161 lines
16 KiB
BibTeX
161 lines
16 KiB
BibTeX
|
||
@article{zhang_crossformer_2023,
|
||
title = {{CROSSFORMER}: {TRANSFORMER} {UTILIZING} {CROSS}- {DIMENSION} {DEPENDENCY} {FOR} {MULTIVARIATE} {TIME} {SERIES} {FORECASTING}},
|
||
abstract = {Recently many deep models have been proposed for multivariate time series (MTS) forecasting. In particular, Transformer-based models have shown great potential because they can capture long-term dependency. However, existing Transformerbased models mainly focus on modeling the temporal dependency (cross-time dependency) yet often omit the dependency among different variables (crossdimension dependency), which is critical for MTS forecasting. To fill the gap, we propose Crossformer, a Transformer-based model utilizing cross-dimension dependency for MTS forecasting. In Crossformer, the input MTS is embedded into a 2D vector array through the Dimension-Segment-Wise (DSW) embedding to preserve time and dimension information. Then the Two-Stage Attention (TSA) layer is proposed to efficiently capture the cross-time and cross-dimension dependency. Utilizing DSW embedding and TSA layer, Crossformer establishes a Hierarchical Encoder-Decoder (HED) to use the information at different scales for the final forecasting. Extensive experimental results on six real-world datasets show the effectiveness of Crossformer against previous state-of-the-arts.},
|
||
language = {en},
|
||
author = {Zhang, Yunhao and Yan, Junchi},
|
||
year = {2023},
|
||
file = {PDF:/home/alex/Zotero/storage/NM9CETJS/Zhang and Yan - 2023 - CROSSFORMER TRANSFORMER UTILIZING CROSS- DIMENSION DEPENDENCY FOR MULTIVARIATE TIME SERIES FORECAST.pdf:application/pdf},
|
||
}
|
||
|
||
@misc{shao_exploring_2023,
|
||
title = {Exploring {Progress} in {Multivariate} {Time} {Series} {Forecasting}: {Comprehensive} {Benchmarking} and {Heterogeneity} {Analysis}},
|
||
shorttitle = {Exploring {Progress} in {Multivariate} {Time} {Series} {Forecasting}},
|
||
url = {http://arxiv.org/abs/2310.06119},
|
||
abstract = {Multivariate Time Series (MTS) widely exists in real-word complex systems, such as traffic and energy systems, making their forecasting crucial for understanding and influencing these systems. Recently, deep learning-based approaches have gained much popularity for effectively modeling temporal and spatial dependencies in MTS, specifically in Long-term Time Series Forecasting (LTSF) and Spatial-Temporal Forecasting (STF). However, the fair benchmarking issue and the choice of technical approaches have been hotly debated in related work. Such controversies significantly hinder our understanding of progress in this field. Thus, this paper aims to address these controversies to present insights into advancements achieved. To resolve benchmarking issues, we introduce BasicTS, a benchmark designed for fair comparisons in MTS forecasting. BasicTS establishes a unified training pipeline and reasonable evaluation settings, enabling an unbiased evaluation of over 30 popular MTS forecasting models on more than 18 datasets. Furthermore, we highlight the heterogeneity among MTS datasets and classify them based on temporal and spatial characteristics. We further prove that neglecting heterogeneity is the primary reason for generating controversies in technical approaches. Moreover, based on the proposed BasicTS and rich heterogeneous MTS datasets, we conduct an exhaustive and reproducible performance and efficiency comparison of popular models, providing insights for researchers in selecting and designing MTS forecasting models.},
|
||
urldate = {2024-10-10},
|
||
publisher = {arXiv},
|
||
author = {Shao, Zezhi and Wang, Fei and Xu, Yongjun and Wei, Wei and Yu, Chengqing and Zhang, Zhao and Yao, Di and Jin, Guangyin and Cao, Xin and Cong, Gao and Jensen, Christian S. and Cheng, Xueqi},
|
||
month = oct,
|
||
year = {2023},
|
||
note = {arXiv:2310.06119},
|
||
keywords = {Computer Science - Artificial Intelligence, Computer Science - Machine Learning},
|
||
file = {Preprint PDF:/home/alex/Zotero/storage/7EFZ5IT6/Shao et al. - 2023 - Exploring Progress in Multivariate Time Series Forecasting Comprehensive Benchmarking and Heterogen.pdf:application/pdf;Snapshot:/home/alex/Zotero/storage/W6RNWBLM/2310.html:text/html},
