.LG 2025-09 conditional novelty 6.0 of 10

    A pretrained in-context transformer infers Hawkes-style conditional intensities from event histories and transfers zero-shot to real-world event data, roughly matching specialized models after finetuning.

Pith tools