The Tiny Time-series Transformer: Low-latency High-throughput Classification of Astronomical Transients using Deep Model Compression

• URL: http://arxiv.org/abs/2303.08951v1
• Date: Wed, 15 Mar 2023 21:46:35 GMT
• Title: The Tiny Time-series Transformer: Low-latency High-throughput Classification of Astronomical Transients using Deep Model Compression
• Authors: Tarek Allam Jr., Julien Peloton, Jason D. McEwen
• Abstract summary: The upcoming Legacy Survey of Space and Time (LSST) will raise the big-data bar for time-domain astronomy. We show how the use of modern deep compression methods can achieve a $18times$ reduction in model size. We also show that in addition to the deep compression techniques, careful choice of file formats can improve inference latency.
• Score: 4.960046610835999
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A new golden age in astronomy is upon us, dominated by data. Large astronomical surveys are broadcasting unprecedented rates of information, demanding machine learning as a critical component in modern scientific pipelines to handle the deluge of data. The upcoming Legacy Survey of Space and Time (LSST) of the Vera C. Rubin Observatory will raise the big-data bar for time-domain astronomy, with an expected 10 million alerts per-night, and generating many petabytes of data over the lifetime of the survey. Fast and efficient classification algorithms that can operate in real-time, yet robustly and accurately, are needed for time-critical events where additional resources can be sought for follow-up analyses. In order to handle such data, state-of-the-art deep learning architectures coupled with tools that leverage modern hardware accelerators are essential. We showcase how the use of modern deep compression methods can achieve a $18\times$ reduction in model size, whilst preserving classification performance. We also show that in addition to the deep compression techniques, careful choice of file formats can improve inference latency, and thereby throughput of alerts, on the order of $8\times$ for local processing, and $5\times$ in a live production setting. To test this in a live setting, we deploy this optimised version of the original time-series transformer, t2, into the community alert broking system of FINK on real Zwicky Transient Facility (ZTF) alert data, and compare throughput performance with other science modules that exist in FINK. The results shown herein emphasise the time-series transformer's suitability for real-time classification at LSST scale, and beyond, and introduce deep model compression as a fundamental tool for improving deploy-ability and scalable inference of deep learning models for transient classification.

Related papers

• sTransformer: A Modular Approach for Extracting Inter-Sequential and Temporal Information for Time-Series Forecasting [6.434378359932152]
  We review and categorize existing Transformer-based models into two main types: (1) modifications to the model structure and (2) modifications to the input data. We propose $textbfsTransformer$, which introduces the Sequence and Temporal Convolutional Network (STCN) to fully capture both sequential and temporal information. We compare our model with linear models and existing forecasting models on long-term time-series forecasting, achieving new state-of-the-art results.
  arXiv  Detail & Related papers  (2024-08-19T06:23:41Z)
• Frequency-Aware Deepfake Detection: Improving Generalizability through Frequency Space Learning [81.98675881423131]
  This research addresses the challenge of developing a universal deepfake detector that can effectively identify unseen deepfake images. Existing frequency-based paradigms have relied on frequency-level artifacts introduced during the up-sampling in GAN pipelines to detect forgeries. We introduce a novel frequency-aware approach called FreqNet, centered around frequency domain learning, specifically designed to enhance the generalizability of deepfake detectors.
  arXiv  Detail & Related papers  (2024-03-12T01:28:00Z)
• Timer: Generative Pre-trained Transformers Are Large Time Series Models [83.03091523806668]
  This paper aims at the early development of large time series models (LTSM) During pre-training, we curate large-scale datasets with up to 1 billion time points. To meet diverse application needs, we convert forecasting, imputation, and anomaly detection of time series into a unified generative task.
  arXiv  Detail & Related papers  (2024-02-04T06:55:55Z)
• Disentangling Spatial and Temporal Learning for Efficient Image-to-Video Transfer Learning [59.26623999209235]
  We present DiST, which disentangles the learning of spatial and temporal aspects of videos. The disentangled learning in DiST is highly efficient because it avoids the back-propagation of massive pre-trained parameters. Extensive experiments on five benchmarks show that DiST delivers better performance than existing state-of-the-art methods by convincing gaps.
  arXiv  Detail & Related papers  (2023-09-14T17:58:33Z)
• ARFA: An Asymmetric Receptive Field Autoencoder Model for Spatiotemporal Prediction [55.30913411696375]
  We propose an Asymmetric Receptive Field Autoencoder (ARFA) model, which introduces corresponding sizes of receptive field modules. In the encoder, we present large kernel module for globaltemporal feature extraction. In the decoder, we develop a small kernel module for localtemporal reconstruction. We construct the RainBench, a large-scale radar echo dataset for precipitation prediction, to address the scarcity of meteorological data in the domain.
  arXiv  Detail & Related papers  (2023-09-01T07:55:53Z)
• Learning Gaussian Mixture Representations for Tensor Time Series Forecasting [8.31607451942671]
  We develop a novel TTS forecasting framework, which seeks to individually model each heterogeneity component implied in the time, the location, and the source variables. Experiment results on two real-world TTS datasets verify the superiority of our approach compared with the state-of-the-art baselines.
  arXiv  Detail & Related papers  (2023-06-01T06:50:47Z)
• GC-GRU-N for Traffic Prediction using Loop Detector Data [5.735035463793008]
  We use Seattle loop detector data aggregated over 15 minutes and reframe the problem through space time. The model ranked second with the fastest inference time and a very close performance to first place (Transformers)
  arXiv  Detail & Related papers  (2022-11-13T06:32:28Z)
• Improving Astronomical Time-series Classification via Data Augmentation with Generative Adversarial Networks [1.2891210250935146]
  We propose a data augmentation methodology based on Generative Adrial Networks (GANs) to generate a variety of synthetic light curves from variable stars. The classification accuracy of variable stars is improved significantly when training with synthetic data and testing with real data.
  arXiv  Detail & Related papers  (2022-05-13T16:39:54Z)
• Paying Attention to Astronomical Transients: Introducing the Time-series Transformer for Photometric Classification [6.586394734694152]
  We develop a new transformer architecture, first proposed for natural language processing. We apply the time-series transformer to the task of photometric classification, minimising the reliance of expert domain knowledge. We achieve a logarithmic-loss of 0.507 on imbalanced data in a representative setting using data from the Photometric LSST Astronomical Time-Series Classification Challenge.
  arXiv  Detail & Related papers  (2021-05-13T10:16:13Z)
• Adaptive Latent Space Tuning for Non-Stationary Distributions [62.997667081978825]
  We present a method for adaptive tuning of the low-dimensional latent space of deep encoder-decoder style CNNs. We demonstrate our approach for predicting the properties of a time-varying charged particle beam in a particle accelerator.
  arXiv  Detail & Related papers  (2021-05-08T03:50:45Z)
• Deep Transformer Networks for Time Series Classification: The NPP Safety Case [59.20947681019466]
  An advanced temporal neural network referred to as the Transformer is used within a supervised learning fashion to model the time-dependent NPP simulation data. The Transformer can learn the characteristics of the sequential data and yield promising performance with approximately 99% classification accuracy on the testing dataset.
  arXiv  Detail & Related papers  (2021-04-09T14:26:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.