Ccloud's

Empyrean bright moon is always in the sky.

AutoSTG:Neural Architecture Search for Predictions of Spatio-Temporal Graphs

An introduction to AutoSTG

The blog introduces the paper : AutoSTG IntroductionA growing number of ST neural networks have been proposed for STG prediction, by leveraging the capability of modeling ST correlations, these m......

AutoST:Efficient Neural Architecture Search for Spatio-Temporal Prediction

An introduction to AutoST

The blog introduces the paper : AutoST:Efficient Neural Architecture Search for Spatio-Temporal Prediction Introduction How to find the optimal neural architecture at various scenarios in cities ......

AutoCTS+:Joint Neural Architecture and Hyperparameter Search for Correlated Times Series Forecasting

An introduction to AutoCTS+

The blog introduces the paper : AutoCTS+ Introduction Leveraging the powerful feature extraction capabilities of deep learning models, expert-designed ST-blocks have been proposed to capture spat......

DARTS:Differentiable Architecture Search

An introduction to DARTS

The blog introduces the paper : DARTS IntroductionThe conventional architecture search algorithms are computationally demanding despite their remarkable performance. An inherent cause of ineffici......

Python学习资料分享

书籍分享

Python作为一门万物皆对象的语言,其一部分语法糖来自于对象的特点,如魔法方法、迭代器。还有一部分来自于函数的特点,如Lambda表达式、生成器。在此分别推荐一本初级和一本高级用法的书,以便快速查询。 Python官方文档 Python程序设计基础 [美] (Tony Gaddis) Python高级编程 [波兰] (Michal......

Triformer:Triangular,Variable-Specific Attentions for Long Sequence

An introduction to Triformer

The blog introduces the paper : Triformer Introduction Recent studies show that attentions are able to capture better long term dependencies. But For a time series of timestamps, canonical self-......

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

An introduction to Informer

The blog introduces the paper : Informer Introduction The conventional time-series forecasting models perform well in short-term prediction tasks. The increasingly long sequences strain the mode......

STTN:Spatial-Temporal Transformer Networks for Traffic Flow Forecasting

An introduction to STTN

The blog introduces the paper : STTN Introduction Models with stationary assumption are not practical in long-term forecasting, as traffic flows are highly dynamical in nature. CNN-based and RNN......

ST-GRAT:A Novel Spatio-temporal Graph Attention Network for Accurately Forecasting Dynamically Changing Road Speed

An introduction to ST-GRAT

The blog introduces the paper : ST-GRAT Introduction A method for predicting traffic speed should not only find spatial-temporal dependencies among roads but also understand how these dependenc......

Attention Is All You Need

Transformer

The blog introduces the paper : Attention is all you need Introduction Recurrent models and encoder-decoder architectures are widely used so that numerous efforts have continued to push their bou......