|
||
}
|
||
|
||
@misc{nie_time_2023,
|
||
title = {A {Time} {Series} is {Worth} 64 {Words}: {Long}-term {Forecasting} with {Transformers}},
|
||
shorttitle = {A {Time} {Series} is {Worth} 64 {Words}},
|
||
url = {http://arxiv.org/abs/2211.14730},
|
||
abstract = {We propose an efficient design of Transformer-based models for multivariate time series forecasting and self-supervised representation learning. It is based on two key components: (i) segmentation of time series into subseries-level patches which are served as input tokens to Transformer; (ii) channel-independence where each channel contains a single univariate time series that shares the same embedding and Transformer weights across all the series. Patching design naturally has three-fold benefit: local semantic information is retained in the embedding; computation and memory usage of the attention maps are quadratically reduced given the same look-back window; and the model can attend longer history. Our channel-independent patch time series Transformer (PatchTST) can improve the long-term forecasting accuracy significantly when compared with that of SOTA Transformer-based models. We also apply our model to self-supervised pre-training tasks and attain excellent fine-tuning performance, which outperforms supervised training on large datasets. Transferring of masked pre-trained representation on one dataset to others also produces SOTA forecasting accuracy. Code is available at: https://github.com/yuqinie98/PatchTST.},
|
||
urldate = {2024-10-10},
|
||
publisher = {arXiv},
|
||
author = {Nie, Yuqi and Nguyen, Nam H. and Sinthong, Phanwadee and Kalagnanam, Jayant},
|
||
month = mar,
|
||
year = {2023},
|
||
note = {arXiv:2211.14730},
|
||
keywords = {Computer Science - Artificial Intelligence, Computer Science - Machine Learning},
|
||
file = {Preprint PDF:/home/alex/Zotero/storage/DG4ZJCWV/Nie et al. - 2023 - A Time Series is Worth 64 Words Long-term Forecasting with Transformers.pdf:application/pdf;Snapshot:/home/alex/Zotero/storage/H6XGVBY6/2211.html:text/html},
|
||
}
|
||
|
||
@misc{lim_temporal_2020,
|
||
title = {Temporal {Fusion} {Transformers} for {Interpretable} {Multi}-horizon {Time} {Series} {Forecasting}},
|
||
url = {http://arxiv.org/abs/1912.09363},
|
||
abstract = {Multi-horizon forecasting problems often contain a complex mix of inputs -- including static (i.e. time-invariant) covariates, known future inputs, and other exogenous time series that are only observed historically -- without any prior information on how they interact with the target. While several deep learning models have been proposed for multi-step prediction, they typically comprise black-box models which do not account for the full range of inputs present in common scenarios. In this paper, we introduce the Temporal Fusion Transformer (TFT) -- a novel attention-based architecture which combines high-performance multi-horizon forecasting with interpretable insights into temporal dynamics. To learn temporal relationships at different scales, the TFT utilizes recurrent layers for local processing and interpretable self-attention layers for learning long-term dependencies. The TFT also uses specialized components for the judicious selection of relevant features and a series of gating layers to suppress unnecessary components, enabling high performance in a wide range of regimes. On a variety of real-world datasets, we demonstrate significant performance improvements over existing benchmarks, and showcase three practical interpretability use-cases of TFT.},
|
||
urldate = {2024-10-10},
|
||
publisher = {arXiv},
|
||
author = {Lim, Bryan and Arik, Sercan O. and Loeff, Nicolas and Pfister, Tomas},
|
||
month = sep,
|
||
year = {2020},
|
||
note = {arXiv:1912.09363},
|
||
keywords = {Computer Science - Machine Learning, Statistics - Machine Learning},
|
||
file = {Preprint PDF:/home/alex/Zotero/storage/2R2H34KB/Lim et al. - 2020 - Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting.pdf:application/pdf;Snapshot:/home/alex/Zotero/storage/ETDAYW36/1912.html:text/html},
|
||
}
|
||
|
||
@article{hochreiter_long_1997,
|
||
title = {Long {Short}-{Term} {Memory}},
|
||
volume = {9},
|
||
issn = {0899-7667, 1530-888X},
|
||
