Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting

Abstract

Many real-world applications require the prediction of long sequence time-series, such as electricity consumption planning. Long sequence time-series forecasting (LSTF) demands a high prediction capacity of the model, which is the ability to capture precise long-range dependency coupling between output and input efficiently. Recent studies have shown the potential of Transformer to increase the prediction capacity. However, there are several severe issues with Transformer that prevent it from being directly applicable to LSTF, including quadratic time complexity, high memory usage, and inherent limitation of the encoder-decoder architecture. To address these issues, we design an efficient transformer-based model for LSTF, named Informer, with three distinctive characteristics: (i) a $ProbSparse$ self-attention mechanism, which achieves $O(L\log L)$ in time complexity and memory usage, and has comparable performance on sequences' dependency alignment. (ii) the self-attention distilling highlights dominating attention by halving cascading layer input, and efficiently handles extreme long input sequences. (iii) the generative style decoder, while conceptually simple, predicts the long time-series sequences at one forward operation rather than a step-by-step way, which drastically improves the inference speed of long-sequence predictions. Extensive experiments on four large-scale datasets demonstrate that Informer significantly outperforms existing methods and provides a new solution to the LSTF problem.

8 pages (main), 5 pages (appendix) and to be appeared in AAAI2021

References in corpus (10)

• Sequence to Sequence Learning with Neural Networks
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Language Models are Few-Shot Learners
• Linformer: Self-Attention with Linear Complexity
• Generating Long Sequences with Sparse Transformers
• Reformer: The Efficient Transformer
• Compressive Transformers for Long-Range Sequence Modelling
• Adaptively Truncating Backpropagation Through Time to Control Gradient Bias
• Approximate Bayesian Inference in Linear State Space Models for Intermittent Demand Forecasting at Scale
• DSTP-RNN: a dual-stage two-phase attention-based recurrent neural networks for long-term and multivariate time series prediction

Cited by in corpus (1)

• Transfer training from smaller language model