Long sequence time-series forecasting with deep learning: A survey

TL;DR: This comprehensive survey offers a meticulous examination of the privacy and security challenges inherent to GAI, and provides five pivotal perspectives essential for a comprehensive understanding of these intricacies.

TL;DR: It is proved that neglecting heterogeneity is the primary reason for generating controversies in technical approaches and an exhaustive and reproducible performance and efficiency comparison of popular models is conducted, providing insights for researchers in selecting and designing MTS forecasting models.

TL;DR: This paper proposes STGAFormer, a Graph Neural Network model that leverages transformer encoder architecture and novel gated attention modules to predict traffic flow, achieving state-of-the-art performance on four real datasets with improved MAE value of 3.82% on PeMS08 dataset.

Abstract: The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.

TL;DR: In this paper, the encoder and decoder of the RNN Encoder-Decoder model are jointly trained to maximize the conditional probability of a target sequence given a source sequence.

TL;DR: A proposal along these lines first described by Jordan (1986) which involves the use of recurrent links in order to provide networks with a dynamic memory and suggests a method for representing lexical categories and the type/token distinction is developed.

TL;DR: This paper proposed WaveNet, a deep neural network for generating audio waveforms, which is fully probabilistic and autoregressive, with the predictive distribution for each audio sample conditioned on all previous ones.