Comments (2)
感谢您的关注!时间和空间信息作为embedding去自适应地学习是更加合理的做法。
数据集本身并不提供时间和空间的Attributes。
虽然我们可以通过一些特殊方法(例如空间维度上使用Node2Vec,时间维度上使用one-hot编码)来产生特征,但我们并不能确保这样的特征是不是合适的。
例如,空间维度的embedding之间的相似度,通常代表着时间序列之间的相似度。而通过特殊方法产生的结果不一定是最优的。
从效果来看不如让模型自适应的去学习时间和空间的embedding。
模型的输入数据是一个[B, L, N, C]
的Tensor,其中B=batch size
, L=sequence length
, N=number of variates
, C=features of each variate at each time step
。
C
的第一维通常是传感器测量出来的值,例如Traffic Speed, Traffic Flow。后续的维度通常是Temporal Features。例如第二维是Time in Day,第三维是Day in Week,后续类推。
更详细的数据预处理可以参考:这一行 ~ 这一行。
from stid.
感谢您详尽的回复,完美解答了我的疑惑!非常solid的工作,follow学习一下~
from stid.
Related Issues (18)
- Code HOT 1
- Questions about the time of day embedding HOT 3
- 请教一下可视化的代码,能否分享呢?在二维空间中的embedding的可视化的过程 HOT 3
- 请问scaler pkl文件在哪里? HOT 1
- 小白请教是否没有公开模型测试部分的代码 HOT 1
- 请问为什么没有用PEMS03呢?谢谢 HOT 1
- 我感觉预处理完数据后,使用run.py依旧没有办法执行到主函数 HOT 3
- sth about my own dataset HOT 2
- node_emb为什么不和his_data数据交互呢? HOT 4
- How to get prediction with shape [B, L, N, C]
- Question about T^TiD and T^DiW HOT 1
- 关于模型维度的处理 HOT 6
- 有关于空间Identity HOT 5
- The time series embedding in file "stid_arch.py" HOT 2
- Some questions about the Visualization Section in the paper. HOT 3
- stid_arch.py代码问题 HOT 1
- easy-torch和pytorch1.10.0冲突 HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from stid.