← Search

Jieqi Peng

2 accepted papers

2022

Jump Self-attention: Capturing High-order Statistics in Transformers

NeurIPS 2022accept

The recent success of Transformer has benefited many real-world applications, with its capability of building long dependency through pairwise dot-products. However, the strong assumption that elements are directly attentive to each other limits the performance of tasks with high-order dependencies…

Cited by 3SourcePDFScholar
2021

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

AAAI 2021technical

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 out…