Comments (6)
Yes, MLP in our model is utilized to learn the series (as a token) representations, which are aggregated from past observations and projected into future predictions.
Position embedding is needed in the vanilla Transformer since the attention is permutation-invariant, however, MLP is not (as we mentioned in our paper:"since the order of sequence is already stored in the permutation of neurons of feed-forward network").
from itransformer.
A visualization example: the sequential modeling is reflected by the permutation of MLP neurons.
from itransformer.
A related issue can be helpful for you: #13
from itransformer.
Thanks for your reply! As I see #13, you say 'distinguishing variate is not essential but it is essential to keep them independent'. Among the temporal dimensions, however, a well-accepted logic is p(x_t|x_{t-1}) or p(x_t|x_{1:t-1}) and they are not independent. Seems like this paper gives up modeling this kind of sequential dependency but focuses on the correlations between variables. Does it support that relations between variables are more significant?
from itransformer.
Very interesting!
We think they are both important to achieve good MTSF performance. However, the relations of variates can be hardly considered in the vanilla Transformer. At the beginning of embedding, the variates are projected into the channels of embedding. It ignores the problem of inconsistent physical measurements and can fail to maintain the independence of variates, let alone capture and utilize the multivariate correlation, which is essential for forecasting with numerous variates, as well as in complicated systems driven by the latent physical process (such as meteorological systems).
In addition, even if the FFN and layernorm seem simpler than attention blocks, they are efficient and competent in learning the temporal dependency of a series, which can be traced back to statistical forecasters such as ARIMA and Holt-Winter. They also have no problems with inconsistent measurements since they work on the time points of the same variates, and have an enlarged respective field as the whole lookback series can be embeded as the variate token.
from itransformer.
Good views. Thanks!
from itransformer.
Related Issues (20)
- How to get prediction without normalized? HOT 1
- Regarding the figures in the article HOT 3
- StandardScaler vs iTransformer normalization HOT 1
- encoder模块和decoder模块 是否做过对比 HOT 1
- Dimension issue for backtesting HOT 1
- 怎么添加自己的数据集 HOT 1
- About the radar figure HOT 1
- 关于输入数据的标准化处理 HOT 1
- 预测结果很差? HOT 8
- i have a question HOT 1
- Market dataset HOT 1
- 预测结果不好 HOT 3
- Memory Footprint? HOT 1
- 当运行到训练的循环时,内存消耗骤增
- train_loader invocation encountered "RuntimeError: stack expects each tensor to be equal size, but got [35, 34] at entry 0 and [0, 34] at entry 1" HOT 1
- ValueError: could not convert string to float: '2020-01-01 00:20:00' HOT 1
- Error when using a Custom dataset with weekly frequency HOT 1
- Question: Support for Dynamic Categorical Inputs in iTransformer HOT 2
- 无法重现论文中的结果 HOT 2
- How to visualize the results? HOT 5
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 itransformer.