url = {https://direct.mit.edu/neco/article/9/8/1735-1780/6109},
|
||
doi = {10.1162/neco.1997.9.8.1735},
|
||
abstract = {Learningtostoreinformationoverextendedtimeintervalsviarecurrentbackpropagation takesaverylongtime,mostlyduetoinsu cient,decayingerrorbackow.Webrieyreview Hochreiter's1991analysisofthisproblem,thenaddressitbyintroducinganovel,e cient, gradient-basedmethodcalled{\textbackslash}LongShort-TermMemory"(LSTM).Truncatingthegradient wherethisdoesnotdoharm,LSTMcanlearntobridgeminimaltimelagsinexcessof1000 discretetimestepsbyenforcingconstanterrorowthrough{\textbackslash}constanterrorcarrousels"within specialunits.Multiplicativegateunitslearntoopenandcloseaccesstotheconstanterror ow.LSTMislocalinspaceandtime;itscomputationalcomplexitypertimestepandweight isO(1).Ourexperimentswitharticialdatainvolvelocal,distributed,real-valued,andnoisy patternrepresentations.IncomparisonswithRTRL,BPTT,RecurrentCascade-Correlation, Elmannets,andNeuralSequenceChunking,LSTMleadstomanymoresuccessfulruns,and learnsmuchfaster.LSTMalsosolvescomplex,articiallongtimelagtasksthathavenever beensolvedbypreviousrecurrentnetworkalgorithms.},
|
||
language = {en},
|
||
number = {8},
|
||
urldate = {2024-10-10},
|
||
journal = {Neural Computation},
|
||
author = {Hochreiter, Sepp and Schmidhuber, Jürgen},
|
||
month = nov,
|
||
year = {1997},
|
||
pages = {1735--1780},
|
||
file = {PDF:/home/alex/Zotero/storage/CZSV2ASE/Hochreiter and Schmidhuber - 1997 - Long Short-Term Memory.pdf:application/pdf},
|
||
}
|
||
|
||
@misc{cho_learning_2014,
|
||
title = {Learning {Phrase} {Representations} using {RNN} {Encoder}-{Decoder} for {Statistical} {Machine} {Translation}},
|
||
url = {http://arxiv.org/abs/1406.1078},
|
||
abstract = {In this paper, we propose a novel neural network model called RNN Encoder-Decoder that consists of two recurrent neural networks (RNN). One RNN encodes a sequence of symbols into a fixed-length vector representation, and the other decodes the representation into another sequence of symbols. The encoder and decoder of the proposed model are jointly trained to maximize the conditional probability of a target sequence given a source sequence. The performance of a statistical machine translation system is empirically found to improve by using the conditional probabilities of phrase pairs computed by the RNN Encoder-Decoder as an additional feature in the existing log-linear model. Qualitatively, we show that the proposed model learns a semantically and syntactically meaningful representation of linguistic phrases.},
|
||
urldate = {2024-10-10},
|
||
publisher = {arXiv},
|
||
author = {Cho, Kyunghyun and Merrienboer, Bart van and Gulcehre, Caglar and Bahdanau, Dzmitry and Bougares, Fethi and Schwenk, Holger and Bengio, Yoshua},
|
||
month = sep,
|
||
year = {2014},
|
||
note = {arXiv:1406.1078},
|
||
keywords = {Computer Science - Computation and Language, Computer Science - Machine Learning, Computer Science - Neural and Evolutionary Computing, Statistics - Machine Learning},
|
||
file = {Preprint PDF:/home/alex/Zotero/storage/E8WMK2IN/Cho et al. - 2014 - Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation.pdf:application/pdf;Snapshot:/home/alex/Zotero/storage/6PTCL8LW/1406.html:text/html},
|
||
}
|
||
|
||
@incollection{hutter_general_2021,
|
||
address = {Cham},
|
||
title = {A {General} {Machine} {Learning} {Framework} for {Survival} {Analysis}},
|
||
volume = {12459},
|
||
isbn = {978-3-030-67663-6 978-3-030-67664-3},
|
||
url = {https://link.springer.com/10.1007/978-3-030-67664-3_10},
|
||
language = {en},
|
||
urldate = {2024-10-14},
|
||
booktitle = {Machine {Learning} and {Knowledge} {Discovery} in {Databases}},
|
||
publisher = {Springer International Publishing},
|
||
author = {Bender, Andreas and Rügamer, David and Scheipl, Fabian and Bischl, Bernd},
|
||
editor = {Hutter, Frank and Kersting, Kristian and Lijffijt, Jefrey and Valera, Isabel},
|
||
year = {2021},
|
||
doi = {10.1007/978-3-030-67664-3_10},
|
||
note = {Series Title: Lecture Notes in Computer Science},
|
||
pages = {158--173},
|
||
file = {Submitted Version:/home/alex/Zotero/storage/WQIHZ7IP/Bender et al. - 2021 - A General Machine Learning Framework for Survival Analysis.pdf:application/pdf},
|
||
}
|
||
|
||
