REVIEW 2 cited by
Gated Transformer Networks for Multivariate Time Series Classification
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
read the original abstract
Deep learning model (primarily convolutional networks and LSTM) for time series classification has been studied broadly by the community with the wide applications in different domains like healthcare, finance, industrial engineering and IoT. Meanwhile, Transformer Networks recently achieved frontier performance on various natural language processing and computer vision tasks. In this work, we explored a simple extension of the current Transformer Networks with gating, named Gated Transformer Networks (GTN) for the multivariate time series classification problem. With the gating that merges two towers of Transformer which model the channel-wise and step-wise correlations respectively, we show how GTN is naturally and effectively suitable for the multivariate time series classification task. We conduct comprehensive experiments on thirteen dataset with full ablation study. Our results show that GTN is able to achieve competing results with current state-of-the-art deep learning models. We also explored the attention map for the natural interpretability of GTN on time series modeling. Our preliminary results provide a strong baseline for the Transformer Networks on multivariate time series classification task and grounds the foundation for future research.
Forward citations
Cited by 2 Pith papers
-
HealthCAT: An Interpretable Encoder-only Transformer Framework for Health Indicator Prediction and Temporal Interpretation of Wearable Sensor Data
A transformer with AttentiveCAT yields class-specific, time-step importance scores for wearable health data, beats deep-learning baselines, and beats random time-step selection in masking tests.
-
InstructTime++: Time Series Classification with Multimodal Language Modeling via Implicit Feature Enhancement
A generative framework that discretizes time series into tokens and uses a language model with added statistical and visual text features to classify them beats several discriminative neural baselines on five benchmarks.
Discussion (0). Continue with ORCID to comment.