paper-with-me

Papers

Adversarial Sparse Transformer for Time Series Forecasting

2020-12-01 · NeurIPS 2020 12 · Sifan Wu, Xi Xiao, Qianggang Ding, Peilin Zhao, Ying WEI, Junzhou Huang

Many approaches have been proposed for time series forecasting, in light of its significance in wide applications including business demand prediction. However, the existing methods suffer from two key limitations. Firstly, most point prediction models only predict an exact value of each time step without flexibility, which can hardly capture the stochasticity of data. Even probabilistic prediction using the likelihood estimation suffers these problems in the same way. Besides, most of them use the auto-regressive generative mode, where ground-truth is provided during training and replaced by the network’s own one-step ahead output during inference, causing the error accumulation in inference. Thus they may fail to forecast time series for long time horizon due to the error accumulation. To solve these issues, in this paper, we propose a new time series forecasting model -- Adversarial Sparse Transformer (AST), based on Generated Adversarial Networks (GANs). Specifically, AST adopts a Sparse Transformer as the generator to learn a sparse attention map for time series forecasting, and uses a discriminator to improve the prediction performance from sequence level. Extensive experiments on several real-world datasets show the effectiveness and efficiency of our method.

📄 PDF Abstract BibTeX

Code (1)

hihihihiwsf/AST pytorch

Tasks

Multivariate Time Series ForecastingPredictionProbabilistic Time Series ForecastingTime SeriesTime Series AnalysisTime Series Forecasting

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Sparse-VQ Transformer: An FFN-Free Framework with Vector Quantization for Enhanced Time Series Forecasting

2024-02-08 · Yanjun Zhao, Tian Zhou, Chao Chen, Liang Sun 외

Time series analysis is vital for numerous applications, and transformers have become increasingly prominent in this domain. Leading methods customize the transformer architecture from NLP and CV, utilizing a patching te…

Computational EfficiencyMultivariate Time Series ForecastingQuantizationTime Series+2

Robust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense Mechanisms

2022-07-19 · Linbo Liu, Youngsuk Park, Trong Nghia Hoang, Hilaf Hasson 외

This work studies the threats of adversarial attack on multivariate probabilistic forecasting models and viable defense mechanisms. Our studies discover a new attack pattern that negatively impact the forecasting of a ta…

Adversarial AttackMultivariate Time Series ForecastingTime SeriesTime Series Analysis+2

Long-term series forecasting with Query Selector -- efficient model of sparse attention

2021-07-19 · Jacek Klimek, Jakub Klimek, Witold Kraskiewicz, Mateusz Topolewski

Various modifications of TRANSFORMER were recently used to solve time-series forecasting problem. We propose Query Selector - an efficient, deterministic algorithm for sparse attention matrix. Experiments show it achieve…

Multivariate Time Series ForecastingTime SeriesTime Series AnalysisTime Series Forecasting

ForecastGAN: A Decomposition-Based Adversarial Framework for Multi-Horizon Time Series Forecasting

2025-11-06 · Syeda Sitara Wishal Fatima, Afshin Rahimi arxiv

Time series forecasting is essential across domains from finance to supply chain management. This paper introduces ForecastGAN, a novel decomposition based adversarial framework addressing limitations in existing approac…

Time Series Forecasting

Fre-CW: Targeted Attack on Time Series Forecasting using Frequency Domain Loss

2025-08-12 · Naifu Feng, Lixing Chen, Junhua Tang, Hua Ding 외 arxiv

Transformer-based models have made significant progress in time series forecasting. However, a key limitation of deep learning models is their susceptibility to adversarial attacks, which has not been studied enough in t…

Time Series ForecastingTime Series PredictionAdversarial Robustness