@book{hutter_machine_2021,
|
||
address = {Cham},
|
||
series = {Lecture {Notes} in {Computer} {Science}},
|
||
title = {Machine {Learning} and {Knowledge} {Discovery} in {Databases}: {European} {Conference}, {ECML} {PKDD} 2020, {Ghent}, {Belgium}, {September} 14–18, 2020, {Proceedings}, {Part} {III}},
|
||
volume = {12459},
|
||
copyright = {https://www.springernature.com/gp/researchers/text-and-data-mining},
|
||
isbn = {978-3-030-67663-6 978-3-030-67664-3},
|
||
shorttitle = {Machine {Learning} and {Knowledge} {Discovery} in {Databases}},
|
||
url = {https://link.springer.com/10.1007/978-3-030-67664-3},
|
||
language = {en},
|
||
urldate = {2024-10-14},
|
||
publisher = {Springer International Publishing},
|
||
editor = {Hutter, Frank and Kersting, Kristian and Lijffijt, Jefrey and Valera, Isabel},
|
||
year = {2021},
|
||
doi = {10.1007/978-3-030-67664-3},
|
||
file = {Submitted Version:/home/alex/Zotero/storage/JMVJMLJ5/Hutter et al. - 2021 - Machine Learning and Knowledge Discovery in Databases European Conference, ECML PKDD 2020, Ghent, B.pdf:application/pdf},
|
||
}
|
||
|
||
@misc{taylor_forecasting_2017,
|
||
title = {Forecasting at scale},
|
||
copyright = {http://creativecommons.org/licenses/by/4.0/},
|
||
url = {https://peerj.com/preprints/3190v2},
|
||
doi = {10.7287/peerj.preprints.3190v2},
|
||
abstract = {Forecasting is a common data science task that helps organizations with capacity planning, goal setting, and anomaly detection. Despite its importance, there are serious challenges associated with producing reliable and high quality forecasts –especially when there are a variety of time series and analysts with expertise in time series modeling are relatively rare. To address these challenges, we describe a practical approach to forecasting “at scale” that combines configurable models with analyst-in-the-loop performance analysis. We propose a modular regression model with interpretable parameters that can be intuitively adjusted by analysts with domain knowledge about the time series. We describe performance analyses to compare and evaluate forecasting procedures, and automatically flag forecasts for manual review and adjustment. Tools that help analysts to use their expertise most effectively enable reliable, practical forecasting of business time series.},
|
||
language = {en},
|
||
urldate = {2024-10-14},
|
||
publisher = {PeerJ Preprints},
|
||
author = {Taylor, Sean J and Letham, Benjamin},
|
||
month = sep,
|
||
year = {2017},
|
||
file = {PDF:/home/alex/Zotero/storage/GK5AIG2V/Taylor and Letham - 2017 - Forecasting at scale.pdf:application/pdf},
|
||
}
|
||
|
||
@misc{alexandrov_gluonts_2019,
|
||
title = {{GluonTS}: {Probabilistic} {Time} {Series} {Models} in {Python}},
|
||
shorttitle = {{GluonTS}},
|
||
url = {http://arxiv.org/abs/1906.05264},
|
||
abstract = {We introduce Gluon Time Series (GluonTS, available at https://gluon-ts.mxnet.io), a library for deep-learning-based time series modeling. GluonTS simplifies the development of and experimentation with time series models for common tasks such as forecasting or anomaly detection. It provides all necessary components and tools that scientists need for quickly building new models, for efficiently running and analyzing experiments and for evaluating model accuracy.},
|
||
urldate = {2024-10-14},
|
||
publisher = {arXiv},
|
||
author = {Alexandrov, Alexander and Benidis, Konstantinos and Bohlke-Schneider, Michael and Flunkert, Valentin and Gasthaus, Jan and Januschowski, Tim and Maddix, Danielle C. and Rangapuram, Syama and Salinas, David and Schulz, Jasper and Stella, Lorenzo and Türkmen, Ali Caner and Wang, Yuyang},
|
||
month = jun,
|
||
year = {2019},
|
||
note = {arXiv:1906.05264},
|
||
keywords = {Computer Science - Machine Learning, Statistics - Machine Learning},
|
||
file = {Preprint PDF:/home/alex/Zotero/storage/JP9K74A8/Alexandrov et al. - 2019 - GluonTS Probabilistic Time Series Models in Python.pdf:application/pdf;Snapshot:/home/alex/Zotero/storage/RJYSBT29/1906.html:text/html},
|
||
}
|
||
|
||
@misc{lightningai_pytorch_2024,
|
||
title = {{PyTorch} {Lightning}},
|
||
url = {https://www.pytorchlightning.ai},
|
||
urldate = {2024-10-14},
|
||
author = {lightning.ai},
|
||
year = {2024},
|
||
}
|